No entries match these filters. Clear filters
Gemini CLI gains experimental model steering: inject real-time guidance into a running agent via modelSteering in settings.json
└──▷ USE IT
Enable model steering once in your settings file so all future long-running agent sessions accept mid-task hints.
json
copy
{
"experimental": {
"modelSteering": true
}
}
While the agent is refactoring code and heads down the wrong path, steer it without restarting the task.
📍 /settings
# Search for Model Steering , set to true
# Then start your task:
# › Refactor the database service
# (spinner visible) type:
# Actually, the utilities are in src/common/utils.
# Press Enter — CLI acknowledges and injects the hint into the next turn.
Adds experimental.modelSteering key to settings.json to enable real-time steering hints injected into a running agent's context mid-task (disabled by default). Not checked yet Adds Model Steering toggle accessible via the /settings command as an alternative to editing settings.json directly. Not checked yet New model steering capability lets practitioners type free-text hints while the agent spinner is active — correcting paths, skipping steps, adding context, or redirecting effort — without stopping and restarting the session. Not checked yet Steering hints trigger a two-phase response: a fast small-model acknowledgment confirming receipt, then context injection at the agent's next turn with plan re-evaluation and minimal-diff task updates. Not checked yet
4 details in Everything
gemini-cli v0.55.1 adds tool registry discovery, an eval coverage report command, and a Cloud Run Cloud Run Google's managed container runtime that executes stateless workloads on demand, scaling to zero when idle, so tools can deploy without managing servers or paying for idle capacity. -based caretaker triage pipeline
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.55.1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.55.1
Adds feat(evals) eval coverage report command for measuring evaluation coverage across the codebase. Not checked yet Adds tool registry discovery, enabling the CLI to find and enumerate registered tools automatically. Not checked yet Introduces a Cloud Run webhook ingestion service for the caretaker agent, enabling automated issue intake from GitHub. Not checked yet Adds a caretaker triage Cloud Run job workflow with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -driven orchestrator, prompt hill-climbing, and automatic pre-close commenting. Not checked yet Adds a caretaker evaluation framework with a judge runner, local golden issue collection, and Firestore sync tools for offline triage quality measurement. Not checked yet
+6 more
show less
Adds issue comment handling and re-triage workflow in the caretaker ingestion pipeline. Not checked yet Implements a PR-generator agent with an Antigravity runner, iterative bug-fixing state machine, Cloud Run job, Firestore dual-locking, and Workflows infrastructure. Not checked yet Publishes workable spec events to a ready-for-code Pub/Sub topic from the caretaker pipeline. Not checked yet Adds a GCP deployment script for caretaker agent services. Not checked yet Updates Firestore schema with error and pr_number fields for caretaker triage tracking. Not checked yet Bumps node google-auth-library to version 10.9.0. Not checked yet
11 details in Everything
gemini-cli v0.53.0 adds LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. triage orchestration, eval coverage reporting, and sandbox security hardening.
New LLM triage orchestrator with container build setup for caretaker triage workflows. Not checked yet New command for generating evaluation coverage reports. Not checked yet Enforces workspace trust and task isolation in the A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. server. Not checked yet Aligns macOS Seatbelt profiles with the deny-default model. Not checked yet Mitigates infinite ReAct and prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. loops. Not checked yet
5 details in Everything
gemini-cli v0.53.0 adds an eval coverage report command and an LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. triage orchestrator.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.53.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.53.0
Adds eval coverage report command to surface evaluation coverage metrics. Not checked yet Implements an LLM triage orchestrator for automated issue triage workflows. Not checked yet
2 details in Everything
Gemini CLI v0.50.0 adds tool registry discovery for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. integrations.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.50.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.50.0
gemini-cli v0.49.0 adds GDC air-gapped auth, a new eval:inventory command, and JSON output for eval inventory.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.49.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.49.0
└──▷ TRY IT
List available eval sources in a project in a CI pipeline — pipe structured output structured output Forcing a model's response to match a given format or JSON schema, so software can parse it reliably instead of hoping the text is well formed. to other tools.
copy
$ gemini eval:inventory --output-format json
Supports GDC air-gapped Service Identity authentication after auth library update, enabling Gemini CLI use in isolated/air-gapped Google Distributed Cloud environments. Not checked yet Adds new eval:inventory CLI command to enumerate and report on available eval sources. Not checked yet Adds JSON output mode for eval:inventory, enabling machine-readable reporting for pipeline integration. Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! The coreTools config setting is migrated to tools.core; existing configurations using coreTools will need to be updated.
Gemini CLI v0.47.0 adds Antigravity CLI migration commands and promotes browser agent to stable.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.47.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.47.0
Adds documentation and migration commands for the Antigravity CLI transition. Not checked yet Promotes browser agent out of experimental status (now generally available). Not checked yet Updates auto model-selection mode to use Gemini 3.5 Flash when the flag is enabled. Not checked yet
3 details in Everything
gemini-cli v0.45.0 exposes A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. usage metadata and updates default auto routing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.45.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.45.0
Exposes usage metadata for A2A (agent-to-agent) interactions, giving practitioners visibility into token and resource consumption across agent calls. Not checked yet Updates default auto routing behavior for model selection. Not checked yet
2 details in Everything
gemini-cli v0.44.0 adds unified Auto mode, Sublime Text/Emacs editor support, RAG RAG Retrieval-augmented generation: looking up relevant documents and adding them to the prompt before the model answers. It grounds responses in private or current data without retraining. debug logging, and new AgentSession invocation wiring.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.44.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.44.0
Merges multiple Auto modes into a single unified Auto mode, simplifying permission-level selection. Not checked yet Adds Sublime Text and Emacs Client as supported external editors with improved error messages. Not checked yet Exposes RAG snippets to the local log file for debugging retrieval-augmented generation retrieval-augmented generation Retrieval-augmented generation: looking up relevant documents and adding them to the prompt before the model answers. It grounds responses in private or current data without retraining. context. Not checked yet Adds adk.agentSessionSubagentEnabled flag to control agent session subagent behavior. Not checked yet Introduces LocalSessionInvocation and RemoteSessionInvocation for agent session management. Not checked yet
+3 more
show less
Wires AgentSession invocations into the agent-tool, enabling session-based agent orchestration. Not checked yet Changes agent registration to first-wins priority, with project-level agents taking precedence. Not checked yet Adds agent-tui and tui-tester skills for agent terminal UI testing. Not checked yet
8 details in Everything
gemini-cli v0.43.0 adds session export/import, machine hostname display, shell safety evals, and new subagent protocols.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.43.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.43.0
Adds session export to file and import via flag, enabling portable session handoff and replay. Not checked yet Displays machine hostname in the CLI interface for easier identification in multi-host workflows. Not checked yet Adds shell command safety evaluations to assess risky command patterns. Not checked yet Introduces LocalSubagentProtocol behind AgentProtocol for local subagent orchestration. Not checked yet Introduces RemoteSubagentProtocol behind AgentProtocol for remote subagent orchestration. Not checked yet
+4 more
show less
Prefixes tool call IDs with tool names to support tool rendering in ACP-compliant IDEs. Not checked yet Introduces an adaptive token calculator for more accurate content size estimation in context management. Not checked yet Enables NumericalRouter when using dynamic model configs for smarter model routing. Not checked yet Improves context snapshotter with enhancements to snapshot handling. Not checked yet
9 details in Everything
gemini-cli v0.42.0 adds session deletion, voice mode UX, Gemma 4 models, auto memory, and several new CLI subcommands.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.42.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.42.0
└──▷ TRY IT
Exit and simultaneously delete the current session to clean up session state — useful in CI or scripted workflows.
copy
$ gemini /exit --delete
List all available slash commands at any point in a session to discover what's usable.
copy
$ gemini /commands list
Uninstall an extension using the new delete alias instead of the longer uninstall subcommand.
copy
$ gemini /extensions delete <extension-name>
Adds --delete flag to the /exit command to delete the current session on exit. Not checked yet Adds list subcommand to /commands for discovering available commands. Not checked yet Adds delete as an alias for /extensions uninstall to remove extensions. Not checked yet Enables Gemma 4 models by default via the Gemini API. Not checked yet Adds microphone UI and updated placeholder for voice mode. Not checked yet
+6 more
show less
Adds wave animation visual feedback during voice mode. Not checked yet Adds a privacy and compliance UX warning for the Gemini Live backend. Not checked yet Adds Auto Memory inbox flow with a canonical-patch contract for persistent memory management. Not checked yet Adds a minimal V8 heap snapshot utility for memory diagnostics. Not checked yet Allows non-HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. proxy URLs to support container environments. Not checked yet Respects logPrompts flag to control logging of sensitive fields. Not checked yet
11 details in Everything
gemini-cli v0.41.0 adds real-time voice mode, Gemma 4 model support, persistent auto-memory, and enhanced shell command validation.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.41.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.41.0
└──▷ TRY IT
Pin a reproducible session UUID UUID A universally unique identifier, usually a 128-bit value used to identify an object across systems. It is designed to make independently generated identifiers unlikely to collide. for audit logging or replay — pass the new flag to correlate CLI activity with external records.
copy
$ gemini --session-id <your-uuid> 'Run a recon summary on <target>'
New real-time voice mode with both cloud and local backends for hands-free interaction. Not checked yet Adds support for Gemma 4 models Experimental as an available model choice. Not checked yet Persistent auto-memory scratchpad enables skill extraction across sessions. Not checked yet Enhanced shell command validation and a new core tools allowlist for tighter execution control. Not checked yet Secure .env loading and enforced workspace trust in headless mode. Not checked yet
+4 more
show less
New ContextManager and AgentChatHistory wired up for improved context handling. Not checked yet Supports boolean and number type casting for environment variables in settings.json. Not checked yet Allows providing a manual session UUID via command-line argument. Not checked yet Boot performance improved by fetching experiments and quota asynchronously. Not checked yet
9 details in Everything
gemini-cli v0.40.0 adds local Gemma setup, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. resource tools, offline ripgrep, Vertex routing, trace telemetry, and new themes
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.40.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.40.0
└──▷ TRY IT
Set up a local Gemma model for offline/private inference without leaving the CLI
Adds gemini gemma subcommand for streamlined local Gemma model setup Not checked yet Adds tools to list and read MCP resources directly from the CLI Not checked yet Bundles ripgrep binaries into the SEA build for offline grep support Not checked yet Adds settings for Vertex AI request routing Not checked yet Adds --traces flag (or equivalent) to enable OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. traces specifically Not checked yet
+6 more
show less
Adds GitHub colorblind themes to the theme selector Not checked yet Adds /new as an alias for /clear to start a fresh session Not checked yet Adds .mdx file support to the get-internal-docs tool Not checked yet Splits memoryManager config flag into autoMemory for finer memory control Not checked yet Uses OSC 777 escape sequences for terminal task-completion notifications Not checked yet Detects newly created files in @ file recommendations via filesystem watcher Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The memoryManager config flag is split into autoMemory; existing configs using memoryManager will need to be updated.
gemini-cli v0.39.0 adds /memory inbox skill review, invoke_subagent unification, Plan Mode confirmation, and scroll momentum enhancements.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.39.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.39.0
└──▷ TRY IT
Review and approve extracted memory skills before they are activated, preventing unintended skill updates.
Configure an MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server in an agent definition with an auth block for authenticated tool access.
json
copy
{
"mcpServers": {
"my-server": {
"url": "https://my-mcp-server.example.com",
"auth": {
"type": "bearer",
"token": "<your-token>"
}
}
}
}
Adds /memory inbox command for reviewing and patching extracted skills, including skill patching support with inbox integration. Not checked yet Introduces unified invoke_subagent tool, consolidating subagent invocation under a single interface. Not checked yet Requires user confirmation for activate_skill actions in Plan Mode, adding a safety gate before skill activation. Not checked yet Implements silent fallback for Plan Mode model routing when the preferred model is unavailable. Not checked yet Adds useAgentStream hook and wires it into AppContainer for streaming agent responses. Not checked yet
+13 more
show less
Implements tool-controlled display protocol (Steps 2-3) for agent UI rendering. Not checked yet Migrates chat recording to JSONL JSONL A text format where each line is a self-contained, valid JSON object, making it easy to stream, append, and process large datasets line by line without parsing a full JSON array into memory. streaming format. Not checked yet Introduces decoupled ContextManager and Sidecar architecture in core. Not checked yet Adds Strategic Re-evaluation guidance to the system prompt. Not checked yet Persists subagent agentId in tool call records for better traceability. Not checked yet Supports auth block in MCP servers config within agents. Not checked yet Adds scroll momentum enhancements to the terminal UI. Not checked yet Adds debugRainbow optional debug setting in the UI. Not checked yet Optimizes Windows sandbox initialization via native ACL ACL An access control list, a set of rules allowing or denying operations for particular users, services or network addresses. It decides who can use a resource. application. Not checked yet Refines shell tool description display logic. Not checked yet Refines tool output formatting for compact mode. Not checked yet Supports Ctrl+Shift+G keyboard shortcut. Not checked yet Scrollbar now only shown in terminalBuffer mode. Not checked yet
18 details in Everything
gemini-cli v0.38.0 adds background memory, context compression, persistent policy approvals, process monitoring, and richer UI controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.38.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.38.0
└──▷ USE IT
Enable non-interactive ADK ADK Google's Agent Development Kit, an open-source framework for building and orchestrating AI agents; cyber tools use it to compose multi-agent workflows with built-in tool-calling and state management. agent sessions in CI or scripted pipelines where no TTY is present.
json
copy
# In settings.json or gemini config:
{
"experimental": {
"adk": {
"agentSessionNoninteractiveEnabled": true
}
}
}
Check role-specific token usage (e.g. how many tokens the tool-use role consumed) for the current session.
Query an ACP-connected agent for its capabilities and version information without leaving the CLI.
Adds experimental.adk.agentSessionNoninteractiveEnabled config setting for non-interactive ADK agent sessions. Not checked yet Introduces a background memory service for automatic skill extraction from sessions. Not checked yet Adds a ContextCompressionService to automatically manage and compress long context windows context windows The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. . Not checked yet Implements context-aware persistent policy approvals so users don't repeatedly confirm the same tool actions. Not checked yet Implements background process monitoring and inspection tools for tracking long-running agent processes. Not checked yet
+15 more
show less
Supports default values for environment variables in CLI configuration. Not checked yet Adds /about command support for ACP-connected agents. Not checked yet Adds /help command for ACP-connected agents. Not checked yet Adds role-specific token/usage metrics to the /stats command output. Not checked yet Enables web_fetch in plan mode with user confirmation, expanding what agents can do without leaving plan mode. Not checked yet Enables compact tool output by default, reducing visual noise in the terminal. Not checked yet Adds a scrollbar to the input prompt for long multi-line inputs. Not checked yet Introduces minimalist sandbox status labels in the UI. Not checked yet Adds TerminalBuffer rendering mode to eliminate UI flicker. Not checked yet Enhances tool confirmation UI with an improved selection layout. Not checked yet Supports selective topic expansion and click-to-expand for conversation topic headers. Not checked yet Displays hook system messages directly in the UI when hooks fire. Not checked yet Adds an Other free-text option for yes/no question prompts. Not checked yet Scopes subagent workspace directories via AsyncLocalStorage for better isolation. Not checked yet Changes default loadingPhrases to off, hiding loading tips by default. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! The default value of loadingPhrases is now off; users who relied on loading tips/phrases appearing by default will no longer see them without explicitly enabling the setting.
gemini-cli v0.37.0 adds sandbox lockdown, persistent browser sessions, cross-platform notifications, new skills, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.37.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.37.0
Adds maxActionsPerTask setting for the browser agent to cap the number of actions per task. Not checked yet Adds a CI skill for automated failure replication. Not checked yet Implements forbiddenPaths for OS-specific sandbox managers to block access to sensitive filesystem paths. Not checked yet Supports inline agentCardJson string literal for configuring remote agents without a separate file. Not checked yet Adds experiment-gated support for Gemini Flash 3.1 Lite model. Not checked yet
+15 more
show less
Adds a new skill to detect duplicated code while reviewing PRs. Not checked yet Enables cross-platform notifications via terminal bell fallback. Not checked yet Implements secret visibility lockdown for env files in the sandbox. Not checked yet Implements persistent browser session management across tasks. Not checked yet Adds forbiddenPaths to GlobalSandboxOptions for centralized sandbox path restriction. Not checked yet Implements dynamic Linux sandbox expansion with worktree support. Not checked yet Implements Windows sandbox dynamic expansion and denial detection. Not checked yet Adds a debug command. Not checked yet Adds configurable memoryBoundaryMarkers setting for context management. Not checked yet Enables network access configuration in sandbox settings. Not checked yet Implements AgentHistoryProvider for tracking agent execution history. Not checked yet Adds subagent isolation and cleanup hardening. Not checked yet Defines TrajectoryProvider interface for agent trajectory tracking. Not checked yet Browser agent now dynamically discovers read-only tools at runtime. Not checked yet Adds development worker infrastructure for GCP. Not checked yet
20 details in Everything
gemini-cli v0.36.0 adds Git worktree isolation, macOS/Windows sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. , admin-forced MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. installs, plan mode in CI, and major subagent enhancements.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.36.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.36.0
└──▷ TRY IT
Install an extension without modifying settings.json, useful in automated or shared environments.
copy
$ gemini extensions install <extension-name> --skip-settings
Adds Git worktree support for isolated parallel sessions, enabling concurrent agent runs without workspace conflicts. Not checked yet Implements strict macOS sandboxing via Seatbelt allowlist to constrain subagent filesystem and process access. Not checked yet Implements native Windows sandboxing for subagent tool isolation. Not checked yet Adds support for admin-forced MCP server installations, allowing organizations to mandate specific MCP servers. Not checked yet Supports plan mode in non-interactive (CI/batch) mode. Not checked yet
+24 more
show less
Introduces multi-registry architecture and per-subagent tool filtering. Not checked yet Adds subagent local execution with tool isolation, keeping each subagent's tool access scoped. Not checked yet Injects memory and JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. (just-in-time) context into subagents for richer, context-aware execution. Not checked yet Adds resilient subagent tool rejection with contextual feedback when a tool is unavailable. Not checked yet Adds --skip-settings flag to the extension install command. Not checked yet Adds linking support in the extension registry. Not checked yet Introduces AgentSession and renames stream events to agent events in the core API. Not checked yet Adds token usage metadata to the ACP send method's return value. Not checked yet Adds an experimental memory manager agent to replace the save_memory tool. Not checked yet Adds a blocked status to tasks and todos in the task tracker. Not checked yet Integrates the task tracker protocol into the core system prompt. Not checked yet Adds an agent acknowledgment command and enhances registry discovery for agent-to-agent (A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. ) communication. Not checked yet Adds browser sensitive action controls and read-only noise reduction. Not checked yet Adds a security prompt for the browser agent. Not checked yet Adds a warning message when browser session mode is set to existing. Not checked yet Adds browser privacy consent handling. Not checked yet Adds dynamic model resolution to ModelConfigService. Not checked yet Adds ModelChain support to ModelConfigService with a dynamic Model Dialog. Not checked yet Formats multi-line banner warnings with a bold title in the UI. Not checked yet Conditionally excludes the ask_user tool when running in ACP mode. Not checked yet Adds onboarding telemetry. Not checked yet Tracks whether a session is running inside a Git worktree via telemetry. Not checked yet Refines the User-Agent string for VS Code traffic to a unified format. Not checked yet Adds content-utils to core for shared content manipulation utilities. Not checked yet
29 details in Everything
gemini-cli v0.35.0 adds customizable keyboard shortcuts, vim yank/paste, gRPC gRPC An open-source remote procedure call framework from Google that uses HTTP/2 and Protocol Buffers to let services call each other's functions across a network, giving tools low-latency, strongly typed inter-process communication. support, parallel tool execution, an --admin-policy flag, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.35.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.35.0
└──▷ TRY IT
Point gemini-cli at a self-hosted or proxy Gemini-compatible endpoint instead of the default Google API.
copy
$ GEMINI_BASE_URL=https://my-proxy.example.com/v1 gemini
Unbind an existing shortcut (e.g. remove the default binding for Ctrl+R) using the - prefix in your keybindings config.
json
copy
# In ~/.gemini/settings.json
{
"keybindings": {
"-ctrl+r": ""
}
}
Adds customizable keyboard shortcuts, including support for literal character keybindings and extended Kitty protocol keys. Not checked yet Supports removing keybindings via a - prefix in the keybinding configuration. Not checked yet Adds missing vim mode motions: X, ~, r, f/F/t/T, df/dt and related commands. Not checked yet Adds vim yank and paste (y/p/P) with an unnamed register. Not checked yet New --admin-policy flag for supplying supplemental admin policies at startup. Not checked yet
+14 more
show less
Enables native gRPC support and protocol routing for A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. (agent-to-agent) communication. Not checked yet Allows safe tools to execute concurrently while the agent is busy processing. Not checked yet Implements a model-driven parallel tool scheduler for running multiple tool calls simultaneously. Not checked yet Supports a custom base URL for the API via environment variables. Not checked yet Displays pending and confirming tool calls in the UI. Not checked yet Implements a SandboxManager interface and config schema for sandboxed execution. Not checked yet Implements Stage 1 improvements to the webfetch tool. Not checked yet Adds Google credentials provider for authenticating to remote agents. Not checked yet Increases sub-agent turn and time limits. Not checked yet Instruments file system tools for just-in-time context discovery. Not checked yet Enables code splitting and deferred UI loading for faster startup. Not checked yet Implements an input blocker overlay in the browser agent during automation. Not checked yet Hides the /upgrade hint for Ultra-tier users. Not checked yet Differentiates the User-Agent header for A2A-server and ACP clients. Not checked yet
19 details in Everything
gemini-cli v0.34.0 adds LXC and gVisor gVisor A user-space kernel written in Go by Google that intercepts and handles system calls on behalf of a container, sandboxing it without needing a full VM. sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. , tracker CRUD CRUD The four basic database operations — Create, Read, Update, Delete — used as shorthand for any system that manages persistent data records, giving cyber tools a standard model for interacting with stored information. tools, loop detection, AI Gateway auth, and a custom footer command.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.34.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.34.0
└──▷ TRY IT
Connect to an AI Gateway-authenticated ACP endpoint instead of direct Gemini API access.
Adds experimental LXC container sandbox support for isolating agent execution. Not checked yet Adds native gVisor (runsc) sandboxing support as a new sandbox backend. Not checked yet Adds tracker CRUD tools and visualization for managing task tracking within sessions. Not checked yet Implements iterative loop detection with model feedback to reduce repetitive agent loops. Not checked yet Adds custom footer configuration via the /footer command. Not checked yet
+9 more
show less
Adds AI Gateway auth support for ACP connections. Not checked yet Improves @file autocomplete to prioritize filenames for faster file referencing. Not checked yet Ships an esbuild bundle in the npm package for faster installs and startup. Not checked yet Implements a unified KeychainService and migrates token storage to it. Not checked yet Adds concurrency safety guidance for subagent delegation in core. Not checked yet Dynamically generates all keybinding hints in the UI. Not checked yet Implements Clearcut logging for startup statistics in telemetry. Not checked yet Adds fallback to Gemini 2.5 models when the current model lacks tool-call access. Not checked yet Promotes --acp flag (previously --experimental-acp) to stable, removing the experimental prefix. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! The --experimental-acp flag is renamed to --acp; scripts using --experimental-acp will break.
gemini-cli v0.33.0 adds HTTP auth for A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. agents, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , plan copy/annotation, GitHub issue skill, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.33.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.33.0
└──▷ TRY IT
Unassign a task or issue from within the CLI without leaving your workflow.
Adds github-issue-creator skill for creating GitHub issues directly from the CLI. Not checked yet Implements HTTP authentication support for A2A remote agents. Not checked yet Supports authenticated A2A agent card discovery. Not checked yet Adds MCPOAuthProvider implementing the MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. SDK OAuthClientProvider for authenticated MCP servers. Not checked yet Adds tool name validation in TOML TOML A configuration file format designed to be minimal and readable, mapping unambiguously to a hash table; cyber tools use it as a structured alternative to YAML or INI for config files. policy files. Not checked yet
+12 more
show less
Enables 30-day default retention for chat history. Not checked yet Supports annotating plans with feedback for iterative refinement. Not checked yet Enables built-in research subagents in plan mode. Not checked yet Adds copy subcommand to plan for duplicating plans. Not checked yet Adds /unassign slash command support. Not checked yet Adds set models interface to ACP. Not checked yet Supports plan directory specification in extension manifests. Not checked yet Inverts context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. display to show token usage rather than remaining capacity. Not checked yet Redesigns the header to be compact with an ASCII icon. Not checked yet Adds dialog pattern UI for the /hooks command. Not checked yet Introduces subagent activity UX for monitoring background agent work. Not checked yet Directly indicates auth-required state for agents in the UI. Not checked yet
17 details in Everything
gemini-cli v0.32.0 adds shell autocompletion, plan-mode editor support, a Gemma router, billing overage flow, and richer OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. telemetry.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.32.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.32.0
Adds interactive shell autocompletion inside the CLI REPL. Not checked yet Supports opening and modifying the plan in an external editor during plan approval. Not checked yet Adapts the planning workflow based on task complexity, encouraging multi-select with option descriptions. Not checked yet Adds a temporary flag to disable workspace policies. Not checked yet Hides the workspace policy update dialog and auto-accepts by default. Not checked yet
+17 more
show less
Enables model steering in workspace context. Not checked yet Introduces an experimental Gemma Router using a LiteRT-LM shim as a composite model classifier strategy. Not checked yet Implements a task tracker foundation and service for tracking agent tasks. Not checked yet Introduces Kind.Agent classification for sub-agent tools, with contiguous parallel admission. Not checked yet Enables the generalist agent. Not checked yet Improves A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. streaming reassembly and task continuity. Not checked yet Improves A2A content extraction. Not checked yet Loads extensions in parallel for faster startup. Not checked yet Adds support for a policy engine in extensions. Not checked yet Instruments OTEL traces with more attributes. Not checked yet Implements G1 AI credits overage flow with billing telemetry. Not checked yet Adds low/full CLI error verbosity mode for a cleaner UI. Not checked yet Adds a Ctrl+O hint to truncated content messages in the UI. Not checked yet Renames the grep_search tool's include parameter to include_pattern. Not checked yet Plumbs the maxAttempts setting through config args. Not checked yet Maps HTTP 499 to retryable quota errors. Not checked yet Increases fetch timeout. Not checked yet
22 details in Everything
└──▷ BREAKING ON UPGRADE
! The grep_search tool's include parameter is renamed to include_pattern.
gemini-cli v0.31.0 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. progress updates, OSC52 clipboard copy, plan mode storage config, deceptive URL detection, and Gemini 3.1 Pro support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.31.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.31.0
└──▷ USE IT
Enable OSC52 clipboard copy so you can yank model output to your system clipboard even inside tmux or SSH sessions.
json
copy
# In your gemini settings (e.g., settings.json or equivalent config)
{ "experimental": { "useOSC52Copy": true } }
Store Plan Mode plans in a shared team directory instead of the default location.
json
copy
# In your gemini config, set a custom plans storage directory
{ "plan": { "storageDirectory": "/path/to/team-plans" } }
Browse and install extensions without leaving the CLI.
copy
$ /extensions explore
Adds gemini --resume hint on exit so users know how to pick up a previous session. Not checked yet Adds Alt+D keyboard shortcut for forward word deletion in the input line. Not checked yet Adds macOS run-event notifications (interactive sessions only) to alert when long tasks complete. Not checked yet Adds MCP progress update support, surfacing real-time progress from Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers. Not checked yet Adds experimental in-progress steering hints, letting users redirect the model mid-task. Not checked yet
+15 more
show less
Adds /dir add directories to @-path autocomplete suggestions. Not checked yet Adds experimental.useOSC52Copy setting to enable clipboard copy via OSC 52 terminal escape sequences. Not checked yet Replaces the loading-phrases boolean with a new enum setting for finer control over loading phrase display. Not checked yet Adds support for configuring a custom plans storage directory in Plan Mode. Not checked yet Implements project-level policy support for controlling tool and behavior constraints per project. Not checked yet Implements parallel function calling function calling A model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions. for read-only tools, improving throughput on multi-tool queries. Not checked yet Adds /extensions explore command for browsing available extensions from within the CLI. Not checked yet Adds numpad SS3 sequence support for terminals that emit SS3 escape codes for numpad keys. Not checked yet Enhances folder trust with configuration discovery and security warnings when opening untrusted directories. Not checked yet Improves startup warnings UX with dismissal support and show-count limits. Not checked yet Adds API key authentication provider for Agent-to-Agent Agent-to-Agent Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. (A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. ) connections. Not checked yet Adds support for Gemini 3.1 Pro Preview model. Not checked yet Detects and discloses deceptive URLs in tool confirmations to surface prompt-injection prompt-injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. attempts. Not checked yet Adds TrueColor detection and centralized terminal compatibility checks. Not checked yet Adds ACP set_mode interface support for IDE integration mode switching. Not checked yet
20 details in Everything
gemini-cli v0.30.0 adds a --policy flag, Ctrl-Z suspension, tool output masking, multi-line ask-user input, strict seatbelt profiles, and an initial SDK package.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.30.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.30.0
└──▷ TRY IT
Enforce a custom tool policy file on every invocation instead of using the deprecated --allowed-tools flag.
copy
$ gemini --policy ./my-policy.json
Suspend a long-running gemini-cli session to the background to run another shell command, then resume.
copy
$ # Press Ctrl-Z inside an active gemini-cli session to suspend it
# Then resume with:
fg
Adds --policy flag for user-defined tool policies, replacing --allowed-tools and excludeTools. Not checked yet Enables tool output masking by default to reduce sensitive data exposure in tool responses. Not checked yet Supports multi-line text answers in the ask-user tool for richer interactive prompts. Not checked yet Adds Ctrl-Z process suspension support for pausing and backgrounding the CLI. Not checked yet Introduces strict seatbelt profiles for tighter sandbox enforcement. Not checked yet
+15 more
show less
Adds autoconfigure memory usage setting directly in the settings dialog. Not checked yet Adds a setting to hide the shortcuts hint UI. Not checked yet Introduces limits on search results to control context size. Not checked yet Formalizes a 5-phase sequential planning workflow in Plan Mode. Not checked yet Allows skills to be enabled in Plan Mode. Not checked yet Updates internal utility models to Gemini 3. Not checked yet Adds A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. value-resolver for auth credential resolution. Not checked yet Enables 30-day session retention by default. Not checked yet Adds text wrapping support for markdown tables in the terminal UI. Not checked yet Adds a searchable list UI backing settings and extensions panels. Not checked yet Shows a notification when an extension command conflicts with a built-in command. Not checked yet Enables in-CLI extension management commands. Not checked yet Bootstraps an initial SDK package with SessionContext support, dynamic system instructions, and custom skills. Not checked yet Fallback to chat-base model automatically when an unrecognized model is specified for chat. Not checked yet Adds admin controls documentation and policy overrides for Plan Mode. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! --allowed-tools and excludeTools are deprecated in favor of the policy engine; existing configurations relying on these flags will need to migrate to the --policy flag.
gemini-cli v0.29.0 adds a /plan slash command, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. admin allowlists, agent skill linking, Vim motions, and WebSocket WebSocket A protocol that upgrades an HTTP connection into a persistent, full-duplex channel, letting a server push data to a client without repeated polling. Cyber tools use it for real-time event streaming and live command output. network logging.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.29.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.29.0
└──▷ TRY IT
Enter plan mode before execution to review and edit the agent's proposed plan for a complex task.
copy
$ /plan Refactor the authentication module to use JWT tokens
List all MCP servers permitted by the admin allowlist to audit what is available to the agent.
Adds /plan slash command to enter an interactive planning mode before execution. Not checked yet Adds enter_plan_mode tool so the agent can autonomously switch into plan mode. Not checked yet Supports the replace tool inside plan mode to edit plans in-place. Not checked yet Supports MCP servers within plan mode. Not checked yet Implements admin allowlist for MCP server configurations, now also applied to extensions. Not checked yet
+19 more
show less
Adds gemini mcp list command to inspect allowed MCP configurations. Not checked yet Implements linking for agent skills. Not checked yet Adds /extensions config command for managing extension configuration. Not checked yet Adds extension registry client and enables extension config by default. Not checked yet Adds W, B, and E Vim motions with operator support in the input prompt. Not checked yet Adds WebSocket-based network logging and streaming chunk support. Not checked yet Adds autocomplete in the input prompt. Not checked yet Adds a shortcuts hint and panel for discoverability. Not checked yet Adds default execution limits for subagents. Not checked yet Implements observation masking for tool outputs, with high-signal tools exempted and remote configuration for masking thresholds. Not checked yet Implements session-linked tool output storage and cleanup, with persistence and resumption for masked outputs. Not checked yet Pauses agent timeout budget while waiting for tool confirmation. Not checked yet Truncates shell output in UI history and improves active shell display. Not checked yet Transitions to event-driven tool scheduler engine. Not checked yet Removes hardcoded policy bypass for local subagents, enforcing consistent policy. Not checked yet Exposes getUserTierName in config. Not checked yet Updates approval modes UI. Not checked yet Transitions sub-agents to XML format with improved definitions. Not checked yet Expands verify-release to macOS and Windows platforms. Not checked yet
24 details in Everything
└──▷ BREAKING ON UPGRADE
! The experimental.enableEventDrivenScheduler setting is removed; the event-driven scheduler is now the default engine.! The previewFeatures flag is removed and Gemini 3 is now the default model.
gemini-cli v0.28.0 adds /prompt-suggest, background shell commands, auto theme switching, and policy deny messages.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.28.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.28.0
└──▷ USE IT
Restrict a shared environment to only load approved extensions, reducing supply-chain risk from arbitrary extension installs.
json
copy
# In settings.json
{
"allowedExtensions": ["my-org/approved-ext-a", "my-org/approved-ext-b"]
}
Get prompt ideas mid-session when you're unsure how to phrase a security analysis request.
Adds /prompt-suggest slash command to surface prompt suggestions interactively. Not checked yet Supports background shell command execution. Not checked yet Implements automatic theme switching based on terminal background color. Not checked yet Adds allowedExtensions setting to restrict which extensions can be loaded. Not checked yet Displays user identity (auth method, email, tier) on startup. Not checked yet
+19 more
show less
Adds user identity info (auth method, email, tier) to the /stats command output. Not checked yet Adds support for custom deny messages in policy rules. Not checked yet Adds GOOGLE_GENAI_API_VERSION environment variable to override the Gemini API version. Not checked yet Enables overriding CODE_ASSIST_API_VERSION with an environment variable. Not checked yet Enables activity logging for non-interactive mode and evals. Not checked yet Adds a setting to disable loop detection. Not checked yet Implements dynamic policy registration for subagents. Not checked yet Implements tool name aliasing for backward compatibility. Not checked yet Adds session resume support for ACP. Not checked yet Shows hooksConfig.enabled status in the settings dialog. Not checked yet Adds support for custom themes in extensions. Not checked yet Adds support for Positron IDE. Not checked yet Adds multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. tool response support to token calculation. Not checked yet Preserves end-of-line style in files when making edits. Not checked yet Updates undo/redo keybindings to Cmd+Z / Alt+Z and Shift+Cmd+Z / Shift+Alt+Z. Not checked yet Aligns hooks enable/disable controls with skills and improves tab completion. Not checked yet Provides actionable error messages when admin-disabled features are accessed. Not checked yet Implements interactive and non-interactive consent flows for OAuth. Not checked yet Includes auth method in /bug reports. Not checked yet
24 details in Everything
└──▷ BREAKING ON UPGRADE
! The legacy tools.enableHooks setting is removed; hooks configuration must use the new hooksConfig.enabled setting.
gemini-cli v0.27.0 adds /rewind, /agents config, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. enable/disable, Plan Mode, AskUser tool, image paste on Linux, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.27.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.27.0
└──▷ TRY IT
Roll back a conversation to an earlier turn when the agent went down the wrong path.
Enable or disable an MCP server at runtime without editing config files.
copy
$ /mcp enable <server-name>
Inspect and configure subagents discovered by the AgentRegistry.
Adds /rewind command to roll back conversation history to a previous state. Not checked yet Adds /agents config command for configuring and discovering subagents. Not checked yet Adds enable/disable commands for MCP servers via /mcp enable and /mcp disable. Not checked yet Adds AskUser tool and accompanying AskUserDialog UI for structured mid-task user prompts. Not checked yet Adds Plan mode, now reachable via Shift+Tab mode cycling, with its own UI theme and a communicate tool kind. Not checked yet
+15 more
show less
Adds code-reviewer skill for automated code review workflows. Not checked yet Adds docs-writer skill for documentation authoring workflows. Not checked yet Enables image pasting on Linux (Wayland and X11). Not checked yet Adds dynamic variable substitution in system prompt overrides. Not checked yet Adds ANSI escape sequence sanitization in non-interactive (piped/redirect) output. Not checked yet Enables the event-driven tool execution scheduler by default. Not checked yet Enables the hooks system by default, with hook-injected context wrapped in distinct XML tags for security. Not checked yet Adds AgentRegistry to track all discovered subagents across extensions. Not checked yet Replaces large text pastes with a [Pasted Text: X lines] placeholder to keep context concise. Not checked yet Adds JetBrains IDE detection for IDE-companion integration. Not checked yet Displays user tier (e.g., free/paid) in the /about command output. Not checked yet Consolidates shell inactivity and redirection monitoring into a unified monitor. Not checked yet Disables startup tips automatically after 10 runs. Not checked yet Adds an agent configuration dialog with full state management. Not checked yet Adds A/B test routing using numerical complexity scoring for Gemini model selection. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! The default behavior for positional arguments changes to interactive mode (Default to interactive mode for positional arguments ), which may break scripts relying on the previous non-interactive default.! Legacy settings removed (feat(core): Remove legacy settings) — configurations relying on those settings will no longer be applied.
gemini-cli v0.26.0 adds skill-creator, plan approval mode, agent enable/disable, and undeprecates --prompt
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.26.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.26.0
└──▷ TRY IT
Pass a one-shot prompt directly on the command line without entering the interactive REPL.
copy
$ gemini --prompt "Summarize the last 10 git commits in this repo"
Introduces skill-creator built-in skill and CJS management tools for authoring and managing agent skills. Not checked yet Adds experimental --plan flag and plan approval mode that enforces a strict read-only policy and halts execution on violations before any writes occur. Not checked yet Enables and disables individual agents from the CLI. Not checked yet Undeprecates the --prompt flag for passing prompts directly on the command line. Not checked yet Adds auto alias for default model selection in config. Not checked yet
+14 more
show less
Enables agent skills by default. Not checked yet Adds conflict detection and warnings when skills override one another. Not checked yet Adds security consent prompts when installing skills. Not checked yet Adds a Rewind Confirmation dialog and Rewind Viewer component for reviewing conversation history. Not checked yet Adds source tracking to policy rules for auditability. Not checked yet Adds a generalist agent to the core agent roster. Not checked yet Adds admin controls polling and restart prompt for centralized admin management. Not checked yet Renames negative settings to positive naming convention (disable* → enable*). Not checked yet Adds support for running available commands before MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers finish loading. Not checked yet Steers the outer agent to delegate to expert sub-agents when they are present. Not checked yet Adds experimental extension config setting. Not checked yet Adds types and SchedulerStateManager for an event-driven scheduler with reactive tool state. Not checked yet Optimizes text buffer and syntax highlighting for large inputs. Not checked yet Removes read_many_files from plan approval mode policies so file reads are always permitted without approval. Not checked yet
19 details in Everything
└──▷ BREAKING ON UPGRADE
! Settings previously named with a disable* prefix are renamed to enable* (e.g., a setting like disableX becomes enableX); existing configs using the old names will need to be updated.
gemini-cli v0.25.0 adds built-in agent skills, /agents command, filepath autosuggestion, model routing to subagents, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.25.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.25.0
└──▷ TRY IT
List all available agents mid-session to know which subagents you can delegate to.
Reload agent definitions after adding or modifying an agent without restarting the CLI.
Override experiment flags locally without changing server-side config, useful for testing experimental model behaviour.
copy
$ GEMINI_EXP=my_experiment gemini
Adds built-in Agent Skills support, including a new pr-creator skill, with multi-scope enablement and shadowing fixes. Not checked yet New /agents slash command lists available agents; /agents refresh reloads agent definitions without restarting. Not checked yet Adds filepath autosuggestion after slash commands for faster input. Not checked yet Introduces subagent model routing, wiring model selection to subagents. Not checked yet Supports @ mention suggestions for subagents in the prompt. Not checked yet
+19 more
show less
Adds mcp_context to BeforeTool and AfterTool hook inputs for richer hook logic. Not checked yet Model hooks now support explicit stop and block execution control. Not checked yet Adds GEMINI_EXP environment variable for local experiments override. Not checked yet Adds GEMINI_CLI_HOME environment variable for strict environment isolation. Not checked yet Adds fallback option for capacity errors in Pro Quota. Not checked yet Adds native Sublime Text support to IDE detection. Not checked yet Adds support for the Antigravity terminal in terminal setup utility. Not checked yet Adds Helix (hx) editor support. Not checked yet Exports chat history in /bug command and prefills the GitHub issue body. Not checked yet Adds extension linking capabilities in the CLI. Not checked yet Shows settings source in extension lists. Not checked yet Adds upgrade option for paid users. Not checked yet Implements passive activity logger for session analysis. Not checked yet Adds /chat debug command for nightly builds. Not checked yet Enables the cli_help agent by default. Not checked yet Adds confirmation details support and JSON-RPC RPC Remote Procedure Call, a protocol that lets a program execute a function on another machine as if it were local, giving cyber tools a structured way to communicate across processes or hosts without managing raw sockets. vs HTTP REST support for external tool integrations. Not checked yet Adds opt-out setting for home directory warnings to reduce noise. Not checked yet Caches ignore instances for improved file-traversal performance. Not checked yet Applies remote admin settings. Not checked yet
24 details in Everything
gemini-cli v0.24.0 adds Agent Skills, remote multi-agent support, in-CLI extension install/uninstall, hook tool-input modification, and a new gemini skills command.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.24.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.24.0
└──▷ TRY IT
List available Agent Skills and check how many are active (shown in the status bar), then hot-reload after adding a new skill.
copy
$ gemini skills
# after adding a skill file, inside the CLI:
/skills reload
Adds experimental extension install and extension uninstall subcommands to manage extensions directly from the CLI. Not checked yet Adds gemini skills CLI management command for discovering, listing, and reloading Agent Skills. Not checked yet Adds /skills reload slash command to hot-reload skills without restarting a session. Not checked yet Introduces Agent Skills infrastructure with tiered discovery, autonomous activation, system-prompt injection prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. , status-bar skill counts, and extension support. Not checked yet Adds support for remote agents and multi-agent TOML TOML A configuration file format designed to be minimal and readable, mapping unambiguously to a hash table; cyber tools use it as a structured alternative to YAML or INI for config files. configuration files. Not checked yet
+16 more
show less
Adds A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. (Agent-to-Agent Agent-to-Agent Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. ) Client Manager for connecting to remote agents. Not checked yet Supports tool input modification via hooks, allowing hooks to rewrite tool arguments before execution. Not checked yet Adds context injection via the SessionStart hook. Not checked yet Implements dynamic mode-aware policy evaluation in the policy engine. Not checked yet Allows modes field in user and admin policy files for per-mode policy rules. Not checked yet Adds unified secrets sanitization and environment variable redaction options. Not checked yet Adds folder trust support to hooks, with project-level hook security warnings. Not checked yet Enables automatic /model persistence across sessions (opt-in). Not checked yet Adds folder suggestions to the /dir add command. Not checked yet Adds descriptions for each setting item displayed in /settings. Not checked yet Adds a hooks.enabled setting to globally enable or disable hooks. Not checked yet Adds OSC 52 paste support via a new setting. Not checked yet Adds modifyOtherKeys protocol support for improved key handling in tmux. Not checked yet Shows a snowfall animation for the holiday UI theme. Not checked yet Adds visual indicators in the UI for hook execution status. Not checked yet Adds exponential back-off retries for retryable API errors without a specified retry delay. Not checked yet
21 details in Everything
└──▷ BREAKING ON UPGRADE
! Deprecated permission aliases are removed from BeforeToolHookOutput; hooks using those aliases will break.! Legacy confirmation settings are deprecated and the Policy Engine is now enforced; configurations relying on the old confirmation settings will no longer apply.! Legacy shell security policy logic is removed and unified under the new policy engine; existing shell allowlist configurations may need to be updated.! SmartEditTool is consolidated into EditTool and the smart-edit module is renamed to edit; configurations or extensions referencing smart-edit by name will break.
gemini-cli v0.23.0 adds Gemini 3 Flash, HTTP/SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers, /auth logout, Windows clipboard image paste, and more
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.23.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.23.0
└──▷ TRY IT
Log out and clear all stored credentials when rotating accounts or revoking access.
copy
$ gemini /auth logout
Adds support for Gemini 3 Flash as an available model in the CLI Not checked yet Supports HTTP/SSE based MCP servers via the official ACP SDK Not checked yet New /auth logout command clears credentials and auth state Not checked yet Adds Windows clipboard image support with Alt+V paste workaround Not checked yet Introduces remote agent infrastructure for orchestrating remote agents Not checked yet
+8 more
show less
Adds an agent TOML TOML A configuration file format designed to be minimal and readable, mapping unambiguously to a hash table; cyber tools use it as a structured alternative to YAML or INI for config files. parser for defining agents declaratively Not checked yet Supports friendly names and descriptions for hooks Not checked yet Implements JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. (just-in-time) context memory loading with UI sync Not checked yet Passes additional environment variables to shell execution Not checked yet Detects terminal background color for improved theme rendering Not checked yet Adds Allow for all future sessions tool-confirmation option (off by default) Not checked yet Simplifies tool confirmation labels for better UX Not checked yet Adds clearcut telemetry logging for hooks Not checked yet
13 details in Everything
gemini-cli v0.22.0 adds persistent Always Allow policies, multi-file image drag-and-drop, /init for A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. servers, transcript_path in hooks, and richer /stats output.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.22.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.22.0
└──▷ TRY IT
Check quota consumption for every model — including ones you haven't used this session — to spot headroom before hitting limits.
Initialize an Agent-to-Agent Agent-to-Agent Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. server configuration in the current directory.
Adds persistent Always Allow policies with granular shell and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool support, so approved tools aren't re-prompted across sessions. Not checked yet Supports multi-file drag and drop of images directly into the CLI prompt. Not checked yet Introduces /init command for the Agent-to-Agent (A2A) server. Not checked yet Adds transcript_path field in hooks for git-ai/Gemini extension integrations. Not checked yet Displays quota stats for unused models in /stats, alongside polished cached token stats. Not checked yet
+4 more
show less
Falls back to GEMINI_CLI_IDE_AUTH_TOKEN environment variable for IDE authentication. Not checked yet Adds schema validation for settings files, catching misconfiguration at load time. Not checked yet Shows raw input token counts in JSON output mode. Not checked yet Hooks now refresh automatically when extensions are refreshed. Not checked yet
9 details in Everything
gemini-cli v0.21.0 adds hook lifecycle events, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Resources, OSC52 remote copy, extension settings commands, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.21.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.21.0
└──▷ TRY IT
Copy output to your local clipboard from an SSH/remote session without needing a local selection.
copy
$ gemini
# inside the session:
/copy
Add a remote MCP server using the new consolidated url field and the --type alias.
copy
$ gemini mcp add my-server --type sse --url https://my-mcp-server.example.com/sse
Adds hook system for session lifecycle and compression integration, enabling scripts to react to session start/end and context compression events. Not checked yet Adds a Hooks Commands Panel in the UI with per-hook enable/disable toggles and migration support. Not checked yet Supports Extension Hooks with a security warning when a hook is loaded from an extension. Not checked yet Adds --enableAgents experimental flag to opt into agent-based workflows. Not checked yet Supports MCP Resources, allowing MCP servers to expose file/data resources to the CLI. Not checked yet
+17 more
show less
Adds --type alias for --transport flag in gemini mcp add for convenience. Not checked yet Auto-executes MCP prompts that require no arguments when selected, skipping a manual Enter press. Not checked yet Auto-executes slash commands on completion when the command function takes no arguments. Not checked yet Consolidates remote MCP server config to use a single url field instead of separate transport fields. Not checked yet Supports dynamic MCP tool updates via notifications/tools/list_changed, keeping the tool list current without restarting. Not checked yet Adds /copy slash command support in remote SSH sessions using OSC52 escape sequences. Not checked yet Adds commands for listing and updating per-extension settings. Not checked yet Adds support for user-scoped extension settings, separate from project-level settings. Not checked yet Implements fuzzy search inside the settings panel. Not checked yet Enables message bus integration by default. Not checked yet Allows telemetry exporters to GCP to use the user's login credentials when requested. Not checked yet Tracks GitHub repository names in telemetry events. Not checked yet Emits gemini_cli.startup_stats OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. log event for startup performance metrics. Not checked yet Generates a one-line AI summary to describe saved sessions in the session list. Not checked yet Introduces a restore command for the a2a server to resume previous sessions. Not checked yet Integrates model availability service into backend logic for smarter model selection. Not checked yet Includes session_id in JSON output for easier programmatic session tracking. Not checked yet
22 details in Everything
└──▷ BREAKING ON UPGRADE
! Remote MCP server config now uses a single url field; existing configs using separate transport fields must be updated.
gemini-cli v0.20.0 adds hooks for tool/LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. interception, JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. context management, policy-driven model fallback, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server instruction injection.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.20.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.20.0
└──▷ TRY IT
Check remaining usage quota alongside token and cost stats mid-session.
Adds hook integration for tool execution, enabling external scripts to intercept and act on tool calls before and after they run. Not checked yet Adds hook integration for LLM request/response, allowing external scripts to observe or modify model inputs and outputs. Not checked yet Implements a JIT (Just-in-Time) context manager and accompanying setting to dynamically manage context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. usage. Not checked yet Introduces a policy-driven model fallback mechanism with wrapped fallback and single-model policies for availability routing. Not checked yet Adds configurable inactivity timeout for shell commands to prevent runaway executions. Not checked yet
+10 more
show less
Adds support for MCP server instructions, now always injected into the system prompt. Not checked yet Injects GoogleCredentialProvider headers in McpClient, enabling authenticated MCP server connections. Not checked yet Shows waiting/connecting MCP servers in the ConfigInitDisplay UI during startup. Not checked yet Adds usage limit remaining to the /stats command output. Not checked yet Auto-executes simple slash commands (e.g., /clear) on Enter without requiring a second confirmation. Not checked yet Adds a startup profiler to measure and record application initialization phases. Not checked yet Adds a built-in holiday theme accessible via the themes system. Not checked yet Adds a consent flag to the link command. Not checked yet Adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. semantic logging for API request events with finish reasons via updated telemetry. Not checked yet Standardizes the pager to cat for shell executions run by the model, ensuring consistent output handling. Not checked yet
15 details in Everything
gemini-cli v0.19.0 adds Databricks auth, a session browser, hooks infrastructure, custom model aliases, and automatic Flash fallback on quota errors.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0
└──▷ TRY IT
Browse and resume a previous chat session interactively without leaving the CLI.
Adds Databricks authentication support and a custom header option for connecting to Databricks-hosted Gemini endpoints. Not checked yet Adds interactive session browser component with a new /resume slash command to browse and reopen past chat sessions. Not checked yet Introduces hooks infrastructure (telemetry, event handling, agent lifecycle, and system orchestration) enabling extensible automation around agent actions. Not checked yet Adds model availability service (modelAvailabilityService) with ModelPolicy and PolicyCatalog for tracking and managing model health. Not checked yet Adds isModelAvailabilityServiceEnabled setting to toggle the model availability service. Not checked yet
+5 more
show less
Supports custom aliases for model configs, letting users define shorthand names for specific model configurations. Not checked yet Automatic fallback to Gemini Flash on TerminalQuota errors so sessions continue without manual intervention. Not checked yet Adds session subtask display in the /stats command output. Not checked yet Displays a custom loading phrase when an interactive shell tool requires user input. Not checked yet Removes the useModelRouter experimental flag, graduating model routing to standard behavior. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! Alternate buffer mode is now off by default; terminals that relied on the previous default alternate-buffer behavior will see a changed display mode on upgrade.
v0.20.0-nightly.20251202.29920b16d
Prerelease
Dec 2, 2025
· release notes
gemini-cli v0.20.0-nightly adds auto-executing slash commands, a holiday theme, and enhanced model availability routing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.20.0-nightly.20251202.29920b16d https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.20.0-nightly.20251202.29920b16d
Auto-executes simple slash commands on Enter, removing the need for an extra confirmation keystroke. Not checked yet Adds a built-in holiday theme () selectable via the themes system. Not checked yet Enhances availability routing with wrapped fallback and single-model policies for more resilient model selection. Not checked yet Adds a startup profiler to measure and record application initialization phases. Not checked yet Always applies MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server instructions when MCP tools are in use. Not checked yet
5 details in Everything
v0.20.0-nightly.20251201.2fe609cb6
Prerelease
Dec 1, 2025
· release notes
gemini-cli v0.20.0-nightly adds usage-limit tracking in /stats, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server visibility, and richer OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. telemetry.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.20.0-nightly.20251201.2fe609cb6 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.20.0-nightly.20251201.2fe609cb6
└──▷ TRY IT
Check remaining API usage quota mid-session without leaving the CLI.
Adds remaining usage-limit display to the /stats command so you can track API quota at a glance. Not checked yet Shows waiting/pending MCP servers in the ConfigInitDisplay so you can see server connection status during initialization. Not checked yet Standardizes the pager to cat for shell commands executed by the model, ensuring consistent, non-interactive output. Not checked yet Adds semantic logging for API request events in OTel telemetry. Not checked yet Emits finish reasons on OTel API response events for richer observability. Not checked yet
5 details in Everything
v0.20.0-nightly.20251127.5bed97064
Prerelease
Nov 27, 2025
· release notes
gemini-cli v0.20.0-nightly adds Databricks auth, hooks for tool/LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. events, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server instructions, and policy-driven model fallback.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.20.0-nightly.20251127.5bed97064 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.20.0-nightly.20251127.5bed97064
Adds Databricks authentication support and a custom header option for connecting gemini-cli to Databricks-hosted models. Not checked yet Adds hook integration for tool execution, enabling scripts or handlers to fire before/after the CLI invokes any tool. Not checked yet Adds hook integration for LLM request/response events, allowing interception or logging of raw model traffic. Not checked yet Adds support for MCP server instructions via a config option, letting operators inject server-level guidance into the context. Not checked yet Injects GoogleCredentialProvider headers into MCP client connections, enabling authenticated MCP server access. Not checked yet
+3 more
show less
Implements a policy-driven model fallback mechanism so the CLI can automatically switch models when a primary model is unavailable. Not checked yet Adds a configurable inactivity timeout for shell commands, preventing runaway shell tool calls from hanging indefinitely. Not checked yet Adds a consent flag to the Link command for non-interactive linking flows. Not checked yet
8 details in Everything
v0.19.0-nightly.20251126.03845198c
Prerelease
Nov 26, 2025
· release notes
gemini-cli v0.19.0-nightly adds /resume slash command, model availability service setting, and Flash quota fallback.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0-nightly.20251126.03845198c https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0-nightly.20251126.03845198c
└──▷ TRY IT
Browse and restore a previous conversation interactively without leaving the CLI.
New /resume slash command opens an interactive session browser to restore previous chats. Not checked yet New isModelAvailabilityServiceEnabled config setting controls the model availability service. Not checked yet Automatically falls back to Gemini Flash when a TerminalQuota error is encountered. Not checked yet
3 details in Everything
gemini-cli v0.18.0 adds Gemini 3 thinking support, click-to-focus shell, live preview toggles, and richer session recording.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.18.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.18.0
Adds thinking level support for Gemini 3 models, with thinking mode now excluded for gemini-2.0 models. Not checked yet Incorporates Gemini 3 into the model config hierarchy for default model routing. Not checked yet Adds click-to-focus support for the interactive shell. Not checked yet Enables switching preview features on/off without restarting the CLI. Not checked yet Records interactive-only errors and warnings to chat recording JSON files in session logs. Not checked yet
+3 more
show less
Adds user email detail to the about box. Not checked yet Changes default context-compression threshold to 0.5 for API key users. Not checked yet Keeps header ASCII art colored on non-gradient terminals. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! The default compress threshold is changed to 0.5 for API key users, which may trigger context compression more aggressively than before.
gemini-cli v0.19.0 adds Databricks auth, a session browser, hooks infrastructure, model aliases, and model health tracking.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0-preview.0
└──▷ TRY IT
Browse and resume a past session interactively without leaving the CLI.
Check token usage and session subtask breakdown for the current conversation.
Adds Databricks authentication support and a custom header option for connecting to Databricks-hosted models. Not checked yet New interactive session browser component lets users browse, select, and resume past sessions from within the CLI. Not checked yet New /resume slash command opens the session browser directly from an interactive session. Not checked yet Adds hook telemetry infrastructure, event handling, agent lifecycle integration, and system orchestration — enabling hook-based extensibility across the agent pipeline. Not checked yet Adds support for custom aliases for model configs, letting users refer to models by shorthand names. Not checked yet
+10 more
show less
Introduces modelAvailabilityService with ModelPolicy and PolicyCatalog for managing and tracking model health. Not checked yet Adds isModelAvailabilityServiceEnabled setting to toggle model availability tracking. Not checked yet Automatic fallback to Gemini Flash on TerminalQuota errors keeps sessions running when quota is exhausted. Not checked yet Adds session subtask display to the /stats command output. Not checked yet Chat compression service migrated to model configs, enabling per-model compression configuration. Not checked yet Custom loading phrase displayed when the interactive shell is waiting for input from an external tool or subprocess. Not checked yet Alternate buffer mode is now off by default, improving terminal compatibility. Not checked yet Removes the useModelRouter experimental flag (model routing is now standard behavior). Not checked yet Updates MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. SDK dependency to v1.23.0, bringing the latest Model Context Protocol Model Context Protocol Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. improvements. Not checked yet Lenient MCP output schema validator reduces noise from non-conforming MCP server responses. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The useModelRouter experimental flag has been removed; any config or scripts referencing it will need to be updated.! Alternate buffer mode is now off by default; setups that relied on alternate buffer mode being enabled will see changed terminal rendering behavior.
v0.19.0-nightly.20251125.f6d97d448
Prerelease
Nov 25, 2025
· release notes
gemini-cli v0.19.0-nightly adds hook lifecycle infrastructure, session stats, and model policy controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0-nightly.20251125.f6d97d448 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0-nightly.20251125.f6d97d448
Adds hook telemetry infrastructure, enabling hooks to emit and track telemetry events during execution. Not checked yet Adds hook event handling, allowing hooks to respond to and process agent events. Not checked yet Adds hook agent lifecycle integration, connecting hooks to agent start/stop and lifecycle transitions. Not checked yet Adds hook system orchestration, enabling coordinated hook execution across the agent system. Not checked yet Adds session subtask breakdown to the /stats command for finer-grained session inspection. Not checked yet
+2 more
show less
Introduces ModelPolicy and PolicyCatalog to govern model availability and selection rules. Not checked yet Migrates chat compression service to model configs, enabling per-model compression configuration. Not checked yet
7 details in Everything
v0.19.0-nightly.20251123.dadd606c0
Prerelease
Nov 23, 2025
· release notes
gemini-cli v0.19.0-nightly adds BaseLlmClient.generateContent and disables alternate buffer mode by default.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0-nightly.20251123.dadd606c0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0-nightly.20251123.dadd606c0
Adds BaseLlmClient.generateContent method to the core LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. client interface. Not checked yet Disables alternate buffer mode by default for a more standard terminal experience. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! Alternate buffer mode is now off by default, which changes terminal rendering behavior for users who relied on the previous default.
v0.19.0-nightly.20251122.42c2e1b21
Prerelease
Nov 22, 2025
· release notes
gemini-cli v0.19.0-nightly adds an interactive session browser, model health tracking, custom model aliases, and custom shell loading phrases.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0-nightly.20251122.42c2e1b21 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0-nightly.20251122.42c2e1b21
Adds interactive session browser component for navigating past sessions within the UI. Not checked yet Adds modelAvailabilityService for managing and tracking model health, enabling automatic model fallback awareness. Not checked yet Supports custom aliases for model configs, letting users define shorthand names for frequently used model configurations. Not checked yet Displays a custom loading phrase when the interactive shell is waiting for input from an external process. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The useModelRouter experimental flag has been removed; any configuration or scripts referencing it will no longer be recognized.
v0.19.0-nightly.20251121.5982abeff
Prerelease
Nov 21, 2025
· release notes
gemini-cli v0.19.0-nightly adds Gemini 3 thinking-level support, live preview-feature toggling, and user email in the about box.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.19.0-nightly.20251121.5982abeff https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.19.0-nightly.20251121.5982abeff
Adds thinking-level control for Gemini 3 models, wired into the model config hierarchy. Not checked yet Enables switching preview features on and off without restarting the CLI. Not checked yet Displays the authenticated user's email in the about box. Not checked yet Wires up chat code path to honour per-model config settings. Not checked yet Applies default model routing for the Zed integration. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! The default compress threshold for API key users is changed to 0.5 (from its previous value), which may trigger context compression sooner than before on existing setups.
gemini-cli v0.17.0 adds Gemini 3 support, multi-extension uninstall, metadata server auth, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool discovery rework.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.17.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.17.0
Launches Gemini 3 model support in Gemini CLI. Not checked yet Adds option for metadata server application default credentials without project override. Not checked yet Enables uninstalling multiple extensions in a single command. Not checked yet Reworks MCP tool discovery and invocation. Not checked yet Updates the permissions command to support modifying trust for other directories. Not checked yet
+4 more
show less
Checks folder trust before allowing add directory operations. Not checked yet Shows the active model in conversation history. Not checked yet Supports right-click to paste in Alternate Buffer mode. Not checked yet Changes default compress threshold to 0.7 for API key users. Not checked yet
9 details in Everything
gemini-cli v0.18.0 adds Gemini 3 thinking support, click-to-focus shell, live preview toggles, and richer session recordings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.18.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.18.0-preview.0
└──▷ HOW TO FIND IT
Toggle a preview feature on or off at runtime without restarting the CLI session.
📍 # Inside a running gemini-cli session, open Settings and toggle preview features on or off without exiting.
Adds thinking level support for Gemini 3 models via updated model config hierarchy. Not checked yet Narrows thinking mode support to exclude gemini-2.0 models, simplifying model selection logic. Not checked yet Enables click-to-focus support for the interactive shell. Not checked yet Enables switching preview features on/off without restarting the CLI. Not checked yet Records interactive-only errors and warnings to chat recording JSON files for better session replay. Not checked yet
+6 more
show less
Displays user email detail in the about box. Not checked yet Wires up chat code path for model configs, enabling per-chat model configuration. Not checked yet Uses default model routing for the Zed integration. Not checked yet Updates banner design. Not checked yet Keeps header ASCII art colored on non-gradient terminals. Not checked yet Changes default compress threshold to 0.5 for API key users. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The default context compression threshold is changed to 0.5 for API key users, which may trigger earlier automatic context compression than before.
v0.18.0-nightly.20251120.2231497b1
Prerelease
Nov 20, 2025
· release notes
gemini-cli v0.18.0-nightly adds chat-session error recording, click-to-focus in interactive shell, and updated thinking-mode model support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.18.0-nightly.20251120.2231497b1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.18.0-nightly.20251120.2231497b1
Records interactive-only errors and warnings to chat recording JSON files for post-session review. Not checked yet Adds click-to-focus support for the interactive shell, letting users mouse-click to direct input focus. Not checked yet Updates thinking mode support to exclude gemini-2.0 models with simplified selection logic. Not checked yet Bumps genai SDK to v1.30.0, unlocking access to the latest Gemini API capabilities. Not checked yet
4 details in Everything
v0.18.0-nightly.20251118.7cc5234b9
Prerelease
Nov 18, 2025
· release notes
gemini-cli v0.18.0-nightly adds Gemini 3, bulk extension uninstall, reworked MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool discovery, and right-click paste in Alternate Buffer mode.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.18.0-nightly.20251118.7cc5234b9 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.18.0-nightly.20251118.7cc5234b9
Launches Gemini 3 model support in Gemini CLI. Not checked yet Enables uninstalling multiple extensions in a single command. Not checked yet Reworks MCP tool discovery and invocation for improved reliability. Not checked yet Adds right-click to paste in Alternate Buffer mode. Not checked yet Shows a tip on the first request to guide new users. Not checked yet
5 details in Everything
Gemini CLI v0.16.0 launches Gemini 3 model support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.16.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.16.0
v0.17.0-nightly.20251116.e650a4ee5
Prerelease
Nov 16, 2025
· release notes
gemini-cli v0.17.0-nightly adds metadata server ADC auth option, permissions command trust management, and model display in history.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.17.0-nightly.20251116.e650a4ee5 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.17.0-nightly.20251116.e650a4ee5
Adds option to authenticate via metadata server application default credentials without a project override. Not checked yet Extends the permissions command to support modifying trust for directories beyond the current working directory. Not checked yet Adds folder trust verification before allowing a directory to be added via add directory. Not checked yet Shows the active model in conversation history output. Not checked yet
4 details in Everything
v0.17.0-nightly.20251114.0fcbff506
Prerelease
Nov 14, 2025
· release notes
gemini-cli v0.17.0-nightly adds animated scrolling, draggable scrollbar, sticky headers, and alternate buffer UI by default.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.17.0-nightly.20251114.0fcbff506 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.17.0-nightly.20251114.0fcbff506
Enables alternate screen buffer (useAlternateBuffer) by default for a cleaner terminal UI experience. Not checked yet Adds animated page-up/page-down, fn-up/fn-down, and End/Home key navigation in the UI. Not checked yet Introduces a draggable scrollbar for mouse-driven scroll control. Not checked yet Adds sticky headers with top rounded border that remain visible while scrolling. Not checked yet Supports an incremental update experiment flag for rendering optimization. Not checked yet
+2 more
show less
Records auth type in history checkpoints for improved session tracking. Not checked yet Allows users to manually reset model selection back to auto mode when the client is in fallback mode. Not checked yet
7 details in Everything
gemini-cli v0.15.0 adds session resume flags, a hooks execution engine, /extensions restart, and a listCommands A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. endpoint.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.15.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.15.0
└──▷ TRY IT
Reload all extensions mid-session after editing their configs or tool exclusion lists, without restarting the CLI.
copy
$ /extensions restart
Adds CLI flags for session management, including the ability to resume previous geminiChat sessions. Not checked yet Introduces a Hook Execution Engine, enabling hooks to fire during CLI operations. Not checked yet Adds /extensions restart slash command to reload extensions without restarting the CLI. Not checked yet Adds listCommands endpoint to the A2A (agent-to-agent) server. Not checked yet Gemini memory now reloads automatically on extension load/unload. Not checked yet
+5 more
show less
Extension reloading now respects updates to excluded tools. Not checked yet Adds a setting to disable GitHub extensions. Not checked yet Adds expected_replacements parameter to the smart-edit tool. Not checked yet Supports scrolling within the Ink-rendered UI. Not checked yet Switches terminal rendering to alternate buffer mode for cleaner display. Not checked yet
10 details in Everything
gemini-cli v0.16.0 adds a safety checker framework, hook result aggregation, enhanced RipGrep search, and new UI navigation capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.16.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.16.0-preview.0
Introduces a safety checker framework (feat(safety) ) for validating tool actions before execution. Not checked yet Adds hook result aggregation, allowing multiple hook outputs to be combined and acted upon together. Not checked yet Enhances the RipGrep tool with advanced search options and improved defaults for richer code search. Not checked yet Enables the write_todo tool so the agent can create and manage to-do lists during sessions. Not checked yet Adds animated page-up/page-down, Fn+Up/Down, and End+Home keyboard navigation in the UI. Not checked yet
+6 more
show less
Adds draggable scrollbar support in the terminal UI. Not checked yet Adds two-stage loop detection in the agent core to catch and break repetitive model behavior earlier. Not checked yet Supports an incremental update experiment flag for streaming response rendering. Not checked yet Auth type is now recorded in history checkpoints, enabling per-session auth tracking. Not checked yet Always shows the tool internal name in /tools output alongside the display name. Not checked yet Switches the UI to use the alternate terminal buffer by default, keeping the primary buffer clean. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The read-many-files tool has been removed from the agent; workflows relying on it must switch to alternative file-reading approaches.
v0.16.0-nightly.20251113.ad1f0d99
Prerelease
Nov 13, 2025
· release notes
gemini-cli v0.16.0-nightly adds hook result aggregation, a safety checker framework, and the write_todo tool.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.16.0-nightly.20251113.ad1f0d99 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.16.0-nightly.20251113.ad1f0d99
Adds Hook Result Aggregation, enabling multiple hook outputs to be combined and surfaced together. Not checked yet Introduces a safety checker framework for validating tool actions before execution. Not checked yet Enables the write_todo tool for managing task lists directly within the CLI. Not checked yet Always displays the internal tool name in /tools output for clearer tool identification. Not checked yet
4 details in Everything
v0.16.0-nightly.20251112.c961f274
Prerelease
Nov 12, 2025
· release notes
gemini-cli v0.16.0-nightly adds session resuming, GitHub extension disabling, enhanced RipGrep search, and improved loop detection.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.16.0-nightly.20251112.c961f274 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.16.0-nightly.20251112.c961f274
Adds CLI flags for session management, including the ability to resume previous geminiChat sessions. Not checked yet Adds a setting to disable GitHub extensions from the CLI. Not checked yet Enhances the RipGrep tool with advanced search options and improved defaults. Not checked yet Enhances loop detection with a 2-stage check for more reliable agentic runs. Not checked yet Adds expected_replacements parameter to the smart-edit tool for more precise edits. Not checked yet
+2 more
show less
Adds experiment logging and a caching experiment for performance optimization. Not checked yet Supports Ink scrolling for improved terminal rendering of long outputs. Not checked yet
7 details in Everything
gemini-cli v0.14.0 adds scrollable output, extension enable/disable commands, subagent compression, and shell CWD context.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.14.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.14.0
└──▷ TRY IT
Temporarily disable a noisy extension mid-session without restarting the CLI.
copy
$ /disable <extension-name>
Re-enable a previously disabled extension and pick up any custom command changes without restarting.
copy
$ /enable <extension-name>
Adds scrollable support to the CLI output interface. Not checked yet Adds /enable and /disable commands for extensions, and live reloading of custom commands without restarting the CLI. Not checked yet Adds compression mechanism to subagent conversations to manage context length context length The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. . Not checked yet Includes current working directory (cwd) in shell command descriptions for clearer context. Not checked yet Notifies users when the model falls back to Flash, with an updated error message. Not checked yet
+1 more
show less
Adds ModelConfigService for centralized model configuration management. Not checked yet
6 details in Everything
gemini-cli v0.15.0 adds session resumption flags, a hook execution engine, /extensions restart, and an a2a listCommands endpoint.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.15.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.15.0-preview.0
└──▷ TRY IT
Restart all loaded extensions after editing their configuration, without restarting the CLI.
copy
$ /extensions restart
Adds CLI flags for session management and resuming chat sessions via geminiChat. Not checked yet Introduces a Hook Execution Engine for automating actions around tool calls and model responses. Not checked yet Adds /extensions restart slash command to reload extensions without restarting the CLI. Not checked yet Gemini memory now reloads automatically on extension load/unload. Not checked yet Extension reloading now respects updates to excluded tools. Not checked yet
+6 more
show less
Adds listCommands endpoint to the a2a server for agent-to-agent capability discovery. Not checked yet Adds setting to disable GitHub extensions. Not checked yet Adds expected_replacements parameter to the smart-edit tool for more precise edits. Not checked yet Switches to alternate buffer mode before rendering Ink for a cleaner terminal UI. Not checked yet Supports scrolling in the Ink UI. Not checked yet Tabs are now preserved on paste. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The icon property on info messages is renamed to prefix.
v0.15.0-nightly.20251111.51f952e7
Prerelease
Nov 11, 2025
· release notes
gemini-cli v0.15.0-nightly adds a Hook Execution Engine for automating actions around tool calls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.15.0-nightly.20251111.51f952e7 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.15.0-nightly.20251111.51f952e7
Adds a Hook Execution Engine, enabling lifecycle hooks to run custom logic around tool execution. Not checked yet Preserves tab characters when pasting text into the prompt. Not checked yet
2 details in Everything
v0.15.0-nightly.20251110.c0b766ad
Prerelease
Nov 10, 2025
· release notes
gemini-cli v0.15.0-nightly adds /extensions restart command, live memory reload on extension changes, and a new a2a listCommands endpoint.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.15.0-nightly.20251110.c0b766ad https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.15.0-nightly.20251110.c0b766ad
└──▷ TRY IT
Reload all extensions mid-session after editing an extension config or toggling excluded tools — no need to restart the CLI.
copy
$ /extensions restart
Adds /extensions restart slash command to reload extensions without restarting the CLI. Not checked yet Reloads Gemini memory automatically when extensions are loaded or unloaded. Not checked yet Respects updates to excluded tools when extensions are reloaded at runtime. Not checked yet Adds listCommands endpoint to the a2a server. Not checked yet
4 details in Everything
v0.15.0-nightly.20251107.cd27cae8
Prerelease
Nov 7, 2025
· release notes
gemini-cli v0.15.0-nightly adds scrollable UI, extension enable/disable commands, subagent compression, and shell CWD context.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.15.0-nightly.20251107.cd27cae8 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.15.0-nightly.20251107.cd27cae8
Adds scrollable support to the CLI interface, enabling navigation through long outputs. Not checked yet Adds /enable and /disable commands for extensions, plus live reloading of custom commands. Not checked yet Adds compression mechanism to subagent to manage context size in multi-agent workflows. Not checked yet Includes current working directory in shell command descriptions for better context visibility. Not checked yet Notifies users when the model falls back to Flash, with an updated error message. Not checked yet
+1 more
show less
Adds ModelConfigService for centralized model configuration management. Not checked yet
6 details in Everything
gemini-cli v0.13.0 adds a validate command, hook configuration, extension hot-reload, kitty keyboard support, and model routing for all users.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0
└──▷ HOW TO FIND IT
Adjust the context compression threshold on the fly via the settings UI without editing config files.
📍 # In the gemini-cli settings UI, navigate to the compression threshold field and enter the desired token count. Note: requires a restart to take effect.
Adds validate command for catching common package/CLI regressions. Not checked yet Introduces Hook Configuration Schema and Types, enabling lifecycle hook definitions. Not checked yet Initial support for reloading extensions (MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers) in the CLI without restarting. Not checked yet Enables model routing for all users, automatically selecting the best model for each request. Not checked yet Adds kitty terminal protocol support for function keys. Not checked yet
+16 more
show less
Makes compression threshold editable in the UI settings. Not checked yet Adds auth_type to StartSessionEvent OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging. Not checked yet Adds extension name and ID to ToolCallEvent and slash command invocation telemetry. Not checked yet Adds active extensions list to StartSessionEvent telemetry. Not checked yet Introduces release channel detection in core. Not checked yet Adds support for listing active experiments. Not checked yet Adds DarkGray color to the ColorTheme palette for custom themes. Not checked yet Adds a response semantic color for UI theming. Not checked yet Adds alternate terminal buffer support. Not checked yet Enforces timeout for subagents and grants a recovery turn on TIMEOUT, MAX_TURNS, or NO_TOOL_CALL failures. Not checked yet Implements granular memory loaders for the JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. architecture. Not checked yet Removes context percentage from the footer by default, reducing UI noise. Not checked yet Hides the collapsed Todo tray when all items are complete. Not checked yet Handles untrusted folder prompts during extension install and link. Not checked yet Logs recovery/nudge events occurring inside subagents. Not checked yet Improves API key authentication flow. Not checked yet
21 details in Everything
└──▷ BREAKING ON UPGRADE
! The default compression threshold has changed; existing setups relying on the previous default will compress context at a different level.! model.compressionThreshold is now marked as requiring a restart to take effect.
gemini-cli v0.14.0 adds scrollable output, extension enable/disable commands, subagent compression, and shell CWD context.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.14.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.14.0-preview.0
└──▷ TRY IT
Reload a custom extension and toggle it on or off without restarting the CLI session.
copy
$ /disable my-extension
/enable my-extension
Adds scrollable support to the CLI output UI. Not checked yet Adds /enable and /disable commands for extensions, and live reloading of custom commands without restarting. Not checked yet Adds compression mechanism to subagent to manage long context automatically. Not checked yet Includes current working directory (cwd) in shell command descriptions for better context. Not checked yet Notifies users when the model falls back to Flash, with an updated error message. Not checked yet
+1 more
show less
Adds ModelConfigService for centralized model configuration management. Not checked yet
6 details in Everything
v0.13.0-nightly.20251105.da3da198
Prerelease
Nov 5, 2025
· release notes
gemini-cli gains hook I/O contracts, alternate buffer UI, thinking budget cap, WriteTodos tool, and subagent timeout/recovery.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0-nightly.20251105.da3da198 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0-nightly.20251105.da3da198
Adds hook type decoupling and translation, enabling hooks to be defined independently of their execution context. Not checked yet Adds hook input/output contracts, formalizing the data shapes passed to and returned from hooks. Not checked yet Adds hook execution planning and matching, giving the runtime a structured way to select and schedule which hooks fire. Not checked yet Enables alternate terminal buffer by default, keeping the shell history clean after gemini-cli exits. Not checked yet Grants subagents a recovery turn when they hit TIMEOUT, MAX_TURNS, or NO_TOOL_CALL failures. Not checked yet
+7 more
show less
Logs recovery events (nudges) that occur inside a subagent for post-hoc debugging. Not checked yet Enables the WriteTodos tool by default, letting the model maintain a persistent task list. Not checked yet Adds support for listing available experiments via the core experiments API. Not checked yet Integrates remote experiments configuration so experiment flags can be served dynamically. Not checked yet Enables codebase investigator by default for preview users. Not checked yet Adds semantic color to AI responses in the UI for faster visual parsing. Not checked yet Uses dynamic port allocation for MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. instead of the hardcoded port 7777. Not checked yet
12 details in Everything
gemini-cli v0.13.0-preview.0 adds a validate command, hooks schema, extension reloading, model routing, kitty keyboard support, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0-preview.0
└──▷ HOW TO FIND IT
Adjust the compression threshold live during a session without restarting — open Settings, find the threshold field, and change it (note: takes effect after restart).
📍 Press s to open Settings in the UI, navigate to model.compressionThreshold, edit the value, then restart gemini-cli for it to take effect.
Adds validate command for catching common package/CLI regressions. Not checked yet Initial support for reloading extensions (MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers) in the CLI without a full restart. Not checked yet Enables model routing for all users, automatically selecting the best model for each task. Not checked yet Adds Hook Configuration Schema and Types, enabling lifecycle hook configuration. Not checked yet Adds Kitty terminal protocol support for function keys. Not checked yet
+15 more
show less
Makes the context compression threshold editable directly in the UI settings. Not checked yet Adds alternate buffer support for improved terminal rendering. Not checked yet Grants subagents a recovery turn when they hit TIMEOUT, MAX_TURNS, or NO_TOOL_CALL failures. Not checked yet Enforces a timeout for subagent execution. Not checked yet Adds DarkGray to the ColorTheme for custom theme configuration. Not checked yet Adds a response semantic color to the UI color theme. Not checked yet Implements granular memory loaders for Just-In-Time (JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. ) architecture. Not checked yet Introduces release channel detection in the core. Not checked yet Adds support for listing experiments via the core. Not checked yet Adds auth_type and active extensions to StartSessionEvent OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging. Not checked yet Logs extension name with ToolCallEvent telemetry. Not checked yet Handles untrusted folders on extension install and link. Not checked yet Removes the context percentage from the footer by default. Not checked yet Improves the API key authentication flow. Not checked yet Adds policy engine documentation. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! The model.compressionThreshold setting now requires a restart to take effect.
gemini-cli v0.12.0 adds YOLO mode disable setting, extension aliases, sequential tool approval, and an executeCommand API endpoint.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.12.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.12.0
Adds a setting to disable YOLO mode, giving users control over autonomous tool execution. Not checked yet Adds an extension alias for the /extensions command for faster CLI access. Not checked yet Adds an executeCommand API endpoint with support for /extensions list. Not checked yet Supports requesting extension settings during install via extension settings. Not checked yet Implements sequential approval for tool execution, prompting confirmation one tool at a time. Not checked yet
+4 more
show less
Introduces a message bus for tool execution confirmation, enabling programmatic approval workflows. Not checked yet Adds BYOID (Bring Your Own Identity) auth client support when BYOID credentials are detected. Not checked yet Adds basic OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. (OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. ) trace instrumentation for developer observability. Not checked yet Supports recitation events in responses from the A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. Server. Not checked yet
9 details in Everything
v0.13.0-nightly.20251103.9187f6f6
Prerelease
Nov 3, 2025
· release notes
gemini-cli v0.13.0-nightly adds Hook Configuration Schema and Types plus a new DarkGray color theme option.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0-nightly.20251103.9187f6f6 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0-nightly.20251103.9187f6f6
Adds Hook Configuration Schema and Types, enabling structured hook definitions for extending gemini-cli behavior. Not checked yet Adds DarkGray to the ColorTheme options for terminal output customization. Not checked yet
2 details in Everything
v0.13.0-nightly.20251101.caf2ca14
Prerelease
Nov 1, 2025
· release notes
gemini-cli v0.13.0-nightly adds Kitty function-key support, release channel detection, and untrusted-folder handling on extension install.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0-nightly.20251101.caf2ca14 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0-nightly.20251101.caf2ca14
Adds Kitty terminal support for function keys, enabling full keyboard navigation in Kitty-based environments. Not checked yet Introduces release channel detection so the CLI can identify and report which release channel (stable, nightly, etc.) is in use. Not checked yet Handles untrusted folders during extension install and link, prompting appropriately rather than silently proceeding. Not checked yet Adds extension name to ToolCallEvent telemetry, giving operators visibility into which extension triggered each tool call. Not checked yet Adds slow-rendering metric and logging to telemetry, enabling detection of UI performance regressions. Not checked yet
5 details in Everything
v0.13.0-nightly.20251031.c89bc30d
Prerelease
Oct 31, 2025
· release notes
gemini-cli v0.13.0-nightly adds a validate command, extension reload support, model routing for all users, and editable compression threshold.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0-nightly.20251031.c89bc30d https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0-nightly.20251031.c89bc30d
Adds validate command for checking CLI configuration or extension correctness. Not checked yet Supports reloading extensions (MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers) without restarting the CLI session. Not checked yet Enables model routing for all users, previously limited to a subset. Not checked yet Allows the compression threshold to be edited interactively in the UI. Not checked yet Logs extension ID alongside tool call and slash command invocations for better traceability. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! The default compression threshold has changed, which may alter when context compression is triggered in existing sessions.
v0.13.0-nightly.20251030.42c79c64
Prerelease
Oct 30, 2025
· release notes
gemini-cli v0.13.0-nightly adds a config-based policy engine, extension explore subcommand, keychain-stored extension settings, and response recording for testing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.13.0-nightly.20251030.42c79c64 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.13.0-nightly.20251030.42c79c64
└──▷ TRY IT
Record live model responses during a session so they can be replayed deterministically in tests.
copy
$ gemini --record-responses
Discover the tools and capabilities exposed by an installed extension without starting a full chat session.
copy
$ gemini extension explore
New config-based policy engine with TOML TOML A configuration file format designed to be minimal and readable, mapping unambiguously to a hash table; cyber tools use it as a structured alternative to YAML or INI for config files. configuration for enforcing tool confirmation guards via message bus settings. Not checked yet New explore subcommand for extensions, enabling discovery of extension capabilities from the CLI. Not checked yet Adds support for sensitive, keychain-stored per-extension settings to protect extension credentials. Not checked yet New --record-responses flag to record model responses for use in testing workflows. Not checked yet Adds OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. -compliant semantic standard logging, including dev OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. trace instrumentation and a Genkit telemetry/dev UI setup script. Not checked yet
+4 more
show less
Granular memory loaders implemented for JIT JIT A runtime compilation strategy where code is translated from an intermediate form to native machine instructions at execution time, giving tools the speed of compiled code without sacrificing dynamic flexibility. (just-in-time) architecture in core. Not checked yet Improved API key authentication flow for a smoother onboarding experience. Not checked yet Debug drawer keybinding changed to F12. Not checked yet Adds auth_type and loaded extensions to StartSessionEvent OTel telemetry for richer session observability. Not checked yet
9 details in Everything
gemini-cli v0.11.0 adds stream-JSON headless output, markdown toggle, Todo List tab, up-arrow message editing, and telemetry activity monitor.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.11.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.11.0
└──▷ TRY IT
Pipe structured, line-delimited JSON from a headless gemini-cli session into downstream tooling for programmatic parsing.
copy
$ gemini --output-format stream-json -p "Summarize the CVEs in this report" < report.txt | jq '.text'
Toggle between rendered Markdown and raw text to inspect model output formatting or copy clean code blocks.
copy
$ # While gemini-cli is running, press:
alt+m
List all registered MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers including their extension names to verify your extension-provided servers are loaded.
Adds --output-format stream-json flag for headless mode to emit streaming JSON output. Not checked yet Adds alt+m keyboard shortcut to toggle between rendered Markdown and raw text in responses. Not checked yet Adds a Todo List Tab (TodoTray) for tracking in-session tasks. Not checked yet Enables editing queued messages using the up-arrow key before they are sent. Not checked yet Displays extension names in gemini mcp list command output. Not checked yet
+7 more
show less
Adds educative/witty tips during loading times for in-tool learning. Not checked yet Adds Esc to close visual hint to SettingsDialog and other dialogs. Not checked yet Adds ASK_USER policy decision UI wired up via the message bus. Not checked yet Adds telemetry activity monitor with event-driven snapshots. Not checked yet Suppresses slash command execution and suggestions inside shell mode. Not checked yet Removes the ctrl+t binding for /mcp commands and reorganizes MCP slash commands. Not checked yet Improves directory autocomplete by omitting trailing space after directory names. Not checked yet
12 details in Everything
└──▷ BREAKING ON UPGRADE
! The --all-files flag has been removed (deprecated flag dropped); scripts or workflows using it will fail.! Deprecated telemetry flags have been removed; any invocations relying on those flags will fail.! Workspace extensions and their migration support have been removed; workspace-scoped extension configurations will no longer work.
gemini-cli v0.12.0-preview.0 adds sequential approval, YOLO-mode disable setting, extension aliases, and BYOID auth support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.12.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.12.0-preview.0
└──▷ TRY IT
Call the new executeCommand endpoint to list extensions programmatically via the API.
copy
$ curl -X POST http://localhost:<port>/executeCommand -H 'Content-Type: application/json' -d '{"command": "/extensions list"}'
Adds extension alias for the extensions command for shorter CLI invocations. Not checked yet New setting to disable YOLO mode, giving users explicit control over auto-approval behavior. Not checked yet Implements sequential approval flow for tool execution confirmation via a message bus. Not checked yet Adds extension settings prompting on install, so extensions can request required config at setup time. Not checked yet Adds executeCommand endpoint with support for /extensions list in the API surface. Not checked yet
+4 more
show less
Supports Bring Your Own Identity (BYOID) authentication by automatically creating a BYOID auth client when BYOID credentials are detected. Not checked yet Adds basic OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. (OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. ) trace instrumentation for developer observability. Not checked yet Supports recitation events in responses from the A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. Server. Not checked yet Bumps bundled ripgrep version, improving search performance. Not checked yet
9 details in Everything
v0.12.0-nightly.20251027.cb0947c5
Prerelease
Oct 27, 2025
· release notes
gemini-cli v0.12.0-nightly adds sequential tool approval, ID token auth, BYOID support, and A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. recitation events.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.12.0-nightly.20251027.cb0947c5 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.12.0-nightly.20251027.cb0947c5
Introduces a message bus for tool execution confirmation, enabling structured approval workflows for tool calls. Not checked yet Implements sequential approval flow for reviewing and approving tool executions one at a time. Not checked yet Adds ID token support for authenticating to MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers. Not checked yet Adds BYOID (Bring Your Own Identity) auth client support when BYOID credentials are detected. Not checked yet Adds support for recitation events in responses from A2A servers. Not checked yet
+2 more
show less
Bumps bundled ripgrep version for improved search capabilities. Not checked yet Supports HTTP redirects in internal fetchJson calls. Not checked yet
7 details in Everything
v0.12.0-nightly.20251023.c4c0c0d1
Prerelease
Oct 23, 2025
· release notes
gemini-cli v0.12.0-nightly adds an executeCommand endpoint with /extensions list support and extension install-time settings requests.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.12.0-nightly.20251023.c4c0c0d1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.12.0-nightly.20251023.c4c0c0d1
Adds executeCommand endpoint supporting /extensions list to query installed extensions programmatically. Not checked yet Extensions can now declare and request user settings at install time. Not checked yet Surfaces internal errors through a unified event system for more consistent error visibility. Not checked yet
3 details in Everything
v0.12.0-nightly.20251023.a7faa208
Prerelease
Oct 23, 2025
· release notes
gemini-cli v0.12.0-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. prompt commands in non-interactive mode, loop-detection override, extensions alias, and a YOLO-mode disable setting.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.12.0-nightly.20251023.a7faa208 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.12.0-nightly.20251023.a7faa208
Enables running MCP prompt commands in non-interactive (scripted/piped) mode. Not checked yet Continues a request after the user disables loop detection mid-session. Not checked yet Adds extension as a short alias for the extensions command. Not checked yet Adds a setting to disable YOLO mode (auto-approve all tool calls). Not checked yet Adds logging for extensions activity. Not checked yet
5 details in Everything
gemini-cli v0.10.0 adds a code-guide command, interactive shell by default, smart edit enabled by default, GOOGLE_CLOUD_PROJECT_ID fallback, and failed-response retry.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0
└──▷ TRY IT
Use GOOGLE_CLOUD_PROJECT_ID as a fallback when GOOGLE_CLOUD_PROJECT is not set, avoiding auth failures in environments where only the _ID variant is configured.
copy
$ GOOGLE_CLOUD_PROJECT_ID=my-project-123 gemini
Adds code guide command for codebase investigation workflows. Not checked yet Enables interactive shell by default, improving command execution experience. Not checked yet Enables useSmartEdit by default for smarter, context-aware file edits. Not checked yet Supports GOOGLE_CLOUD_PROJECT_ID environment variable as a fallback for project configuration. Not checked yet Adds automatic retry with extra prompt on failed model responses. Not checked yet
+7 more
show less
Shortens the context overflow message when usage is below 75% of the limit. Not checked yet Generalizes path correction across tools for more reliable file targeting. Not checked yet Improves shell execution service reliability. Not checked yet Exposes Codebase Investigator settings to users via the settings dialog. Not checked yet Adds screen reader mode notification support. Not checked yet Supports extension pre-releases for early access to extension updates. Not checked yet Shows final install path in the extension consent dialog. Not checked yet
12 details in Everything
gemini-cli v0.11.0-preview.0 adds stream-JSON headless output, markdown toggle, Todo List tab, and up-arrow message editing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.11.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.11.0-preview.0
└──▷ TRY IT
Stream structured JSON output in a headless/scripted pipeline to parse Gemini responses programmatically.
copy
$ gemini --output-format stream-json -p "Summarize the security findings in report.txt"
Toggle between rendered Markdown and raw text while reviewing a response — useful when you need to copy raw syntax.
copy
$ # While in the gemini-cli interactive session, press:
alt+m
List MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers to see which extension each one belongs to.
Adds --output-format stream-json flag for headless mode to stream structured JSON output. Not checked yet Adds alt+m keyboard shortcut to toggle between rendered Markdown and raw text in the CLI. Not checked yet Adds a Todo List tab (TodoTray) to surface and track to-do items in the UI. Not checked yet Enables editing of queued messages using the up arrow key before they are sent. Not checked yet Displays extension names in gemini mcp list output for easier identification. Not checked yet
+7 more
show less
Blends educational tips with witty phrases during loading times. Not checked yet Adds Esc to close visual hint to SettingsDialog and other dialogs. Not checked yet Improves directory autocomplete by not appending a trailing space after directory names. Not checked yet Suppresses slash command execution and suggestions while in shell mode. Not checked yet Wires up UI for ASK_USER policy decisions, enabling interactive permission prompts via the message bus. Not checked yet Adds activity monitor with event-driven telemetry snapshots. Not checked yet Updates shell tool call colors to visually distinguish confirmed actions. Not checked yet
12 details in Everything
└──▷ BREAKING ON UPGRADE
! The --all-files flag has been removed (deprecated flag dropped).! Deprecated telemetry flags have been removed.! Support for workspace extensions and migrations has been removed.! The ctrl+t key binding for /mcp commands has been removed.
v0.11.0-nightly.20251021.e72c00cf
Prerelease
Oct 21, 2025
· release notes
gemini-cli v0.11.0-nightly adds a message bus and policy engine, plus full extension passing to context.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.11.0-nightly.20251021.e72c00cf https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.11.0-nightly.20251021.e72c00cf
Implements a message bus and policy engine for internal event routing and rule enforcement. Not checked yet Passes whole extensions (not just context files) to the model context, giving richer extension-aware sessions. Not checked yet
2 details in Everything
v0.11.0-nightly.20251020.a96f0659
Prerelease
Oct 20, 2025
· release notes
gemini-cli v0.11.0-nightly adds model routing, stream-JSON headless output, markdown toggle, todo list tab, and more UI capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.11.0-nightly.20251020.a96f0659 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.11.0-nightly.20251020.a96f0659
└──▷ TRY IT
Stream structured JSON output line-by-line from a headless gemini-cli invocation for pipeline integration.
copy
$ gemini --output-format stream-json -p "Summarize the CVEs in this advisory: $(cat advisory.txt)"
Inspect MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers registered via extensions, now showing the extension name alongside each server.
Toggle between rendered Markdown and raw model output while reviewing a response in the terminal.
copy
$ # While a response is displayed in gemini-cli, press: Alt+m
Enables Model Routing to automatically direct prompts to the best-fit model. Not checked yet Adds --output-format stream-json flag for streaming JSON output in headless/non-interactive mode. Not checked yet Adds alt+m keyboard shortcut to toggle between rendered Markdown and raw text in the terminal. Not checked yet Introduces a dedicated Todo List Tab (TodoTray) in the UI for tracking task lists generated during sessions. Not checked yet Includes the extension name in gemini mcp list command output for clearer MCP server identification. Not checked yet
+5 more
show less
Surfaces ASK_USER policy decision prompts in the UI message bus, enabling interactive permission flows. Not checked yet Allows editing queued messages using the up-arrow key before they are sent. Not checked yet Displays educative tips blended with witty phrases during loading times. Not checked yet Adds Esc to close visual hint across dialogs (Settings, and other closeable dialogs). Not checked yet Suppresses slash command execution and autocomplete suggestions inside shell command input. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! The deprecated --all-files flag has been removed; invocations using it will fail.! Deprecated telemetry flags have been removed; any scripts or configs referencing them will break.! Additional deprecated flags removed in this release will cause failures if still passed on the command line.! Workspace extensions and their migration support have been removed; workspace-scoped extension configurations will no longer work.! The ctrl-t key binding for /mcp commands has been removed.
gemini-cli v0.10.0-preview.0 adds failed-response retry, context-overflow protection, GOOGLE_CLOUD_PROJECT_ID fallback, and a new code guide command.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0-preview.0
└──▷ TRY IT
Use GOOGLE_CLOUD_PROJECT_ID as a fallback when GOOGLE_CLOUD_PROJECT is not set, avoiding manual flag overrides.
copy
$ export GOOGLE_CLOUD_PROJECT_ID=my-gcp-project && gemini
Adds automatic retry of failed model responses via an extra prompt, improving resilience in long sessions. Not checked yet Adds context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. overflow protection to stop chat from exceeding limits when sending messages. Not checked yet Supports GOOGLE_CLOUD_PROJECT_ID as a fallback environment variable for project configuration. Not checked yet Introduces a new code guide command for codebase investigation workflows. Not checked yet Enables interactive shell by default for shell command execution. Not checked yet
+7 more
show less
Enables useSmartEdit by default for more reliable in-place file edits. Not checked yet Generalizes path correction logic across all file-related tools. Not checked yet Improves shell execution service reliability on all platforms. Not checked yet Adds telemetry for subagent execution, web_fetch fallback attempts, diff stats in tool call metrics, and flicker detection. Not checked yet Exposes Codebase Investigator settings to users via the settings dialog. Not checked yet Optimizes Windows IDE process detection from O(N) to O(1) . Not checked yet Adds screen reader mode notification support. Not checked yet
12 details in Everything
gemini-cli v0.9.0 adds subagent support, OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. metrics, session auto-cleanup, and memory list subcommand.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0
└──▷ TRY IT
List all GEMINI.md memory files currently loaded, useful when debugging which context files are active across nested project directories.
copy
$ gemini memory list
Restrict the tools the agent may call in a non-interactive CI pipeline, now that --allowed-tools works in headless mode.
copy
$ gemini --allowed-tools read_file,run_shell_command -p "Summarize the test failures in the last run"
Adds enableSubagents configuration option to enable subagent registration and orchestration. Not checked yet Adds OpenTelemetry GenAI semantic convention metrics for telemetry instrumentation. Not checked yet Adds automatic session cleanup with a configurable retention policy. Not checked yet Adds memory list subcommand to display the paths of all active GEMINI.md files. Not checked yet Enables --allowed-tools flag in non-interactive (headless) mode. Not checked yet
+3 more
show less
Introduces debug logging for the IDE extension. Not checked yet Enforces auth token validation in the VS Code IDE companion extension. Not checked yet Adds sensitive keyword linter to flag potential credential leaks in prompts. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! The --path argument for the extensions install command has been removed.
v0.10.0-nightly.20251015.996c9f59
Prerelease
Oct 15, 2025
· release notes
Codebase investigator now enabled by default in gemini-cli nightly.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0-nightly.20251015.996c9f59 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0-nightly.20251015.996c9f59
Enables the codebase investigator feature by default ahead of the next preview release. Not checked yet
1 detail in Everything
v0.10.0-nightly.20251014.0a3e492e
Prerelease
Oct 14, 2025
· release notes
gemini-cli v0.10.0-nightly adds a code guide command, Alt+key combos, shell approval rework, and screen reader notifications.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0-nightly.20251014.0a3e492e https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0-nightly.20251014.0a3e492e
Adds a code guide command for codebase guidance workflows. Not checked yet Supports Alt+key keyboard combinations in the interactive UI. Not checked yet Reworks shell command approval flow for improved usability. Not checked yet Shows notifications in screen reader mode for accessibility. Not checked yet Enables useSmartEdit by default for smarter in-place edits. Not checked yet
+3 more
show less
Exposes Codebase Investigator settings to users via the settings dialog. Not checked yet Adds flicker detection and metrics to the UI. Not checked yet Optimizes Windows IDE process detection from O(N) to O(1) lookup. Not checked yet
8 details in Everything
v0.10.0-nightly.20251010.558be873
Prerelease
Oct 10, 2025
· release notes
gemini-cli v0.10.0-nightly adds generalized path correction, failed-response retry, diff stats in telemetry, and a full-width display setting.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0-nightly.20251010.558be873 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0-nightly.20251010.558be873
Generalizes path correction logic across all tools, improving reliability when referencing files in any tool context. Not checked yet Adds automatic retry of failed model responses via an extra prompt, reducing dead-end interactions. Not checked yet Adds diff stats to tool call metrics in telemetry for richer observability of file-editing operations. Not checked yet Adds a full-width display setting for narrow screen layouts. Not checked yet
4 details in Everything
v0.10.0-nightly.20251009.ae02236c
Prerelease
Oct 9, 2025
· release notes
Generalized path correction now applies across all tools in gemini-cli.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0-nightly.20251009.ae02236c https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0-nightly.20251009.ae02236c
Extends automatic path correction to work across all tools, not just a single tool. Not checked yet
1 detail in Everything
v0.10.0-nightly.20251009.cd354aeb
Prerelease
Oct 9, 2025
· release notes
gemini-cli v0.10.0-nightly adds session auto-cleanup, memory list, --allowed-tools in non-interactive mode, and context-overflow protection.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.10.0-nightly.20251009.cd354aeb https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.10.0-nightly.20251009.cd354aeb
└──▷ TRY IT
List all GEMINI.md memory file paths to audit which context files are active in your workspace.
copy
$ gemini memory list
Run a scripted, non-interactive task while restricting which tools the agent may call.
copy
$ echo 'Summarize the README' | gemini --allowed-tools read_file
Use GOOGLE_CLOUD_PROJECT_ID instead of GOOGLE_CLOUD_PROJECT when your environment already exports the former.
copy
$ export GOOGLE_CLOUD_PROJECT_ID=my-gcp-project && gemini 'list buckets in this project'
Adds automatic session cleanup and retention policy to manage old sessions. Not checked yet New list subcommand for memory command lists paths of all GEMINI.md files. Not checked yet Enables --allowed-tools flag in non-interactive (piped/scripted) mode. Not checked yet Adds context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. overflow protection to prevent failures when sending large chats. Not checked yet Supports GOOGLE_CLOUD_PROJECT_ID as a fallback environment variable alongside GOOGLE_CLOUD_PROJECT. Not checked yet
+8 more
show less
Introduces debug logging for the IDE extension. Not checked yet Enforces auth token validation in the VS Code IDE companion extension. Not checked yet Adds support for extension pre-releases. Not checked yet Adds memory monitor telemetry with activity-aware recording. Not checked yet Adds telemetry for subagent execution. Not checked yet Adds telemetry for web_fetch fallback attempts. Not checked yet Enables interactive shell by default. Not checked yet Conditionally applies CodebaseInvestigator in the system prompt for more targeted codebase analysis. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! The --path argument for the extensions install command has been removed.
gemini-cli v0.8.0 adds IAP/Cloud Run Cloud Run Google's managed container runtime that executes stateless workloads on demand, scaling to zero when idle, so tools can deploy without managing servers or paying for idle capacity. MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. support, model router, screen reader layout, tool output truncation, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0
Enables model router by default and exposes it in the settings dialog. Not checked yet Adds service account impersonation provider to MCPServers to support IAP-protected Cloud Run endpoints. Not checked yet Enables tool output truncation by default to keep context windows context windows The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. manageable. Not checked yet Adds content-based retries for JSON generation when the model returns malformed output. Not checked yet Adds AbortSignal support for retry logic and tool execution, enabling clean cancellation. Not checked yet
+12 more
show less
Implements centralized screen reader layout for accessibility. Not checked yet Adds a setting to display Gemini's status or thoughts in the terminal title and taskbar icon. Not checked yet Adds extension name auto-complete to /extensions update command. Not checked yet Adds enable/disable indicator in the extensions list. Not checked yet Uses lastPromptTokenCount to more accurately determine when context compression is needed. Not checked yet Makes compression algorithm slightly more aggressive to reduce context pressure. Not checked yet Sandbox images now pushed to Docker Hub instead of GHCR GHCR GitHub Container Registry, GitHub's hosted service for storing and distributing OCI-compatible container images, giving cyber tools a versioned, access-controlled image store tied directly to a GitHub repository. . Not checked yet Throws a descriptive error for invalid extension names. Not checked yet Adds character-level edit metrics and performance monitoring APIs to telemetry. Not checked yet Relaxes JSON schema validation to accept a broader range of MCP tool schemas. Not checked yet Reduces UI margin on narrow screens and reflows footer contents. Not checked yet Adds a confirmation dialog when updating extensions. Not checked yet
17 details in Everything
gemini-cli v0.9.0 adds subagent support, OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. GenAI metrics, session auto-cleanup, and a memory list subcommand.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-preview.0
└──▷ TRY IT
Audit which GEMINI.md memory files are active in your project hierarchy without opening each one.
copy
$ gemini memory list
Run a one-shot prompt in CI and restrict the model to only specific tools, now supported in non-interactive mode.
copy
$ gemini --allowed-tools read_file,shell_command -p "Summarize the security findings in REPORT.md"
Adds enableSubagents configuration option to enable and register subagents within gemini-cli. Not checked yet Adds OpenTelemetry GenAI semantic convention metrics for telemetry instrumentation. Not checked yet Adds automatic session cleanup and retention policy to manage stored sessions. Not checked yet Adds list subcommand to memory command to display paths of all GEMINI.md files. Not checked yet Enables --allowed-tools flag in non-interactive mode. Not checked yet
+2 more
show less
Introduces debug logging for the IDE extension. Not checked yet Enforces auth token validation in the VS Code IDE companion extension. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The --path argument for the extensions install command has been removed.
v0.9.0-nightly.20251002.0f465e88
Prerelease
Oct 2, 2025
· release notes
gemini-cli v0.9.0-nightly adds debug logging for the IDE extension and GitHub repo URL trailing-slash support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-nightly.20251002.0f465e88 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-nightly.20251002.0f465e88
Adds debug logging to the IDE extension for easier troubleshooting of extension behavior. Not checked yet Supports GitHub repo URLs with a trailing slash, removing a previous input restriction. Not checked yet
2 details in Everything
v0.9.0-nightly.20251002.a6af7bbb
Prerelease
Oct 2, 2025
· release notes
gemini-cli nightly adds IDE extension debug logging and agent submit_final_output tool
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-nightly.20251002.a6af7bbb https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-nightly.20251002.a6af7bbb
Introduces submit_final_output tool for agent completion workflows in the agents subsystem. Not checked yet Adds debug logging to the IDE extension for easier troubleshooting of extension behavior. Not checked yet Supports GitHub repo URLs with a trailing slash, removing a friction point when pasting URLs. Not checked yet
3 details in Everything
v0.9.0-nightly.20251002.4a70d6f2
Prerelease
Oct 2, 2025
· release notes
gemini-cli v0.9.0-nightly adds debug logging for the IDE extension and accepts GitHub repo URLs with trailing slashes.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-nightly.20251002.4a70d6f2 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-nightly.20251002.4a70d6f2
Adds debug logging to the IDE extension for easier troubleshooting of extension behavior. Not checked yet Supports GitHub repo URLs with a trailing slash, removing a common friction point when pasting URLs. Not checked yet
2 details in Everything
v0.9.0-nightly.20251002.460ec602
Prerelease
Oct 2, 2025
· release notes
gemini-cli v0.9.0-nightly adds debug logging for IDE extensions and accepts GitHub repo URLs with trailing slashes.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-nightly.20251002.460ec602 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-nightly.20251002.460ec602
Supports GitHub repo URLs with a trailing slash as valid input. Not checked yet Adds debug logging to the IDE extension. Not checked yet
2 details in Everything
v0.9.0-nightly.20251002.99958c68
Prerelease
Oct 2, 2025
· release notes
gemini-cli now accepts GitHub repo URLs with a trailing slash
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-nightly.20251002.99958c68 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-nightly.20251002.99958c68
v0.9.0-nightly.20251001.14dbda91
Prerelease
Oct 1, 2025
· release notes
gemini-cli v0.9.0-nightly adds regex search/replace editing, subagent support, and OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. GenAI metrics.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.9.0-nightly.20251001.14dbda91 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.9.0-nightly.20251001.14dbda91
└──▷ USE IT
Enable subagents in your gemini-cli config to allow the CLI to delegate tasks to registered sub-agents.
json
copy
# In your gemini-cli settings (e.g., settings.json)
{ "enableSubagents": true }
Adds regex search/replace support to the Smart Edit tool for more precise in-file editing. Not checked yet Adds enableSubagents configuration option to enable and register subagents. Not checked yet Introduces a Declarative Agent Framework for defining agents declaratively. Not checked yet Adds OpenTelemetry GenAI semantic convention metrics for standardized observability of LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. usage. Not checked yet Adds Smart Edit Strategy Logging to surface which edit strategy was selected. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! The model router is now disabled by default (--routing / model router behavior changes for existing setups relying on automatic model routing).
gemini-cli v0.8.0-preview.1 adds model router, IAP support, accessibility improvements, tool output truncation, and smarter context compression.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-preview.1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-preview.1
Enables model router by default and exposes it in the settings dialog. Not checked yet Adds service account impersonation provider to MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers to support Identity-Aware Proxy (IAP) on Cloud Run Cloud Run Google's managed container runtime that executes stateless workloads on demand, scaling to zero when idle, so tools can deploy without managing servers or paying for idle capacity. . Not checked yet Implements centralized screen reader layout for accessibility. Not checked yet Enables tool output truncation by default to manage context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. usage. Not checked yet Adds content-based retries for JSON generation to handle malformed model responses. Not checked yet
+17 more
show less
Uses lastPromptTokenCount to more accurately determine when context compression is needed. Not checked yet Adds a setting to display Gemini status or model thoughts in the terminal title and taskbar icon. Not checked yet Adds AbortSignal support for retry logic and tool execution, enabling proper cancellation. Not checked yet Adds name auto-complete to the /extensions update command. Not checked yet Adds an enable/disable indicator to the extensions list. Not checked yet Re-requests user consent when updating extensions that require it. Not checked yet Shows a confirmation dialog before applying extension updates. Not checked yet Throws an error for invalid extension names to surface misconfiguration early. Not checked yet Escapes ANSI control codes from model output before rendering to the terminal. Not checked yet Adds character-level edit metrics to telemetry. Not checked yet Sandbox images are now pushed to Docker Hub instead of GHCR GHCR GitHub Container Registry, GitHub's hosted service for storing and distributing OCI-compatible container images, giving cyber tools a versioned, access-controlled image store tied directly to a GitHub repository. . Not checked yet Supports standard GitHub release archive format for distribution. Not checked yet Uses dynamic client registration endpoint from config (when available) instead of re-performing OAuth discovery. Not checked yet Relaxes JSON schema validation for broader MCP tool compatibility. Not checked yet Improves compression algorithm aggressiveness to reduce context size. Not checked yet Removes border from user messages and colors > prompt for improved UI readability. Not checked yet Reduces margin on narrow screens and reflows footer contents for better layout. Not checked yet
22 details in Everything
gemini-cli v0.7.0 adds auto-updating git extensions, policy engine config, global telemetry/debug/proxy flags, and custom commands in headless mode.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.7.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.7.0
└──▷ TRY IT
Restrict which tools Gemini may call using a comma-separated list in one flag.
copy
$ gemini --allowed-tools read_file,run_shell_command 'Review the Dockerfile and explain any risks'
Adds auto-updating support for git-sourced extensions, keeping installed extensions current without manual intervention. Not checked yet Enables policy engine configuration directly from existing settings. Not checked yet Promotes --telemetry, --debug, and --proxy flags to global scope, making them available across all subcommands. Not checked yet Supports custom commands in non-interactive/headless mode, enabling scripted workflows. Not checked yet Emits a warning when memory usage exceeds 7 GB. Not checked yet
+6 more
show less
Adds extensions release flow support for simpler extension publishing. Not checked yet Includes MCP Server MCP Server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. name in ToolCallEvent OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for richer observability. Not checked yet Adds CORS CORS A browser mechanism that lets a server declare which foreign origins may read its HTTP responses, enforced by the browser to block unauthorized cross-site requests from JavaScript. and host validation hardening to the VS Code IDE companion server. Not checked yet Supports rendering function calls and responses when sharing chat to markdown. Not checked yet Supports comma-separated values for --allowed-tools. Not checked yet Adds activity detector with user interaction tracking to telemetry. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The shell setting usePty is renamed to enableInteractiveShell; existing configs referencing usePty will stop working.
v0.8.0-nightly.20250930.ae51bbda
Prerelease
Sep 30, 2025
· release notes
gemini-cli v0.8.0-nightly adds tab-completion for extension names in /extensions update.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-nightly.20250930.ae51bbda https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-nightly.20250930.ae51bbda
v0.8.0-nightly.20250929.ae387b61
Prerelease
Sep 29, 2025
· release notes
gemini-cli v0.8.0-nightly adds a confirmation dialog for extension updates and a red threshold indicator for status color.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-nightly.20250929.ae387b61 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-nightly.20250929.ae387b61
Adds a confirmation dialog when updating extensions, giving users a chance to review before applying changes. Not checked yet Adds a red threshold level to the status color utility, enabling clearer visual alerting at critical usage levels. Not checked yet Improves narrow-screen layout by reducing margins and reflowing footer contents for better usability on small terminals. Not checked yet
3 details in Everything
v0.8.0-nightly.20250929.a49a09f1
Prerelease
Sep 29, 2025
· release notes
gemini-cli v0.8.0-nightly adds content-based retries for JSON generation to improve reliability.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-nightly.20250929.a49a09f1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-nightly.20250929.a49a09f1
Adds content-based retries for JSON generation, automatically retrying when the model returns malformed or invalid JSON responses. Not checked yet
1 detail in Everything
v0.8.0-nightly.20250929.042288e7
Prerelease
Sep 29, 2025
· release notes
gemini-cli v0.8.0-nightly adds IAP/Cloud Run Cloud Run Google's managed container runtime that executes stateless workloads on demand, scaling to zero when idle, so tools can deploy without managing servers or paying for idle capacity. MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. support, terminal-title status display, and default tool output truncation.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-nightly.20250929.042288e7 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-nightly.20250929.042288e7
Adds service account impersonation provider to MCPServers, enabling IAP authentication for Cloud Run-hosted MCP endpoints. Not checked yet New setting to display Gemini status (or model thoughts) in the terminal title bar and taskbar icon. Not checked yet Enables tool output truncation by default to manage large tool responses. Not checked yet Makes context compression more aggressive and uses lastPromptTokenCount to more accurately trigger compression. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Tool output truncation is now enabled by default, which may change behavior for workflows that relied on full, untruncated tool output being passed to the model.
v0.8.0-nightly.20250927.19400ba8
Prerelease
Sep 27, 2025
· release notes
gemini-cli v0.8.0-nightly adds screen reader support and a cleaner user message UI.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-nightly.20250927.19400ba8 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-nightly.20250927.19400ba8
Implements centralized screen reader layout for improved accessibility. Not checked yet Removes border from user messages and colors the > prompt for improved readability. Not checked yet
2 details in Everything
v0.8.0-nightly.20250926.2defdcff
Prerelease
Sep 26, 2025
· release notes
gemini-cli v0.8.0-nightly adds a ToDo tool, auto-updating git extensions, policy engine config, and custom commands in headless mode.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.8.0-nightly.20250926.2defdcff https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.8.0-nightly.20250926.2defdcff
└──▷ TRY IT
Restrict which tools the model may call, specifying multiple tools in one flag without repeating it.
copy
$ gemini --allowed-tools read_file,grep,shell_exec "Audit all TODO comments in src/"
Adds a built-in ToDo tool to track ongoing task lists during a session. Not checked yet Supports auto-updating git extensions, keeping installed extensions current without manual reinstall. Not checked yet Enables policy engine configuration directly from existing settings. Not checked yet Custom commands now work in non-interactive/headless mode. Not checked yet Promotes --telemetry, --debug, and --proxy flags to global scope, usable with any subcommand. Not checked yet
+5 more
show less
Supports comma-separated values for --allowed-tools. Not checked yet Adds MCP Server MCP Server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. name to ToolCallEvent OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for richer trace attribution. Not checked yet Adds a simple extensions release flow, including GitHub Release extension support without requiring pre-built assets. Not checked yet Supports rendering function calls and responses when sharing chat to markdown. Not checked yet Hardens the VS Code IDE companion server with CORS CORS A browser mechanism that lets a server declare which foreign origins may read its HTTP responses, enforced by the browser to block unauthorized cross-site requests from JavaScript. and host validation. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! The shell setting usePty is renamed to enableInteractiveShell; existing configs using usePty will break.
gemini-cli v0.6.0 adds JSON output, /chat share, Ctrl+R history search, interactive shell, ripgrep by default, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.6.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.6.0
└──▷ TRY IT
Search command history interactively to re-run a previous prompt without retyping it.
copy
$ # Inside a gemini-cli session, press Ctrl+R then type keywords to fuzzy-search prior commands
Update all installed gemini-cli extensions to their latest versions in one step.
copy
$ gemini extensions update
Adds --output json format flag for machine-readable CLI output. Not checked yet New /chat share command to share the current conversation. Not checked yet Adds Ctrl+R command history search for previously run prompts. Not checked yet Adds Ctrl+Z / Ctrl+R undo/redo shortcuts in the input editor. Not checked yet Enables interactive commands via a virtual terminal in the shell tool. Not checked yet
+13 more
show less
Enables ripgrep (rg) by default for faster file search, with automatic re-download if the binary is deleted. Not checked yet Adds .geminiignore support to the glob tool for excluding files from searches. Not checked yet New extensions update command to update installed extensions. Not checked yet Supports installing a git extension at a specific ref and checking for extension updates. Not checked yet Adds a permission prompt when installing a local extension that includes MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers. Not checked yet Displays local/remote labels for MCP servers in the extensions list. Not checked yet Auto-approves pending tool calls when auto-edit (accept-edits) or yolo mode is activated. Not checked yet Adds a confirmation dialog for disabling loop detection for the current session. Not checked yet Caps shell output truncation threshold to the remaining context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. size. Not checked yet Adds auth token validation and support to the VS Code IDE companion server and IdeClient. Not checked yet Introduces classifier-based model routing strategy and a useModelRouter feature flag. Not checked yet Hybrid and encrypted OAuth token storage when the corresponding security flags are enabled. Not checked yet Stateful extensions list UI showing per-extension update status. Not checked yet
18 details in Everything
gemini-cli v0.7.0-preview.0 adds policy engine config, git extension auto-updates, headless custom commands, and global telemetry/debug/proxy flags.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.7.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.7.0-preview.0
└──▷ TRY IT
Restrict which tools Gemini can call, specifying multiple tools in a single comma-separated argument.
copy
$ gemini --allowed-tools read_file,run_shell_command 'Summarize all TODO comments in this repo'
Enable debug output globally alongside a prompt, now that --debug is a global flag.
copy
$ gemini --debug 'What files changed in the last commit?'
Adds policy engine configuration from existing settings via feat(cli): configure policy engine from existing settings. Not checked yet Supports auto-updating git extensions installed from GitHub release URLs. Not checked yet Enables custom commands in non-interactive/headless mode. Not checked yet Promotes --telemetry, --debug, and --proxy flags to global scope, usable with any subcommand. Not checked yet Adds MCP Server MCP Server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. name to ToolCallEvent OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for better tracing of MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool calls. Not checked yet
+6 more
show less
Emits a warning when memory usage exceeds 7 GB. Not checked yet Adds a simple extensions release flow to support publishing extensions. Not checked yet Supports rendering function calls and responses when sharing a chat session to Markdown. Not checked yet Correctly supports comma-separated values for --allowed-tools. Not checked yet Hardens the VS Code IDE companion server with CORS CORS A browser mechanism that lets a server declare which foreign origins may read its HTTP responses, enforced by the browser to block unauthorized cross-site requests from JavaScript. and host validation. Not checked yet Improves parsing of GitHub extension source URIs. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The shell setting usePty is renamed to enableInteractiveShell; existing configs using usePty will stop working.
v0.7.0-nightly.20250918.2722473a
Prerelease
Sep 18, 2025
· release notes
gemini-cli v0.7.0-nightly adds JSON output, /chat share, Ctrl+R history search, ripgrep by default, interactive shell, and undo/redo.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.7.0-nightly.20250918.2722473a https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.7.0-nightly.20250918.2722473a
└──▷ TRY IT
Search your session history to re-run a previous prompt without retyping it.
copy
$ # Inside an active gemini-cli session, press Ctrl+R then type keywords to fuzzy-search prior commands
Update all installed gemini-cli extensions to their latest versions.
copy
$ gemini extensions update
Adds --output json flag for machine-readable JSON output format. Not checked yet New /chat share slash command to share the current chat session. Not checked yet Adds Ctrl+R command history search in the input prompt. Not checked yet Adds Ctrl+Z / Ctrl+R undo/redo shortcuts in the input editor. Not checked yet Enables ripgrep by default for faster file search, with auto-redownload if the binary is deleted. Not checked yet
+15 more
show less
Supports interactive commands via a virtual terminal in the shell tool. Not checked yet New extensions update command to update installed extensions. Not checked yet Supports installing a git extension at a specific ref and checking for git extension updates. Not checked yet Adds .geminiignore support to the glob tool to exclude files from searches. Not checked yet Auto-approves pending tool calls when auto_edit or yolo mode is activated. Not checked yet Adds a confirmation dialog for disabling loop detection for the current session. Not checked yet Caps shell output truncation threshold to the remaining context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. size. Not checked yet Adds permission prompt when installing a local extension that includes MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers. Not checked yet Adds local/remote designation for MCP servers in extensions. Not checked yet Adds auth token validation and support to the VS Code IDE companion server. Not checked yet Introduces classifier-based model routing strategy and useModelRouter feature flag. Not checked yet Introduces hybrid token storage when the corresponding security flag is enabled. Not checked yet Introduces encrypted OAuth token storage flag. Not checked yet Checks for IDE diffing capabilities before opening diffs, with an improved diff communication protocol. Not checked yet IDE companion extension specification added, defining the diffing interface. Not checked yet
20 details in Everything
gemini-cli v0.5.3 adds docs/git/PR-review commands, runtime ripgrep download, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. slash-command discovery, and large tool-output auto-summarization.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.5.3 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.5.3
└──▷ TRY IT
Install an extension by passing the source as a positional argument (new syntax replaces the old flag).
copy
$ gemini extensions install <source>
Adds new /docs, /git, and PR-review slash commands for common developer workflows. Not checked yet Downloads ripgrep at runtime when enabled, removing the need to pre-install it. Not checked yet Improves discoverability of MCP server slash commands in the UI autocomplete and /help. Not checked yet Automatically saves large shell-command tool outputs to a file and returns a truncated summary to stay within context limits. Not checked yet Adds enum option support for settings, enabling constrained drop-down style configuration values. Not checked yet
+3 more
show less
Makes source a positional argument for the extensions install command, simplifying invocation. Not checked yet Allows users to type input while waiting for MCP servers to initialize. Not checked yet Adds hidden-property support for slash commands, letting commands opt out of autocomplete and /help discovery. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! Org/repo install support has been removed from the extensions install command.! The source argument for extensions install is now a positional argument rather than a flag.
gemini-cli v0.6.0-preview.2 adds JSON output, /chat share, Ctrl+R history search, interactive shell, ripgrep by default, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.6.0-preview.2 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.6.0-preview.2
└──▷ TRY IT
Search your command history interactively to re-run a previous prompt without retyping.
copy
$ # Inside a gemini-cli session, press Ctrl+R then type keywords to search prior commands
Update all installed gemini-cli extensions to their latest versions in one step.
copy
$ gemini extensions update
Adds --output json format flag for machine-readable CLI output. Not checked yet New /chat share command to share the current chat session. Not checked yet Adds Ctrl+R command history search for interactive use. Not checked yet Adds Ctrl+Z / Ctrl+R undo/redo shortcuts in the input editor. Not checked yet Enables ripgrep by default for faster file search, with automatic re-download if the binary is deleted. Not checked yet
+16 more
show less
Supports interactive commands with a virtual terminal in the shell tool. Not checked yet Adds .geminiignore support to the glob tool for file exclusion. Not checked yet New extensions update command to update installed extensions. Not checked yet Adds support for installing extensions at a specific git ref. Not checked yet Stateful extensions list UI showing per-extension update availability. Not checked yet Permission prompt when installing a local extension that includes MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers. Not checked yet Distinguishes local vs. remote MCP servers in the extensions UI. Not checked yet Auto-approves pending tool calls when auto-edit/yolo mode is activated. Not checked yet Confirmation dialog for disabling loop detection for the current session. Not checked yet Caps shell output truncation threshold to the remaining context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. size. Not checked yet Classifier-based model routing strategy introduced behind the useModelRouter feature flag. Not checked yet Hybrid token storage for credentials when the security flag is enabled. Not checked yet Encrypted OAuth token storage via new encrypted OAuth flag. Not checked yet Auth token validation and support added to the VS Code IDE companion server and client. Not checked yet IDE diff capability detection before opening diffs in the companion extension. Not checked yet JSON-formatted errors in non-interactive auth validation mode. Not checked yet
21 details in Everything
gemini-cli v0.5.0-preview.1 adds git/PR review commands, runtime ripgrep download, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. slash command discoverability, and smarter tool output handling.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.5.0-preview.1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.5.0-preview.1
└──▷ TRY IT
Install an extension by passing the source as a positional argument instead of a flag.
copy
$ gemini extensions install <source>
Adds new /docs, /git, and /PR review slash commands for documentation lookup, git operations, and pull request review workflows. Not checked yet Downloads ripgrep at runtime when enabled, removing the need for a pre-installed binary. Not checked yet Saves large shell command tool outputs to a file and returns truncated lines to the model, preventing context overflow. Not checked yet Improves discoverability of MCP slash commands in the UI. Not checked yet Adds enum option support in settings.json for constrained setting values. Not checked yet
+5 more
show less
Makes source a positional argument in extensions install, simplifying the install invocation. Not checked yet Allows users to type input while waiting for MCP servers to initialize. Not checked yet Adds hidden property support for slash commands, enabling commands to opt out of autocompletion and /help discovery. Not checked yet Moves scope settings into a new dedicated dialog for clearer configuration management. Not checked yet Shifts IDE context filtering to the CLI side and updates port discovery logic for the IDE companion. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! Org/repo install support for extensions has been removed; extensions install no longer accepts org/repo targets.
v0.6.0-nightly.20250910.a31830a3
Prerelease
Sep 10, 2025
· release notes
gemini-cli v0.6.0-nightly gains built-in docs, git, and PR review commands plus smarter tool-output summarization
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.6.0-nightly.20250910.a31830a3 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.6.0-nightly.20250910.a31830a3
Adds new built-in commands for docs lookup, git operations, and PR review workflows. Not checked yet Limits long tool output summarization to shell commands only, reducing unnecessary token usage for other tool types. Not checked yet Moves IDE context filtering to the CLI side and updates port discovery logic for IDE integrations. Not checked yet Adds a reusable EnumSelector UI component, enabling richer interactive selection prompts. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Org/repo install support has been removed; setups relying on installing extensions via org or repo references will break on upgrade.
gemini-cli v0.5.0-preview adds docs/git/PR-review commands, runtime ripgrep download, and large tool-output file offloading.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.5.0-preview https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.5.0-preview
└──▷ TRY IT
Install an extension by passing its source as a positional argument (new syntax after the flag was removed).
copy
$ gemini extensions install <source>
Adds new /docs, /git, and PR-review slash commands for common developer workflows. Not checked yet Downloads ripgrep at runtime (when enabled) instead of requiring a pre-installed binary. Not checked yet Saves large shell-command tool outputs to a file and returns only truncated lines, preventing context overflow. Not checked yet Improves discoverability of MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. slash commands in the UI. Not checked yet Adds enum option support for settings fields, enabling constrained value selection. Not checked yet
+4 more
show less
Allows typing in the chat input while MCP servers are still loading. Not checked yet Makes source a positional argument in the extensions install command. Not checked yet Supports hidden slash commands that opt out of autocompletion and /help discovery. Not checked yet Moves scope settings to a new dedicated dialog. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! The source argument for extensions install is now a positional argument instead of a flag; invocations using it as a named flag will break.! Org/repo install support has been removed from extensions; setups relying on that install path will no longer work.
gemini-cli v0.4.0 adds session recording, smart edits, fuzzy command matching, citations, extension linking, and more new CLI capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.4.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.4.0
└──▷ TRY IT
Get a summary of everything discussed after a long session, useful for handoff notes or audit trails.
copy
$ gemini --session-summary
Link a locally developed extension into gemini-cli without publishing it, for rapid iteration.
copy
$ gemini extensions link <path>
Pass a one-shot prompt directly on the command line for scripting or quick queries without entering interactive mode.
copy
$ gemini "Summarize the changes in the last 5 git commits"
Adds --session-summary flag to generate a summary at the end of a session. Not checked yet Adds gemini extensions link command to link local extensions for development. Not checked yet Adds flag to update all extensions at once. Not checked yet Supports installing extensions using org/repo shorthand syntax. Not checked yet Adds fuzzy matching for command suggestions when typing / commands. Not checked yet
+16 more
show less
Adds syntax highlighting for input /commands and @file/paths in the prompt. Not checked yet Integrates chat recording into GeminiChat sessions. Not checked yet Introduces a Smart Edit tool (internally named replace) for more precise file edits. Not checked yet Shows citations at the end of each response turn; enabled by default for certain users. Not checked yet Adds a Pro Quota dialog to surface quota information to users. Not checked yet Adds Ctrl+Backspace keyboard shortcut to delete a word backward in the input. Not checked yet Adds support for environment variable resolution inside extension configuration. Not checked yet Adds enforcedAuthType setting to lock down authentication method. Not checked yet Adds footer configuration settings for UI customization. Not checked yet Adds support for nested .gitignore files when filtering project files. Not checked yet Adds a positional argument for passing a prompt directly on the command line. Not checked yet Adds an MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. loading indicator when initializing the CLI. Not checked yet Skips MCP server connections in untrusted folders (folder trust enforcement). Not checked yet Merges general settings from multiple configuration sources (user, project, etc.). Not checked yet Simplifies MCP server timeout configuration. Not checked yet Supports custom witty loading messages. Not checked yet
21 details in Everything
gemini-cli v0.4.0-preview.4 adds session summaries, fuzzy command matching, smart edits, citation display, extension linking, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.4.0-preview.4 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.4.0-preview.4
└──▷ TRY IT
Summarize a long session at the end to capture key decisions and outputs without scrolling back.
copy
$ gemini --session-summary
Link a locally developed extension for testing without publishing it.
copy
$ gemini extensions link /path/to/my-extension
Pass a one-shot prompt directly on the command line for scripting or quick queries.
copy
$ gemini "Summarize the changes in CHANGELOG.md"
Adds --session-summary flag to generate a summary of the current session. Not checked yet Adds fuzzy matching for command suggestions when typing / commands. Not checked yet Introduces a Smart Edit (replace) tool for more precise in-file edits aligned with the EditTool. Not checked yet Shows citations at the end of each turn in responses. Not checked yet Adds gemini extensions link command to link a local extension directory. Not checked yet
+18 more
show less
Adds a flag to update all installed extensions at once. Not checked yet Supports installing extensions using org/repo shorthand syntax. Not checked yet Adds syntax highlighting for /commands and @file/paths in the input prompt. Not checked yet Adds footer configuration settings for UI customization. Not checked yet Supports Ctrl+Backspace keyboard shortcut to delete a word backward in the input. Not checked yet Handles nested .gitignore files for more accurate file filtering. Not checked yet Adds enforcedAuthType setting to lock down authentication method. Not checked yet Adds positional argument support for passing a prompt directly on the command line. Not checked yet Adds a Pro Quota Dialog to surface quota information to users. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. loading indicator during CLI initialization. Not checked yet Adds custom witty loading messages. Not checked yet Simplifies MCP server timeout configuration. Not checked yet Integrates chat recording into GeminiChat sessions. Not checked yet Merges general settings from multiple configuration sources. Not checked yet Folder trust is now generally available with the feature flag removed. Not checked yet MCP server connections are skipped in untrusted folders. Not checked yet Extensions are refused from loading in untrusted workspaces. Not checked yet VSCode workspace trust now overrides Gemini CLI folder trust when running in IDE mode. Not checked yet
23 details in Everything
v0.5.0-nightly.20250909.2b05cf3b
Prerelease
Sep 9, 2025
· release notes
gemini-cli v0.5.0-nightly adds runtime ripgrep download, enum settings options, and non-blocking MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server input.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.5.0-nightly.20250909.2b05cf3b https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.5.0-nightly.20250909.2b05cf3b
Downloads ripgrep at runtime when enabled, removing the need to pre-install it for search functionality. Not checked yet Adds support for enum options in settings, enabling constrained choices in configuration fields. Not checked yet Moves scope settings to a dedicated new dialog for cleaner configuration management. Not checked yet Allows users to type input while waiting for MCP servers to respond, eliminating forced idle time. Not checked yet
4 details in Everything
v0.5.0-nightly.20250908.4693137b
Prerelease
Sep 8, 2025
· release notes
gemini-cli v0.5.0-nightly gains improved MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. slash command discoverability and a new UIContext hook.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.5.0-nightly.20250908.4693137b https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.5.0-nightly.20250908.4693137b
Improves discoverability of MCP slash commands in the UI, making MCP integrations easier to find and use. Not checked yet Introduces useUI hook and UIContext for richer programmatic UI interaction. Not checked yet Allows slash commands to opt out of autocompletion and /help discovery for cleaner command surfaces. Not checked yet
3 details in Everything
gemini-cli v0.4.0-preview.2 adds session recording, smart edits, fuzzy command matching, citations, extension linking, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.4.0-preview.2 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.4.0-preview.2
└──▷ TRY IT
Get a written summary of everything discussed in the current session — useful for handoffs or saving context before closing.
copy
$ gemini --session-summary
Link a locally developed extension into gemini-cli for testing without publishing it.
copy
$ gemini extensions link /path/to/my-extension
Pass a prompt directly as a positional argument to drive gemini-cli non-interactively from scripts or CI.
copy
$ gemini "Summarize the changes in the last 10 git commits"
New --session-summary flag captures a summary of the current session. Not checked yet Adds gemini extensions link command to link a local extension by path. Not checked yet Adds flag to update all installed extensions at once. Not checked yet Supports installing extensions using org/repo shorthand syntax. Not checked yet New Smart Edit (replace) tool for more precise in-file edits aligned with the EditTool. Not checked yet
+20 more
show less
Integrates chat recording into GeminiChat via session recording support. Not checked yet Adds fuzzy matching for slash-command suggestions in the CLI prompt. Not checked yet Shows citations at the end of each conversation turn. Not checked yet Adds syntax highlighting for /commands and @file/paths in the input prompt. Not checked yet Adds footer configuration settings for UI customization. Not checked yet Adds enforcedAuthType setting to lock down the authentication method. Not checked yet Supports Ctrl+Backspace to delete a word backward in the input field. Not checked yet Adds a Pro Quota Dialog to surface quota upgrade options. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. loading indicator when initializing the CLI. Not checked yet Handles nested .gitignore files for more accurate file filtering. Not checked yet Adds a positional argument for passing a prompt directly on the command line. Not checked yet Simplifies MCP server timeout configuration. Not checked yet Supports resolving environment variables in extension configuration. Not checked yet Merges general settings from multiple configuration sources. Not checked yet Folder trust is now generally available — the feature flag has been removed. Not checked yet MCP server connections are skipped in untrusted folders. Not checked yet Extensions refuse to load from untrusted workspaces. Not checked yet CLI now restarts automatically when folder trust settings change. Not checked yet Screen reader accessibility updates for improved a11y support. Not checked yet Adds support for custom witty loading messages. Not checked yet
25 details in Everything
v0.5.0-nightly.20250906.968e9389
Prerelease
Sep 6, 2025
· release notes
gemini-cli v0.5.0-nightly adds extension update notifications, large tool output file offloading, and hidden slash commands.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.5.0-nightly.20250906.968e9389 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.5.0-nightly.20250906.968e9389
└──▷ TRY IT
Install an extension using the new positional source argument instead of a named flag.
copy
$ gemini extensions install <source>
Adds in-CLI notifications when a new extension version is available, with the ability to update directly from the prompt. Not checked yet Saves large tool outputs to a file and returns truncated lines to the model, preventing context overflow on verbose shell commands. Not checked yet Supports marking slash commands as hidden, enabling internal or developer-only commands that don't surface in the help UI. Not checked yet Makes source a positional argument in extensions install, simplifying the install invocation. Not checked yet Adds OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for FileOperationEvent, expanding observability coverage for file-based tool actions. Not checked yet
+1 more
show less
Improves performance of shell commands that produce large volumes of output. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! The telemetry fields ai_added_lines and ai_removed_lines are renamed to model_added_lines and model_removed_lines; any dashboards or pipelines consuming these field names will break.
gemini-cli v0.4.0-preview.1 adds session recording, smart edit, fuzzy command matching, citations, extension linking, and more new capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.4.0-preview.1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.4.0-preview.1
└──▷ TRY IT
Generate a summary of the current session's conversation at the end — useful for capturing context before closing a long working session.
copy
$ gemini --session-summary
Link a locally developed extension into gemini-cli for testing without publishing it.
copy
$ gemini extensions link <path>
Pass a prompt directly as a positional argument for quick one-shot queries or scripting.
copy
$ gemini "Summarize the file main.go"
Adds --session-summary flag to generate a summary at the end of a session. Not checked yet Adds gemini extensions link command to link local extensions for development. Not checked yet Adds flag to update all extensions at once. Not checked yet Supports installing extensions using org/repo shorthand syntax. Not checked yet Adds a Smart Edit (replace) tool for more precise, targeted file edits. Not checked yet
+16 more
show less
Adds fuzzy matching for slash-command suggestions in the CLI prompt. Not checked yet Shows citations at the end of each response turn. Not checked yet Adds syntax highlighting for /commands and @file/paths in the input prompt. Not checked yet Adds footer configuration settings for UI customization. Not checked yet Supports Ctrl+Backspace to delete a word backward in the input prompt. Not checked yet Integrates chat recording into GeminiChat sessions. Not checked yet Handles nested .gitignore files when determining file visibility. Not checked yet Adds a Pro Quota Dialog to surface quota information to users. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. loading indicator when initializing the CLI. Not checked yet Skips MCP server connections in untrusted folders (folder trust enforcement). Not checked yet Adds enforcedAuthType setting to lock down authentication method. Not checked yet Simplifies MCP server timeout configuration. Not checked yet Merges general settings from multiple configuration sources. Not checked yet Supports a positional argument for the prompt (pass prompt directly on the command line). Not checked yet Adds custom witty loading messages support. Not checked yet Enables citations by default for eligible users. Not checked yet
21 details in Everything
gemini-cli v0.4.0-preview adds session recording, smart edits, fuzzy commands, --session-summary, extension linking, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.4.0-preview https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.4.0-preview
└──▷ TRY IT
Generate a session summary at the end of a long agentic run to capture what was done.
copy
$ gemini --session-summary
Pass a prompt directly as a positional argument for quick, scriptable one-shot queries.
copy
$ gemini 'Summarize the TODOs in this repo'
Link a locally developed extension into gemini-cli without publishing it.
copy
$ gemini extensions link <path>
Adds --session-summary flag to generate a summary at the end of a session. Not checked yet Integrates chat recording into GeminiChat via session recording support. Not checked yet Introduces a Smart Edit (replace) tool for more precise in-file edits aligned with the EditTool. Not checked yet Adds fuzzy matching for slash-command suggestions in the CLI. Not checked yet Adds gemini extensions link command to link local extensions by path. Not checked yet
+16 more
show less
Adds flag to update all extensions at once. Not checked yet Supports installing extensions using org/repo shorthand. Not checked yet Supports resolving environment variables in extension configuration. Not checked yet Adds Pro Quota Dialog to surface quota information to users. Not checked yet Shows citations at the end of each turn. Not checked yet Adds syntax highlighting for input /commands and @file/paths. Not checked yet Adds footer configuration settings. Not checked yet Supports nested .gitignore files for file filtering. Not checked yet Adds Ctrl+Backspace keyboard shortcut to delete a word backward. Not checked yet Adds enforcedAuthType setting to lock down authentication method. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. loading indicator when initializing the CLI. Not checked yet Skips MCP server connections in untrusted folders (folder trust enforcement). Not checked yet Adds positional argument support for passing a prompt directly on the command line. Not checked yet Simplifies MCP server timeout configuration. Not checked yet Merges general settings from multiple configuration sources. Not checked yet Adds custom witty loading messages. Not checked yet
21 details in Everything
gemini-cli v0.3.0 adds extension management commands, screen reader mode, prompt completion, fuzzy search toggle, and custom theme file paths.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0
└──▷ TRY IT
Install, list, and remove a CLI extension to extend gemini-cli's capabilities.
copy
$ gemini extensions install <extension-name>
gemini extensions list
gemini extensions uninstall <extension-name>
Adds extensions install, uninstall, update, and list subcommands for managing CLI extensions. Not checked yet Introduces a screen reader mode flag for improved accessibility. Not checked yet Adds prompt completion in interactive mode. Not checked yet Adds option to disable fuzzy search. Not checked yet Supports specifying themes as file paths instead of named themes only. Not checked yet
+14 more
show less
Supports IDE connections via stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. transport. Not checked yet Improves MCP prompt argument parsing for more robust MCP tool invocation. Not checked yet Adds explicit license selection and visibility of license status. Not checked yet Supports JSON Schema formats via ajv-formats for MCP tool validation. Not checked yet Parallelizes memory discovery file operations for a significant performance improvement. Not checked yet Adds debug logging of keystrokes for input troubleshooting. Not checked yet Shares file list patterns between glob and grep tools for consistent filtering. Not checked yet Introduces system defaults (as distinct from system overrides) in settings. Not checked yet Enables editing of string settings directly from the settings UI. Not checked yet Handles 401 authentication errors for MCP HTTP URL connections. Not checked yet Handles special characters in file search paths. Not checked yet Adds MCP tool count and MCP tool name as telemetry dimensions. Not checked yet Logs MCP requests that result in errors for easier debugging. Not checked yet Adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for malformed JSON events. Not checked yet
19 details in Everything
v0.4.0-nightly.20250904.e133acd2
Prerelease
Sep 4, 2025
· release notes
gemini-cli v0.4.0-nightly adds extension management commands, --allowed-tools flag, YOLO/AUTO_EDIT lockout for untrusted folders, and subagent streaming.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.4.0-nightly.20250904.e133acd2 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.4.0-nightly.20250904.e133acd2
└──▷ TRY IT
Run gemini non-interactively in CI without confirmation prompts for specific tools, reducing pipeline friction.
copy
$ gemini --allowed-tools read_file,shell -p "Summarize all TODO comments in the repo"
Adds extensions install command to install extensions from the CLI. Not checked yet Adds extensions uninstall command to remove installed extensions. Not checked yet Adds extensions list command to view installed extensions. Not checked yet Adds extensions update command to update installed extensions. Not checked yet Adds extensions enable and extensions disable commands to toggle extensions without uninstalling. Not checked yet
+17 more
show less
Adds initial set of extension variables for use within extensions. Not checked yet Adds --allowed-tools flag to bypass tool confirmation prompts for specified tools. Not checked yet Disables YOLO and AUTO_EDIT modes when operating in untrusted folders, preventing unattended destructive actions. Not checked yet Enables incremental output streaming for subagent tasks. Not checked yet Adds OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. fallback to OAuth metadata lookup for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connections. Not checked yet Shares file list patterns between glob and grep tools, so filtering patterns apply consistently across both. Not checked yet Supports JSON Schema formats via ajv-formats for richer schema validation. Not checked yet Adds @file processing support in TOML TOML A configuration file format designed to be minimal and readable, mapping unambiguously to a hash table; cyber tools use it as a structured alternative to YAML or INI for config files. commands. Not checked yet Adds session ID logging for non-interactive sessions in debug mode. Not checked yet Displays usage details in the /tools command output. Not checked yet Introduces system defaults (separate from system overrides) in configuration. Not checked yet Standardizes exit codes across CLI operations. Not checked yet Makes error messages more informative. Not checked yet Adds A2A A2A Agent2Agent, an open protocol started by Google for AI agents from different vendors to discover each other, delegate tasks and exchange results. It complements MCP, which connects an agent to tools. -server package to gemini-cli. Not checked yet Adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for MalformedJsonEvent events. Not checked yet Enables Firebase Studio as a supported IDE install target. Not checked yet Prompts users to migrate workspace extensions on upgrade. Not checked yet
22 details in Everything
└──▷ BREAKING ON UPGRADE
! The CLI flags all_files and show_memory_usage have been removed.
gemini-cli v0.3.0-preview.3 adds extension management commands, prompt completion, screen reader mode, fuzzy search toggle, and custom theme file paths.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0-preview.3 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0-preview.3
└──▷ TRY IT
Install, list, and remove a CLI extension without leaving the terminal.
copy
$ gemini extensions install <extension-name>
gemini extensions list
gemini extensions uninstall <extension-name>
Load a custom color theme from a local JSON file instead of a built-in theme name.
copy
$ gemini --theme /path/to/my-theme.json
Disable fuzzy search when you need exact file/tool name matching in large repos.
copy
$ gemini --no-fuzzy-search
Adds extensions install, uninstall, update, and list subcommands for managing CLI extensions. Not checked yet Adds prompt completion in the CLI interactive prompt. Not checked yet Introduces a screen reader mode flag for improved accessibility. Not checked yet Adds option to disable fuzzy search in file/tool search. Not checked yet Supports specifying themes as file paths instead of only built-in theme names. Not checked yet
+12 more
show less
Supports IDE connections via stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. transport. Not checked yet Supports editing string settings directly from the settings UI. Not checked yet Handles 401 authentication errors for MCP HTTP URL connections. Not checked yet Improves MCP prompt argument parsing. Not checked yet Logs MCP requests that result in errors for easier debugging. Not checked yet Adds debug logging of keystrokes to aid input investigation. Not checked yet Supports JSON schema formats via ajv-formats in tool schemas. Not checked yet Shares file list patterns between glob and grep tools for consistency. Not checked yet Parallelizes memory discovery file operations for a performance gain. Not checked yet Adds explicit license selection and status visibility. Not checked yet Adds OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. logging for malformed JSON events. Not checked yet Retries message stream on empty chunks. Not checked yet
17 details in Everything
gemini-cli v0.3.0-preview.2 adds extension management commands, prompt completion, screen reader mode, fuzzy search toggle, and custom theme file paths.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0-preview.2 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0-preview.2
└──▷ TRY IT
Load a custom color theme from a local file instead of a built-in theme name.
copy
$ gemini --theme /path/to/my-theme.json
Adds extensions install command to install CLI extensions from the command line. Not checked yet Adds extensions uninstall command to remove installed CLI extensions. Not checked yet Adds extensions list command to view all installed extensions. Not checked yet Adds extensions update command to update installed extensions. Not checked yet Adds prompt completion support in the CLI for faster input. Not checked yet
+18 more
show less
Introduces a screen reader mode flag for accessibility. Not checked yet Adds option to disable fuzzy search in file/tool lookups. Not checked yet Supports specifying themes as file paths, enabling custom theme files. Not checked yet Supports IDE connections via stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. transport. Not checked yet Improves MCP prompt argument parsing for better structured input handling. Not checked yet Adds MCP error logging to include the originating MCP request alongside errors. Not checked yet Handles 401 authentication errors for HTTP URL-based MCP connections. Not checked yet Supports editing string settings directly from the settings UI. Not checked yet Adds explicit license selection with status visibility in the UI. Not checked yet Parallelizes memory discovery file operations for significant performance improvement. Not checked yet Shares file list patterns between glob and grep tools for consistent filtering. Not checked yet Supports special characters in file search paths. Not checked yet Supports all content types in prompts from Zed IDE integration. Not checked yet Adds debug logging of keystrokes to aid input investigation. Not checked yet Supports JSON schema formats using ajv-formats in MCP tool schemas. Not checked yet Introduces system defaults configuration (separate from system overrides). Not checked yet Retries message stream on empty chunk responses for improved reliability. Not checked yet Adds MCP tool count and MCP tool name as telemetry dimensions. Not checked yet
23 details in Everything
gemini-cli v0.3.0-preview.1 adds extension management commands, screen reader mode, prompt completion, fuzzy search toggle, and custom theme file paths.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0-preview.1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0-preview.1
└──▷ TRY IT
Install, list, and remove a CLI extension without manually editing config files.
copy
$ gemini extensions install <extension-name>
gemini extensions list
gemini extensions uninstall <extension-name>
Adds extensions install, uninstall, update, and list commands for managing CLI extensions. Not checked yet Introduces a screen reader mode flag for improved accessibility. Not checked yet Adds prompt completion support in the CLI REPL. Not checked yet Supports specifying themes as file paths instead of built-in names only. Not checked yet Adds an option to disable fuzzy search. Not checked yet
+14 more
show less
Supports editing string settings directly in the settings UI. Not checked yet Adds IDE connection support via stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. transport. Not checked yet Supports MCP HTTP URL 401 error handling for authentication flows. Not checked yet Improves MCP prompt argument parsing. Not checked yet Includes MCP request details in error logs. Not checked yet Shares file list patterns between glob and grep tools for consistent filtering. Not checked yet Handles special characters in file search paths. Not checked yet Supports JSON schema formats using ajv-formats in tool definitions. Not checked yet Introduces system defaults (distinct from system overrides) for enterprise configuration. Not checked yet Parallelizes memory discovery file operations for a significant performance gain. Not checked yet Adds debug logging of keystrokes for diagnostic investigation. Not checked yet Adds explicit license selection with status visibility. Not checked yet Writes workspace path to IDE port file for improved IDE integration. Not checked yet Supports all content types in prompts from Zed. Not checked yet
19 details in Everything
gemini-cli v0.2.0 adds automatic conversation saving, Zed editor integration, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server restart, and auto-approval of trusted tools.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.2.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.2.0
└──▷ TRY IT
Restart a misbehaving MCP server mid-session without restarting the entire CLI.
Adds automatic conversation saving via a new core ChatRecordingService that records sessions without manual intervention. Not checked yet Integrates with the Zed editor to read and write files directly through Zed. Not checked yet Adds /mcp refresh now restarts MCP servers in addition to reloading configuration. Not checked yet Adds hideFooter setting to remove the footer from the CLI UI. Not checked yet Adds skipNextSpeakerCheck setting for fine-grained control over conversation turn logic. Not checked yet
+5 more
show less
Auto-approves compatible pending tools when allow always is selected, reducing repetitive confirmation prompts. Not checked yet Shows /ide subcommands based on live connection status rather than a static ideMode boolean. Not checked yet Includes IDE client information in /bug and /about output when IDE mode is active. Not checked yet Adds file change tracking to session metrics. Not checked yet Refactors shell execution to use node-pty, enabling proper pseudo-terminal support. Not checked yet
10 details in Everything
v0.3.0-nightly.20250823.1a89d185
Prerelease
Aug 23, 2025
· release notes
gemini-cli v0.3.0-nightly adds fuzzy search toggle, file-path themes, improved MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. argument parsing, and license visibility.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0-nightly.20250823.1a89d185 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0-nightly.20250823.1a89d185
└──▷ TRY IT
Load a custom theme file from disk instead of relying on a built-in theme name.
copy
$ gemini --theme /path/to/my-theme.json
Adds option to disable fuzzy search for more precise result control. Not checked yet Supports specifying themes as file paths, enabling custom theme files outside built-in options. Not checked yet Improves MCP prompt argument parsing for more reliable MCP integrations. Not checked yet Adds explicit license selection and status visibility in the CLI. Not checked yet Includes programming language metadata in CLI telemetry events. Not checked yet
+2 more
show less
Logs MCP requests that result in errors for easier MCP debugging. Not checked yet Adds debug logging of keystrokes to support input investigation. Not checked yet
7 details in Everything
v0.3.0-nightly.20250822.15c62bad
Prerelease
Aug 22, 2025
· release notes
gemini-cli v0.3.0-nightly adds prompt completion, screen reader mode, IDE stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connections, and editable string settings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0-nightly.20250822.15c62bad https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0-nightly.20250822.15c62bad
Adds prompt completion in the CLI for faster, tab-assisted input. Not checked yet Introduces a screen reader mode flag for accessibility support. Not checked yet Supports IDE connections via stdio MCP, enabling editor integrations. Not checked yet Enables editing of string settings directly from the settings UI. Not checked yet Adds graceful 401 error handling for HTTP URL MCP client connections. Not checked yet
+1 more
show less
Parallelizes memory discovery file operations for faster context loading. Not checked yet
6 details in Everything
v0.3.0-nightly.20250821.653267a6
Prerelease
Aug 21, 2025
· release notes
gemini-cli v0.3.0-nightly adds stdin+prompt combining, HTTP OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. , MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server restart, automatic conversation saving, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.3.0-nightly.20250821.653267a6 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.3.0-nightly.20250821.653267a6
└──▷ TRY IT
Pipe file contents into gemini-cli while also supplying an inline prompt — useful for quick one-shot analysis in CI or shell scripts.
copy
$ cat findings.txt | gemini -p "Summarize the security findings above and suggest remediation steps"
Restart a misbehaving MCP server mid-session without leaving the CLI — handy after updating an MCP tool's config.
Supports combining -p and stdin for prompt input, enabling piped data to be merged with an inline prompt in non-interactive mode. Not checked yet Adds HTTP OpenTelemetry exporter support for shipping traces to any OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. -compatible backend. Not checked yet Introduces ChatRecordingService for automatic conversation saving across sessions. Not checked yet Adds /mcp refresh now restarts MCP servers in addition to refreshing their state. Not checked yet Introduces a non-recursive file search strategy for faster file discovery in large repositories. Not checked yet
+14 more
show less
Adds MCP Root change notifications so MCP servers are informed when workspace roots change. Not checked yet Includes disallowed command names in shell block reason messages for clearer audit output. Not checked yet Adds argument support for shell execution in custom slash commands. Not checked yet Displays untrusted workspace status in the CLI footer. Not checked yet Shows /ide subcommands conditionally based on actual IDE connection status. Not checked yet Adds IDE client name to /about and /bug output when IDE mode is active. Not checked yet Adds session ID to session summary and /bug report template. Not checked yet Adds GitHub OAuth support and resource parameter handling to the OAuth spec. Not checked yet Logs telemetry event when chat context is compressed. Not checked yet Tracks file changes as a session metric. Not checked yet Reads and writes files through Zed editor integration. Not checked yet Supports multi-folder workspaces in IDE mode. Not checked yet Logs CLI version and git commit hash on startup. Not checked yet Saves empty conversations (system context only) with /chat save. Not checked yet
19 details in Everything
gemini-cli v0.2.0-preview.0 adds automatic conversation saving, Zed editor integration, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server restart, and tool auto-approval.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.2.0-preview.0 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.2.0-preview.0
└──▷ TRY IT
Restart a misbehaving MCP server mid-session without quitting gemini-cli.
Introduces ChatRecordingService for automatic conversation saving to session files. Not checked yet Adds read/write file access through the Zed editor via IDE integration. Not checked yet Adds hideFooter setting to hide the footer from the CLI UI. Not checked yet Enables /mcp refresh to restart MCP servers in addition to refreshing them. Not checked yet Shows /ide subcommands dynamically based on actual IDE connection status rather than a static boolean. Not checked yet
+5 more
show less
Adds IDE client information to /bug and /about output when IDE mode is enabled. Not checked yet Adds skipNextSpeakerCheck setting to control speaker-check behavior in core. Not checked yet Auto-approves compatible pending tools when allow always is selected, reducing repetitive prompts. Not checked yet Refactors shell execution to use node-pty for improved terminal emulation support. Not checked yet Adds file change tracking metrics to session telemetry. Not checked yet
10 details in Everything
gemini-cli v0.1.22 adds stdin+flag prompt combining, HTTP OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. export, non-recursive file search, and shell argument support in custom commands.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.22 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.22
└──▷ TRY IT
Pipe a file's contents into gemini-cli while also supplying a prompt flag — useful for scripted code review in CI.
copy
$ cat findings.json | gemini -p "Summarize the critical findings in this report"
Supports combining -p flag with stdin so piped content and inline prompts can be used together in a single invocation. Not checked yet Adds HTTP OpenTelemetry exporter support, enabling traces to be sent to any OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. -compatible HTTP collector. Not checked yet Introduces a non-recursive file search strategy for faster, shallower workspace scans. Not checked yet Enables arguments for shell execution in custom slash commands, making custom commands more flexible and parameterizable. Not checked yet Shows untrusted directory status in the footer UI, giving a persistent visual indicator of workspace trust state. Not checked yet
+6 more
show less
Adds session ID to session summary and /bug report template for easier cross-referencing of support issues. Not checked yet Displays the IDE client's display name in /about output when running in IDE-integrated mode. Not checked yet Shows the disallowed command name in the block reason when a shell command is denied. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. Root change notifications so MCP servers are informed when workspace roots change. Not checked yet Logs telemetry when chat context compression occurs, improving observability of context management. Not checked yet Adds GitHub OAuth support and resource parameter to the OAuth spec implementation. Not checked yet
11 details in Everything
gemini-cli v0.1.21 adds VS Code & Zed IDE integration, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, custom themes, and a new /ide command suite.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.21 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.21
└──▷ TRY IT
Suppress the startup banner in scripted or automated sessions to keep output clean.
copy
$ echo '{"hideBanner": true}' >> ~/.gemini/settings.json
Route all gemini-cli traffic through a corporate proxy.
copy
$ gemini --proxy http://proxy.corp.example.com:8080
Check IDE integration status and install the companion extension from the CLI.
copy
$ gemini
# then inside the session:
/ide status
/ide install
Introduces a VS Code companion extension (VSIX bundled with release) for IDE-aware sessions. Not checked yet Adds Zed editor integration. Not checked yet New /ide status and /ide install commands to manage IDE integration from the CLI. Not checked yet Streams notifications when the active file changes in IDE mode, threading the open file into model context. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth infrastructure (Part 1) for authenticated MCP server connections. Not checked yet
+20 more
show less
Introduces a loop detection service that automatically breaks simple agent loops, with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop checking as a second layer. Not checked yet Adds support for allowed/excluded MCP server name lists in settings. Not checked yet Displays blocked MCP servers in the MCP status display. Not checked yet Shows MCP server stderr output when running in debug mode. Not checked yet New hideBanner setting to suppress the startup banner. Not checked yet Adds an explicit --proxy option to route CLI traffic through a proxy. Not checked yet Adds custom theme support via configuration. Not checked yet Enables automatic detection of non-interactive environments, falling back to a code-based OAuth flow (useful for Docker/CI). Not checked yet Displays declined confirmation code diffs so you can review what was rejected. Not checked yet Runs model availability check in the background to speed up startup time. Not checked yet Tool summarization is now opt-in: only enabled when explicitly set in settings.json. Not checked yet Tool list is now sorted alphabetically for deterministic output. Not checked yet Clears the input buffer on Ctrl+C when no command is executing. Not checked yet Adds numbers to selection lists for faster keyboard-driven picking. Not checked yet Hides the cursor when the terminal window is unfocused. Not checked yet Light theme color improvements. Not checked yet Enhanced OAuth callback for robust Docker support. Not checked yet Slash commands now execute immediately on a perfect match without requiring an extra keypress. Not checked yet Improved command completion trigger logic based on cursor position. Not checked yet Uses simplified (short) names for MCP tools where unambiguous. Not checked yet
25 details in Everything
└──▷ BREAKING ON UPGRADE
! Tool summarization is no longer enabled by default; it must be explicitly set in settings.json to remain active.
v0.1.19-nightly.250814.514e883a
Prerelease
Aug 14, 2025
· release notes
gemini-cli v0.1.19-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, extension listing, SVG support, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.19-nightly.250814.514e883a https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.19-nightly.250814.514e883a
└──▷ TRY IT
Restrict an automated pipeline to only a trusted subset of configured MCP servers.
copy
$ gemini --allowed-mcp-server-names my-server,another-server
Block specific noisy or high-risk tools exposed by an MCP server without removing the server entirely.
json
copy
# In settings.json or .gemini/config.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"excludeTools": ["dangerous_tool", "verbose_tool"]
}
}
}
Discover which extensions are available and enable them from the command line.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at startup. Not checked yet Adds excludeTools and includeTools options to mcpServers config to filter individual MCP tools per server. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+10 more
show less
Adds user startup warnings and home directory checks to surface misconfigurations early. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, improving performance. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Raises minimum required Node.js version to 20. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Improves isCommandAllowed error messages for clearer shell permission feedback. Not checked yet Formats tool execution time as minutes and seconds instead of raw milliseconds. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet Consolidates all CLI flags to use hyphens; underscore variants are deprecated. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum Node.js version is now 20; setups running Node.js <20 will fail to run gemini-cli.! All underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated in favour of hyphen-style equivalents (e.g. --allowed-mcp-server-names); underscore variants may stop working in a future release.
gemini-cli v0.1.20 adds --approval-mode flag and a new VS Code IDE integration.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.20 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.20
└──▷ TRY IT
Run gemini-cli in an automated pipeline where you want to pre-approve all tool calls without manual confirmation.
copy
$ gemini --approval-mode auto
Adds --approval-mode parameter to control how the CLI handles tool-call approvals without interactive prompts. Not checked yet Launches VS Code IDE integration, enabling gemini-cli to operate as a backend for the VS Code extension. Not checked yet
2 details in Everything
v0.1.19-nightly.250813.9d023be1
Prerelease
Aug 13, 2025
· release notes
gemini-cli v0.1.19-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.19-nightly.250813.9d023be1 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.19-nightly.250813.9d023be1
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when your config lists many servers but you only want a trusted subset active during a pentest session.
copy
$ gemini --allowed-mcp-server-names shodan,nuclei
Limit the tools exposed by a specific MCP server so the agent cannot call dangerous endpoints — set in your gemini settings.json.
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"excludeTools": ["delete_resource", "shutdown"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at startup. Not checked yet Adds excludeTools and includeTools options in mcpServers config to filter individual tools exposed by an MCP server. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Supports .svg files as input via the @file mechanism. Not checked yet Enables Gemini CLI to reuse the user's existing auth when running inside Google Cloud Shell. Not checked yet
+12 more
show less
Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Adds user startup warnings and a home-directory check to catch common misconfigurations early. Not checked yet Displays improved, context-aware error messages when a shell command is blocked by isCommandAllowed. Not checked yet Shows YOLO mode shortcut inside /help output. Not checked yet Raises the minimum required Node.js version to 20. Not checked yet Consolidates all CLI flags to use hyphens (underscore variants are deprecated). Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Improves 429/quota error handling, taking Code Assist customer tiers into account, and removes auto-execution Flash fallback on quota errors. Not checked yet Improves auth environment-variable validation and messaging to detect settings that confuse the GenAI SDK. Not checked yet Displays --help output at full terminal width. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet Handles inline content modification in the tool scheduler. Not checked yet
17 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum supported Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! All CLI flags have been consolidated to use hyphens; underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated and may stop working in a future release.! The /chat command now requires a tag argument; existing scripts or muscle-memory invoking /chat without a tag will fail.
gemini-cli v0.1.19 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. management commands, fzf file completion, subagent architecture, /settings panel, and IDE diff support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.19 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.19
└──▷ TRY IT
Open the interactive settings panel mid-session to inspect or change configuration without restarting.
Adds gemini mcp add, gemini mcp remove, and gemini mcp list subcommands for managing MCP server configurations from the CLI. Not checked yet Adds MCP Roots support for scoping MCP server access. Not checked yet Detects tools with bad or cyclic schemas and automatically omits them with a warning rather than failing silently. Not checked yet Introduces Foundational Subagent Architecture, enabling agent-spawning workflows within gemini-cli. Not checked yet Adds @-command file path completion powered by fzf integration for faster, fuzzy file targeting. Not checked yet
+15 more
show less
Introduces /settings slash command and UI panel for in-session configuration management. Not checked yet Adds overwrite confirmation dialog to /chat save to prevent accidental overwrites. Not checked yet Supports in-IDE diff handling and rendering via the edit tool when running in IDE mode. Not checked yet Adds folderTrust setting and launch dialog to control which folders the CLI trusts on startup. Not checked yet Adds a configurable context percentage threshold for triggering automatic context compression. Not checked yet Adds option to hide line numbers in code blocks (showLineNumbers config option). Not checked yet Supports non-recursive file search mode. Not checked yet Enables exiting the authentication menu with CTRL+C (SIGINT). Not checked yet Adds double-ESC to clear the current input line. Not checked yet Drops load-memory-from-include-directories CLI argument (removed from the CLI args surface). Not checked yet Adds host validation to GoogleCredentialProvider for improved credential security. Not checked yet Improves UI layout adaptation for narrow terminals. Not checked yet Introduces DeclarativeTool and ToolInvocation primitives for tool authoring. Not checked yet Adds a request queue to the tool scheduler to serialize concurrent tool invocations. Not checked yet Hints VS Code users to enable IDE integration when detected. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! The load-memory-from-include-directories option is dropped from CLI args; any scripts or configs passing this flag will break.
v0.1.18-nightly.250812.26fe587b
Prerelease
Aug 12, 2025
· release notes
gemini-cli v0.1.18-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool inclusion/exclusion.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.18-nightly.250812.26fe587b https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.18-nightly.250812.26fe587b
└──▷ TRY IT
Restrict which MCP servers are loaded at startup to reduce attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. in automated pipelines.
copy
$ gemini --allowed-mcp-server-names filesystem,github
Limit or expand which tools a specific MCP server exposes, keeping only the tools you actually need.
json
copy
# In settings.json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"],
"includeTools": ["read_file", "list_directory"],
"excludeTools": ["write_file"]
}
}
}
List all available extensions from the command line to audit what is available before enabling.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at startup. Not checked yet Adds excludeTools and includeTools fields to mcpServers config for per-server tool filtering. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+11 more
show less
Adds user startup warnings including a home directory check. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, improving performance. Not checked yet Adds improved error messages in isCommandAllowed for shell command permission denials. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Updates minimum required Node.js version to 20. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Removes auto-execution on Flash model during 429/quota failover. Not checked yet Adds improved auth environment variable validation with clearer messaging for GenAI SDK conflicts. Not checked yet Refactors all CLI flags to use hyphens; underscore variants are deprecated. Not checked yet Improves handling of inline content modification in the tool scheduler. Not checked yet Formats tool execution time display as minutes and seconds. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! Minimum Node.js version is now 20; setups running Node.js <20 will no longer work.! All CLI flags are consolidated to use hyphens (e.g., --allowed-mcp-server-names); underscore-style flags (e.g., --allowed_mcp_server_names) are deprecated and may stop working in a future release.! The /chat command now requires a tag argument; invocations without a tag will fail.
v0.1.18-nightly.250811.2865a527
Prerelease
Aug 11, 2025
· release notes
gemini-cli v0.1.18-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool inclusion/exclusion.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.18-nightly.250811.2865a527 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.18-nightly.250811.2865a527
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful in regulated environments where only approved servers should be active.
copy
$ gemini --allowed-mcp-server-names my-corp-server,approved-scanner
Limit exactly which tools from a given MCP server are exposed to the model, reducing attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. .
json
copy
# In settings.json mcpServers block:
{
"mcpServers": {
"my-corp-server": {
"command": "npx my-corp-mcp",
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["exec_shell"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at startup. Not checked yet Adds excludeTools and includeTools options to mcpServers config for per-server tool filtering. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for @file context inclusion. Not checked yet Enables reuse of the user's existing auth token when running inside Google Cloud Shell. Not checked yet
+9 more
show less
Initializes MCP tools once at startup instead of re-initializing on every authentication event, reducing latency. Not checked yet Adds user startup warnings including a home directory check. Not checked yet Displays YOLO mode shortcut inside /help. Not checked yet Updates minimum required Node.js version to 20. Not checked yet Improves 429/quota error handling with awareness of Code Assist customer tiers. Not checked yet Improves error messages in isCommandAllowed for shell command policy violations. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet Formats tool execution time display as minutes and seconds. Not checked yet Adds general usage message to --help output, using full terminal width. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; setups running Node.js <20 will break on upgrade.! All CLI flags are consolidated to use hyphens; underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated and may not be recognized in future releases.! The /chat command now requires a tag argument; invocations without a tag will fail.
v0.1.18-nightly.250810.c632ec8b
Prerelease
Aug 10, 2025
· release notes
gemini-cli v0.1.18-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool inclusion/exclusion.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.18-nightly.250810.c632ec8b https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.18-nightly.250810.c632ec8b
└──▷ TRY IT
Restrict which MCP servers are activated at startup — useful when your config lists many servers but you only want a specific one active for a session.
copy
$ gemini --allowed-mcp-server-names my-server,another-server
Limit which tools a specific MCP server exposes, reducing attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. and noise from unused capabilities.
json
copy
# in settings.json
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["delete_file"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are loaded at startup. Not checked yet Adds excludeTools and includeTools fields in mcpServers config to control which tools are exposed per MCP server. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Supports .svg files as input via the @file syntax. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+10 more
show less
Improves 429/quota error handling with tier-aware messaging and removes auto-execution fallback to Flash on quota failover. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Adds user startup warnings and home directory check to catch common misconfiguration early. Not checked yet Improves error messages in isCommandAllowed for shell tool permission denials. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Updates minimum Node.js requirement to version 20. Not checked yet Displays --help output using full terminal width. Not checked yet Adds general usage message to --help output. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet All CLI flags consolidated to use hyphens; underscore variants are deprecated. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; installations running Node.js < 20 will no longer work.! All underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated in favor of hyphen-style equivalents (e.g. --allowed-mcp-server-names); underscore flags may stop working in a future release.! /chat now requires a tag argument; invoking /chat without a tag will fail.
v0.1.17-nightly.250809.f35921a7
Prerelease
Aug 9, 2025
· release notes
gemini-cli v0.1.17-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool inclusion/exclusion.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.17-nightly.250809.f35921a7 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.17-nightly.250809.f35921a7
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when your config defines many servers but you only want one active for a given task.
copy
$ gemini --allowed-mcp-server-names my-security-server
Limit which tools a specific MCP server exposes — add includeTools or excludeTools under the server entry in settings.json.
json
copy
{
"mcpServers": {
"my-security-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["run_scan", "get_findings"],
"excludeTools": ["delete_policy"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at startup. Not checked yet Adds excludeTools and includeTools options in mcpServers config to control which tools each MCP server exposes. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+9 more
show less
Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Adds user startup warnings including a home directory check. Not checked yet Improves 429/quota error handling with awareness of Code Assist customer tiers. Not checked yet Updates minimum Node.js version requirement to 20. Not checked yet Displays YOLO mode shortcut inside /help. Not checked yet Improves error messages in isCommandAllowed for shell command policy violations. Not checked yet Improves auth environment variable validation and messaging to detect GenAI SDK misconfigurations. Not checked yet Formats tool execution time display as minutes and seconds. Not checked yet Adds general usage message to --help output using full terminal width. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! Underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated in favor of hyphen-style flags (e.g. --allowed-mcp-server-names); underscore variants may stop working in a future release.! Minimum Node.js version is now 20; setups running Node.js below 20 will break on upgrade.
v0.1.17-nightly.250808.60362e03
Prerelease
Aug 8, 2025
· release notes
gemini-cli v0.1.17-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, SVG support, Cloud Shell auth reuse, extension listing, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.17-nightly.250808.60362e03 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.17-nightly.250808.60362e03
└──▷ TRY IT
Restrict the CLI to only load specific MCP servers at startup, reducing attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. in automated pipelines.
copy
$ gemini --allowed-mcp-server-names=my-server,another-server
Allowlist or blocklist individual tools within a specific MCP server to limit what the model can invoke.
json
copy
# In settings.json or .gemini/settings.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["delete_file"]
}
}
}
List all available extensions to discover what's installed before enabling one for a session.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at startup. Not checked yet Adds excludeTools and includeTools options in mcpServers config to filter tools per MCP server. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Supports .svg files as input (via @file or context). Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+10 more
show less
Initializes MCP tools once at startup instead of on every auth event, reducing latency. Not checked yet Adds user startup warnings including a home directory check. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Displays YOLO mode shortcut inside /help. Not checked yet Improves error messages in isCommandAllowed for clearer shell tool denials. Not checked yet Formats tool execution time as minutes and seconds. Not checked yet Raises minimum Node.js version requirement to 20. Not checked yet Improves auth environment variable validation and messaging to detect settings that confuse the GenAI SDK. Not checked yet Consolidates all CLI flags to use hyphens (underscore variants are deprecated). Not checked yet Adds general usage message to --help output and uses full terminal width for display. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; setups running Node.js <20 will break on upgrade.! All underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated in favor of hyphen-style flags (e.g. --allowed-mcp-server-names); underscore variants may stop working in a future release.! The /chat command now requires a tag argument; existing workflows invoking /chat without a tag will break.
gemini-cli v0.1.18 adds VS Code/Zed IDE integration, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, proxy support, and custom themes.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.18 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.18
└──▷ USE IT
Suppress the ASCII startup banner in automated pipelines or when embedding embedding Lists of numbers a model produces to represent the meaning of text, images or code, so similar items sit close together. They power semantic search and RAG. gemini-cli in scripts.
json
copy
# In your settings.json
{ "hideBanner": true }
Route all gemini-cli traffic through a corporate or intercepting proxy for inspection or compliance.
copy
$ gemini --proxy http://proxy.corp.example.com:8080 "Summarize the findings in report.md"
Install and check the status of the IDE companion integration from within gemini-cli.
copy
$ /ide install
/ide status
Introduces a VS Code companion extension enabling IDE integration, with /ide status and /ide install commands to manage it. Not checked yet Adds Zed editor integration alongside VS Code IDE mode. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth infrastructure (Part 1) for authenticating MCP servers via OAuth. Not checked yet Introduces a loop detection service that automatically breaks simple agentic loops, with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop checking as a second layer. Not checked yet Adds support for allowed/excluded MCP server name filtering in settings. Not checked yet
+15 more
show less
Shows blocked MCP servers in the UI display. Not checked yet Shows MCP server stderr output when running in debug mode. Not checked yet Adds hideBanner setting to suppress the startup banner. Not checked yet Adds an explicit --proxy option to route CLI traffic through a proxy. Not checked yet Enables custom theme support with user-defined theme logic. Not checked yet Automatically detects non-interactive environments and falls back to a manual, code-based OAuth flow (e.g., for Docker). Not checked yet Enhances OAuth callback handling for robust Docker support. Not checked yet Displays the code diff of a declined confirmation, so users can review what was rejected. Not checked yet Adds numbered entries to selection lists for faster keyboard navigation. Not checked yet Tool summarization is now only enabled when explicitly set in settings.json. Not checked yet Runs model availability check in the background to speed up CLI startup. Not checked yet Hides the cursor when the terminal is unfocused. Not checked yet MCP tools now use a simplified name where possible for cleaner output. Not checked yet Slash command auto-completion now executes on a perfect match. Not checked yet In IDE mode, streams notifications when the active file changes and includes it in model requests. Not checked yet
20 details in Everything
└──▷ BREAKING ON UPGRADE
! Tool summarization is no longer enabled by default — it must now be explicitly set in settings.json to remain active.
v0.1.17-nightly.250806.805114ae
Prerelease
Aug 6, 2025
· release notes
gemini-cli v0.1.17-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, extension listing, SVG support, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.17-nightly.250806.805114ae https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.17-nightly.250806.805114ae
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when your config defines many servers but you only want to expose specific ones in a given session.
copy
$ gemini --allowed-mcp-server-names my-server,audit-server
Filter which tools a specific MCP server exposes to the model — add to your settings.json to exclude noisy or dangerous tools from being called.
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"excludeTools": ["delete_database", "drop_table"]
}
}
}
List available extensions or enable one from the command line — useful for auditing which extensions are active in a scripted or headless context.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at launch. Not checked yet Adds excludeTools and includeTools fields to mcpServers config for fine-grained MCP tool filtering. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+12 more
show less
Adds user startup warnings and home directory check to surface misconfigurations early. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Initializes MCP tools once at startup instead of on every auth event, improving performance. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Updates minimum required Node.js version to 20. Not checked yet All flags consolidated to use hyphens; underscore-style flags are deprecated. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Improves auth environment variable validation and messaging to detect SDK-confusing settings. Not checked yet Adds improved error messages in isCommandAllowed for blocked shell commands. Not checked yet Backtick usage re-enabled in the shell tool. Not checked yet Respects respectGitIgnore=false config setting when using @file references. Not checked yet Honors DEBUG and CLI_TITLE environment variables. Not checked yet
17 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! Underscore-style flags (e.g., --allowed_mcp_server_names) are deprecated in favor of hyphen-style equivalents (e.g., --allowed-mcp-server-names); underscore variants may stop working in a future release.! The /chat command now requires a tag argument; existing workflows that invoke /chat without a tag will break.
gemini-cli v0.1.17 adds IDE integration, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, proxy support, custom themes, and new /ide commands.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.17 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.17
└──▷ USE IT
Suppress the startup banner in scripts or headless environments where it adds noise.
json
copy
# In ~/.gemini/settings.json
{
"hideBanner": true
}
Route all gemini-cli traffic through a corporate proxy.
copy
$ gemini --proxy http://proxy.corp.example.com:8080
Install the VS Code companion extension and check IDE integration status from the CLI.
copy
$ /ide install
/ide status
Adds hideBanner setting to disable the startup banner. Not checked yet Introduces VSCode companion extension for IDE integration with gemini-cli. Not checked yet Adds /ide status and /ide install commands to manage IDE integration from the CLI. Not checked yet Streams notifications to the CLI when the active file changes in the IDE, and includes the active file in model requests. Not checked yet Introduces Zed editor integration. Not checked yet
+19 more
show less
Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth infrastructure (Part 1) enabling OAuth-based authentication for MCP servers. Not checked yet Adds support for allowed/excluded MCP server name lists in settings. Not checked yet Introduces a loop detection service that automatically breaks simple agent loops, with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop checking. Not checked yet Adds stderr output from MCP servers visible in debug mode. Not checked yet Shows blocked MCP servers in the MCP display. Not checked yet Adds explicit --proxy option to the CLI. Not checked yet Adds custom theme support. Not checked yet Enhances OAuth callback for robust Docker environment support. Not checked yet Automatically detects non-interactive environments and falls back to a manual code-based authentication flow. Not checked yet Runs model availability check in the background to speed up startup. Not checked yet Displays declined confirmation code diffs so users can review what was rejected. Not checked yet Adds numbers to selection lists for faster keyboard-driven selection. Not checked yet Sends API key in headers instead of the URL. Not checked yet Sorts tool list alphabetically for deterministic output. Not checked yet Enables tool summarization only when explicitly set in settings.json. Not checked yet Clears the input buffer on CTRL+C when no command is executing. Not checked yet Hides the cursor when the terminal is unfocused. Not checked yet Uses simple names for MCP tools where possible to reduce verbosity. Not checked yet Improves command completion trigger logic based on cursor position. Not checked yet
24 details in Everything
v0.1.16-nightly.250805.99ba2f64
Prerelease
Aug 5, 2025
· release notes
gemini-cli v0.1.16-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, SVG support, Cloud Shell auth reuse, and a new extensions CLI flag.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.16-nightly.250805.99ba2f64 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.16-nightly.250805.99ba2f64
└──▷ TRY IT
Restrict which MCP servers are loaded at startup to reduce attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. in automated pipelines.
copy
$ gemini --allowed-mcp-server-names my-server,audit-server
Allowlist or blocklist specific tools from an MCP server in settings.json to limit what the model can invoke.
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["exec_shell"]
}
}
}
List available extensions to discover what's enabled in the current environment.
copy
$ gemini --extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at runtime. Not checked yet Adds excludeTools and includeTools fields to mcpServers config for per-server tool filtering. Not checked yet Adds a command-line option (--extensions) to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables Gemini CLI to reuse the user's existing auth when running inside Google Cloud Shell. Not checked yet
+9 more
show less
Initializes MCP tools once at startup instead of on every auth event, reducing latency. Not checked yet Adds user startup warnings and a home directory check to surface misconfigurations early. Not checked yet Improves 429/quota error handling with tier-aware messaging for Code Assist customers. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Updates minimum required Node.js version to 20. Not checked yet Improves auth environment variable validation to detect settings that confuse the GenAI SDK. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Displays --help output using the full terminal width. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum supported Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! All CLI flags are consolidated to use hyphens; underscore variants (e.g. --allowed_mcp_server_names) are deprecated and may stop working in a future release.! The /chat command now requires a tag argument; invocations without a tag will fail.
v0.1.16-nightly.250804.a8984a9b
Prerelease
Aug 4, 2025
· release notes
gemini-cli v0.1.16-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, SVG support, Cloud Shell auth reuse, and a new extensions CLI flag.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.16-nightly.250804.a8984a9b https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.16-nightly.250804.a8984a9b
└──▷ TRY IT
Restrict which MCP servers are active at launch — useful when your config lists many servers but you only want to expose a trusted subset during a security review.
copy
$ gemini --allowed-mcp-server-names shodan,burp
Whitelist only specific tools from an MCP server so the AI cannot invoke noisy or destructive tools in that server.
json
copy
# in settings.json
{
"mcpServers": {
"my-server": {
"command": "my-mcp-server",
"includeTools": ["read_file", "list_dir"]
}
}
}
List and enable extensions from the command line without entering the interactive UI.
copy
$ gemini --extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at launch. Not checked yet Adds excludeTools and includeTools per-server config options in mcpServers to whitelist or blacklist individual MCP tools. Not checked yet Adds a command-line option (--extensions) to enable and list extensions. Not checked yet Adds .svg file support for inline content input. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+11 more
show less
Improves 429/quota error handling with awareness of Code Assist customer tiers. Not checked yet Initializes MCP tools once at startup instead of re-initializing on every auth cycle, reducing latency. Not checked yet Adds startup warnings and home directory check to surface common misconfigurations early. Not checked yet Displays the YOLO mode shortcut inside /help for discoverability. Not checked yet Improves error messages in isCommandAllowed for clearer shell tool permission feedback. Not checked yet Formats tool execution time as minutes and seconds. Not checked yet Updates minimum Node.js requirement to version 20. Not checked yet Respects respectGitIgnore=false config setting when using @file references. Not checked yet Allows settings.json variable substitution to honor env variables defined in .env. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet Adds general usage message to --help output and renders it at full terminal width. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! The --allowed_mcp_server_names flag is renamed to --allowed-mcp-server-names; underscore-style flags are deprecated across the board (all flags now use hyphens).! Minimum Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! The /chat command now requires a tag argument; invocations without a tag will fail.
v0.1.15-nightly.250803.820169ba
Prerelease
Aug 3, 2025
· release notes
gemini-cli v0.1.15-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool inclusion/exclusion.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.15-nightly.250803.820169ba https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.15-nightly.250803.820169ba
└──▷ TRY IT
Restrict the CLI to only connect to a specific subset of configured MCP servers, useful when you want to audit or limit tool surface in a security-sensitive session.
copy
$ gemini --allowed-mcp-server-names my-server,audit-server
Exclude noisy or risky MCP tools from a specific server while keeping the rest available, without touching other server configs.
json
copy
# In settings.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"excludeTools": ["dangerous_tool", "write_file"]
}
}
}
List all available extensions to discover what's installed before enabling one for a session.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers the CLI connects to at startup. Not checked yet Adds excludeTools and includeTools config options per mcpServers entry to fine-tune which MCP tools are exposed. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables reuse of the user's existing auth in Google Cloud Shell, avoiding re-authentication. Not checked yet
+10 more
show less
Adds user startup warnings and a home directory check to catch common misconfiguration early. Not checked yet Improves 429/quota error handling with tier-aware messaging for Code Assist customers. Not checked yet MCP tools now initialize once at startup instead of on every auth cycle, reducing latency. Not checked yet Displays YOLO mode shortcut inside /help for discoverability. Not checked yet Improves error messages in isCommandAllowed to surface more actionable detail. Not checked yet Updates minimum Node.js requirement to v20. Not checked yet All CLI flags consolidated to use hyphens; underscore variants deprecated. Not checked yet Execution time now formatted as minutes and seconds in the UI. Not checked yet ASCII art adapts to smaller terminal screen widths. Not checked yet --help output now uses the full terminal width. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! Minimum required Node.js version raised to 20; installations running Node.js <20 will no longer work.! All underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated in favour of hyphen-style equivalents (e.g. --allowed-mcp-server-names); scripts using underscore flags will need updating.! /chat now requires a tag argument; invocations without a tag will fail.
gemini-cli v0.1.16 adds IDE integration with VS Code & Zed, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, custom themes, and proxy support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.16 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.16
└──▷ USE IT
Suppress the startup banner in scripts or automated pipelines where it clutters output.
json
copy
# In your settings.json:
{ "hideBanner": true }
Route all gemini-cli traffic through a corporate or debugging proxy.
copy
$ gemini --proxy http://proxy.corp.example.com:8080
Check IDE integration status and install the VS Code companion extension from within gemini-cli.
copy
$ /ide status
/ide install
Adds hideBanner setting to disable the startup banner in settings.json. Not checked yet Introduces VS Code companion extension for IDE integration with gemini-cli. Not checked yet Adds Zed editor integration. Not checked yet Adds /ide status and /ide install commands to manage IDE integration from the CLI. Not checked yet Shows the active file open in the IDE in the context section above the input box during IDE sessions. Not checked yet
+19 more
show less
Streams notifications to gemini-cli when the active file changes in the IDE. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth infrastructure (Part 1) enabling OAuth-based authentication for MCP servers. Not checked yet Adds support for allowed/excluded MCP server name filtering in settings.json. Not checked yet Shows stderr output from MCP servers in debug mode. Not checked yet Shows blocked MCP servers in the MCP display. Not checked yet Introduces a loop detection service that automatically breaks simple agent loops, with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop checking. Not checked yet Adds explicit --proxy option to the CLI. Not checked yet Adds custom theme support. Not checked yet Displays the code diff when a confirmation is declined. Not checked yet Enables tool summarization only when explicitly set in settings.json. Not checked yet Runs model availability check in the background to speed up startup. Not checked yet Adds numbers to selection lists for faster picking. Not checked yet Automatically detects non-interactive environments and falls back to a manual, code-based OAuth flow. Not checked yet Clears input buffer on Ctrl+C when no command is executing. Not checked yet Hides the cursor when the terminal is unfocused. Not checked yet Enhances OAuth callback for robust Docker support. Not checked yet Sorts the tool list alphabetically for deterministic output. Not checked yet Uses simple names for MCP tools where possible. Not checked yet Moves API key to request header instead of URL. Not checked yet
24 details in Everything
v0.1.15-nightly.250802.15a1f1af
Prerelease
Aug 2, 2025
· release notes
gemini-cli v0.1.15-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.15-nightly.250802.15a1f1af https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.15-nightly.250802.15a1f1af
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when a config file defines many servers but you only want one active in a given session.
copy
$ gemini --allowed-mcp-server-names my-server,audit-server
Exclude a noisy or dangerous tool exposed by an MCP server without removing the server from your config.
json
copy
# In settings.json or .gemini/settings.json
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"excludeTools": ["run_shell", "delete_file"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at launch. Not checked yet Adds excludeTools and includeTools per-server options in mcpServers config to filter individual MCP tools. Not checked yet Adds .svg file support for inline content input. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Enables Gemini CLI to reuse the user's existing auth when running inside Google Cloud Shell. Not checked yet
+9 more
show less
Initializes MCP tools once at startup instead of on every auth event, reducing latency. Not checked yet Adds user startup warnings and a home directory check to surface misconfigurations early. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet Displays YOLO mode shortcut inside /help. Not checked yet Improves error messages in isCommandAllowed for clearer shell policy feedback. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Requires Node.js version 20 or higher (minimum version raised from previous requirement). Not checked yet Consolidates all CLI flags to use hyphens; underscore-style flags are deprecated. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! Node.js version 20 is now the minimum required version; setups running on older Node.js versions will break.! /chat now requires a tag argument; bare /chat invocations without a tag will fail.
v0.1.15-nightly.250801.6f7beb41
Prerelease
Aug 1, 2025
· release notes
gemini-cli v0.1.15-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool include/exclude controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.15-nightly.250801.6f7beb41 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.15-nightly.250801.6f7beb41
└──▷ TRY IT
Restrict which MCP servers are activated at startup — useful when your config lists many servers but you only trust a subset for a given session.
copy
$ gemini --allowed-mcp-server-names my-safe-server,audit-server
Limit an MCP server to only a specific subset of its tools, reducing the attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. exposed to the model.
json
copy
# In settings.json or .gemini/config.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"includeTools": ["read_file", "list_dir"]
}
}
}
List all available extensions to verify which are enabled before starting an investigation workflow.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are loaded at startup. Not checked yet Adds excludeTools and includeTools per-server config keys in mcpServers to control which tools each MCP server exposes. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+9 more
show less
Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, improving load performance. Not checked yet Adds user startup warnings and home directory checks to surface misconfigurations early. Not checked yet Updates minimum Node.js requirement to version 20. Not checked yet Displays YOLO mode shortcut inside /help. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet Formats tool execution time as minutes and seconds. Not checked yet Improves isCommandAllowed error messages for clearer shell restriction feedback. Not checked yet Respects .env file environment variables in settings.json variable substitution. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! The --allowed_mcp_server_names flag is renamed to --allowed-mcp-server-names; underscore-style flags are deprecated across the board in favor of hyphen-style flags.! The minimum supported Node.js version is now 20; setups running Node.js 18 or earlier will break on upgrade.
v0.1.15-nightly.250731.0c6f7884
Prerelease
Jul 31, 2025
· release notes
gemini-cli v0.1.15-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, extension listing, SVG support, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.15-nightly.250731.0c6f7884 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.15-nightly.250731.0c6f7884
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when you want to run only a trusted subset of configured servers.
copy
$ gemini --allowed-mcp-server-names my-server,another-server
Filter the tools exposed by a specific MCP server in settings.json to limit the attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. of an untrusted server.
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["shell_exec"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at runtime. Not checked yet Adds excludeTools and includeTools fields to mcpServers config for per-server tool filtering. Not checked yet Adds a command-line option to enable and list extensions (--extensions). Not checked yet Supports .svg files as input via the @file reference syntax. Not checked yet Enables auth reuse from Google Cloud Shell so users don't re-authenticate inside Cloud Shell sessions. Not checked yet
+11 more
show less
Adds user startup warnings and a home directory check to surface misconfigurations at launch. Not checked yet Improves error messages in isCommandAllowed for clearer shell-tool permission feedback. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Raises minimum required Node.js version to 20. Not checked yet Improves 429/quota error handling with Code Assist customer-tier awareness. Not checked yet Formats tool execution time display as minutes and seconds. Not checked yet Consolidates all CLI flags to hyphen-style; underscore variants are deprecated. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet Handles inline content modification in the tool scheduler. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Shows Ctrl+S shortcut to expand the debug console in the UI. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! All underscore-style flags are deprecated in favor of hyphen-style equivalents (e.g., --allowed_mcp_server_names → --allowed-mcp-server-names); underscore variants may stop working in a future release.! The minimum required Node.js version is now 20; setups running Node.js <20 will no longer work.! /chat now requires a tag argument; invoking /chat without a tag will fail.
gemini-cli v0.1.15 adds IDE integration, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, proxy support, custom themes, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.15 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.15
└──▷ USE IT
Suppress the startup banner in headless or scripted environments by setting hideBanner in your config.
yaml
copy
hideBanner: true
Install the VS Code companion extension and check IDE integration status from within the CLI.
copy
$ /ide install
/ide status
Adds hideBanner setting to disable the startup banner. Not checked yet Introduces a VSCode companion extension for IDE integration, with /ide status and /ide install commands to manage it. Not checked yet Adds Zed editor integration. Not checked yet Introduces a loop detection service that identifies and breaks simple agentic loops, including an LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop check. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth infrastructure (Part 1) to support authenticated MCP servers. Not checked yet
+15 more
show less
Adds support for allowed/excluded MCP server name lists in settings to control which MCP servers are active. Not checked yet Adds an explicit --proxy option to route CLI traffic through a proxy. Not checked yet Adds custom theme support for terminal color configuration. Not checked yet Enables automatic detection of non-interactive environments with fallback to a manual code-based OAuth flow (improves Docker/CI support). Not checked yet Shows stderr output from MCP servers when running in debug mode. Not checked yet Shows blocked MCP servers in the /mcp display. Not checked yet Displays the currently open IDE file in the context section above the input box during IDE mode. Not checked yet Adds code diff display when a confirmation prompt is declined. Not checked yet Adds numbers to selection lists for faster keyboard navigation. Not checked yet Clears the input buffer on CTRL+C when no command is executing. Not checked yet Hides the cursor when the terminal is unfocused. Not checked yet Runs model availability check in the background to speed up startup. Not checked yet Enables tool summarization only when explicitly set in settings.json. Not checked yet Sorts tool list alphabetically for deterministic output. Not checked yet Sends API key in the request header instead of the URL. Not checked yet
20 details in Everything
v0.1.13-nightly.250730.091804c7
Prerelease
Jul 30, 2025
· release notes
gemini-cli v0.1.13-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool include/exclude controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.13-nightly.250730.091804c7 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.13-nightly.250730.091804c7
└──▷ TRY IT
Restrict which MCP servers are active in a session — useful when you want to limit tool surface to only trusted servers in a security-sensitive workflow.
copy
$ gemini --allowed-mcp-server-names my-safe-server,audit-server
Limit a noisy MCP server to only the specific tools you need, reducing unintended tool exposure.
json
copy
# In settings.json or .gemini/settings.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"includeTools": ["read_file", "list_dir"]
}
}
}
List all available extensions to discover what capabilities are registered before enabling them.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are loaded at startup. Not checked yet Adds excludeTools and includeTools per-server config options in mcpServers to control which MCP tools are exposed. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+10 more
show less
Adds startup warnings and home directory check to surface configuration issues early. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, improving startup performance. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Updates minimum required Node.js version to 20. Not checked yet Shows --help output using the full terminal width. Not checked yet Improves auth environment variable validation and messaging to detect settings that confuse the GenAI SDK. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet Handles inline content modification in the tool scheduler. Not checked yet Improves error messages in isCommandAllowed for shell tool permission denials. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum supported Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! All CLI flags are consolidated to use hyphens; underscore variants (e.g. --allowed_mcp_server_names) are deprecated — scripts using underscore flags should be updated.! /chat now requires a tag argument; invocations of /chat without a tag will no longer work.
v0.1.13-nightly.250729.83c4dddb
Prerelease
Jul 29, 2025
· release notes
gemini-cli v0.1.13-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, extension listing, SVG support, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.13-nightly.250729.83c4dddb https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.13-nightly.250729.83c4dddb
└──▷ TRY IT
Restrict which MCP servers are loaded at startup to reduce attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. in automated pipelines.
copy
$ gemini --allowed-mcp-server-names filesystem,github
Filter which tools are exposed from a specific MCP server in settings.json, reducing the tool surface Gemini can invoke.
json
copy
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"],
"includeTools": ["read_file", "list_directory"]
}
}
}
List available extensions from the command line to audit what is enabled in the current environment.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at startup. Not checked yet Adds excludeTools and includeTools options in mcpServers config to filter individual MCP tools per server. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds SVG file support for @file content inclusion. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+13 more
show less
Adds user startup warnings, including a home directory check, to surface misconfigurations early. Not checked yet Improves 429/quota error handling with awareness of Code Assist customer tiers. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Updates minimum required Node.js version to 20. Not checked yet Adds improved error messages in isCommandAllowed for clearer shell permission feedback. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Consolidates all CLI flags to use hyphens; underscore-style flags are deprecated. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Improves auth environment variable validation and messaging to detect settings that confuse the GenAI SDK. Not checked yet Re-enables backtick usage in shell tool commands. Not checked yet Handles inline content modification in the tool scheduler. Not checked yet Respects respectGitIgnore=false config when using @file references. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet
18 details in Everything
└──▷ BREAKING ON UPGRADE
! The --allowed_mcp_server_names flag is renamed to --allowed-mcp-server-names; the underscore form is deprecated.! All underscore-style CLI flags are deprecated in favor of hyphen-style equivalents.! Minimum Node.js version is now 20; earlier versions are no longer supported.! /chat now requires a tag argument; invoking /chat without a tag will no longer work.
v0.1.13-nightly.250728.9ed35126
Prerelease
Jul 28, 2025
· release notes
gemini-cli v0.1.13-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering, SVG support, Cloud Shell auth reuse, extension listing, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.13-nightly.250728.9ed35126 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.13-nightly.250728.9ed35126
└──▷ TRY IT
Limit the CLI to only connect to specific MCP servers, preventing untrusted servers from loading tools.
copy
$ gemini --allowed-mcp-server-names my-server,audit-server
Allowlist or blocklist specific tools from an MCP server in settings to reduce the tool surface exposed to the model.
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_directory"],
"excludeTools": ["delete_file"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers the CLI connects to at startup. Not checked yet Adds excludeTools and includeTools options in mcpServers config to filter which tools a given MCP server exposes. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Supports .svg files as input content. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+8 more
show less
Adds user startup warnings, including a home directory check, to surface misconfigurations early. Not checked yet Improves 429/quota error handling with tier-aware messaging and removes auto-execution fallback to Flash on quota failover. Not checked yet Initializes MCP tools once at startup instead of on every auth event, reducing latency. Not checked yet Raises the minimum required Node.js version to 20. Not checked yet Adds improved error messages in isCommandAllowed for clearer shell tool permission feedback. Not checked yet Displays the YOLO mode shortcut inside /help. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet All CLI flags consolidated to use hyphens; underscore variants are deprecated. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! /chat now requires a tag argument; invoking /chat without a tag will no longer work.
v0.1.13-nightly.250727.3e81359c
Prerelease
Jul 27, 2025
· release notes
gemini-cli v0.1.13-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, SVG support, extension listing, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.13-nightly.250727.3e81359c https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.13-nightly.250727.3e81359c
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when you have many servers configured but only want a trusted subset active in a given session.
copy
$ gemini --allowed-mcp-server-names=my-server,other-server
Limit which tools a specific MCP server exposes, reducing attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. when you only need a subset of its capabilities.
json
copy
# In settings.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["exec_shell"]
}
}
}
List available extensions to discover what's installed and verify extension loading before a session.
copy
$ gemini --list-extensions
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at startup. Not checked yet Adds excludeTools and includeTools config keys inside mcpServers config to filter MCP tools per server. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Adds .svg file support for inline content handling. Not checked yet Enables reuse of the user's existing auth in Google Cloud Shell. Not checked yet
+11 more
show less
Adds user startup warnings and home directory check to surface configuration issues early. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Updates ASCII art to adapt for smaller terminal screens. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Formats tool execution time as minutes and seconds for readability. Not checked yet Improves auth environment variable validation and messaging to detect settings that confuse the GenAI SDK. Not checked yet Improves error messages in isCommandAllowed for clearer shell permission feedback. Not checked yet Adds general usage message to --help output. Not checked yet Uses full terminal width for --help rendering. Not checked yet Bumps minimum required Node.js version to 20. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! All CLI flags are consolidated to use hyphens; underscore variants (e.g. --allowed_mcp_server_names) are deprecated and may break scripts relying on the underscore form.! Node.js versions below 20 are no longer supported; setups running Node.js 18 or earlier will fail.
v0.1.13-nightly.250726.fb751c54
Prerelease
Jul 26, 2025
· release notes
gemini-cli v0.1.13-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, SVG support, extension listing, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.13-nightly.250726.fb751c54 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.13-nightly.250726.fb751c54
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful when a project config lists servers you don't want active in a particular session.
copy
$ gemini --allowed-mcp-server-names my-server,another-server
Filter individual tools within an MCP server so the model only sees the subset relevant to your workflow.
json
copy
# In settings.json / .gemini/settings.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"includeTools": ["search", "fetch"],
"excludeTools": ["delete"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at startup. Not checked yet Adds excludeTools and includeTools fields in mcpServers config to filter individual tools per MCP server. Not checked yet Adds .svg file support for inline content in prompts. Not checked yet Adds a command-line option to enable and list extensions (--extensions). Not checked yet Enables Gemini CLI to reuse the user's existing auth credentials when running inside Google Cloud Shell. Not checked yet
+13 more
show less
Adds user startup warnings and a home directory check to surface misconfigurations early. Not checked yet Displays the YOLO mode shortcut inside /help output. Not checked yet Improves error messages in isCommandAllowed to surface clearer shell-permission denials. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Improves 429/quota error handling with Code Assist customer-tier awareness; removes auto-execution Flash fallback on quota failures. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Updates minimum required Node.js version to 20. Not checked yet Consolidates all CLI flags to use hyphens; underscore-style flags are deprecated. Not checked yet Improves auth environment-variable validation and messaging to detect settings that confuse the GenAI SDK. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet Handles inline content modification in the tool scheduler. Not checked yet Adds general usage message to --help output and uses full terminal width for help display. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet
18 details in Everything
└──▷ BREAKING ON UPGRADE
! All underscore-style CLI flags are deprecated in favour of hyphen-style equivalents (e.g. --allowed_mcp_server_names → --allowed-mcp-server-names).! The minimum required Node.js version is raised to 20; setups running Node.js <20 will no longer work.
gemini-cli v0.1.14 adds IDE integration with VS Code & Zed, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, custom themes, and an explicit proxy option.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.14 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.14
└──▷ USE IT
Suppress the startup banner in CI or scripted workflows where the banner adds noise.
json
copy
# In ~/.gemini/settings.json
{ "hideBanner": true }
Route all gemini-cli traffic through a corporate proxy server.
copy
$ gemini --proxy http://proxy.corp.example.com:8080
Install the VS Code companion extension and verify the IDE integration is active.
copy
$ /ide install
/ide status
Adds hideBanner setting to disable the startup banner via settings.json. Not checked yet Introduces a VS Code companion extension for IDE integration, with /ide status and /ide install commands to manage it. Not checked yet Adds Zed editor integration. Not checked yet Surfaces stderr output from MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers when running in debug mode. Not checked yet Introduces a loop detection service that automatically breaks simple agent loops, with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop checking as an additional layer. Not checked yet
+18 more
show less
Adds support for allowed/excluded MCP server name filters in settings. Not checked yet Adds MCP OAuth infrastructure (Part 1) for authenticating MCP servers. Not checked yet Adds an explicit --proxy option to the CLI for routing traffic through a proxy. Not checked yet Adds numbers to selection lists for faster keyboard-driven picking. Not checked yet Introduces custom theme support. Not checked yet Enhances OAuth callback for robust Docker support. Not checked yet Shows blocked MCP servers in the MCP display. Not checked yet Automatically detects non-interactive environments and falls back to a manual, code-based authentication flow. Not checked yet Displays a code diff when a confirmation prompt is declined. Not checked yet In IDE mode, includes the user's active open file as context in model requests. Not checked yet Hides the terminal cursor when the terminal is unfocused. Not checked yet Tool summarization is now only enabled when explicitly set in settings.json. Not checked yet Runs model availability check in the background to speed up startup. Not checked yet Adds a feature flag for IDE integration mode. Not checked yet Clears the input buffer on CTRL+C when not executing a command. Not checked yet Sorts tool list alphabetically for deterministic output. Not checked yet Moves API key from URL parameter to request header. Not checked yet Improves @ command file sorting to ignore file extensions. Not checked yet
23 details in Everything
└──▷ BREAKING ON UPGRADE
! Tool summarization is no longer on by default — it must now be explicitly enabled in settings.json.
gemini-cli v0.1.13 adds IDE integration with VSCode/Zed, MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. , loop detection, proxy support, and new /ide commands.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.13 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.13
└──▷ USE IT
Suppress the startup banner in automated or scripted workflows where the banner clutters output.
json
copy
# In your settings.json
{ "hideBanner": true }
Route all gemini-cli traffic through a corporate or intercepting proxy for inspection or policy enforcement.
copy
$ gemini --proxy http://proxy.corp.example.com:8080
Introduces VSCode companion extension for IDE integration, streaming active-file context into the CLI. Not checked yet Adds Zed editor integration. Not checked yet New /ide status and /ide install commands to manage IDE integration from the CLI. Not checked yet Adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. OAuth infrastructure (Part 1) enabling OAuth-authenticated MCP servers. Not checked yet Adds support for allowed/excluded MCP server name filtering in settings. Not checked yet
+16 more
show less
Shows blocked MCP servers in the MCP display. Not checked yet Shows stderr output from MCP servers in debug mode. Not checked yet Introduces a loop detection service that automatically breaks simple agentic loops, with LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. -based loop detection also added. Not checked yet Adds hideBanner setting to disable the startup banner. Not checked yet Adds explicit --proxy option to the CLI for routing traffic through a proxy. Not checked yet Enhances OAuth callback for robust Docker support in non-interactive environments, automatically falling back to manual code-based auth. Not checked yet Displays declined confirmation code diffs so users can review what was rejected. Not checked yet Tool list is now sorted alphabetically for deterministic output. Not checked yet Runs model availability check in the background to speed up startup. Not checked yet Adds numbers to selection lists for faster item picking. Not checked yet Hides cursor when the terminal is unfocused. Not checked yet Clears input buffer on Ctrl+C when not executing commands. Not checked yet Enables toolSummarization only when explicitly set in settings.json (opt-in). Not checked yet Uses simple (short) names for MCP tools where possible, reducing noise. Not checked yet API key is now sent in the request header instead of the URL. Not checked yet Light theme color improvements. Not checked yet
21 details in Everything
└──▷ BREAKING ON UPGRADE
! Tool summarization (toolSummarization) is now disabled unless explicitly set in settings.json; previously-enabled behavior will stop working on upgrade.
v0.1.11-nightly.250713.4442e893
Prerelease
Jul 13, 2025
· release notes
gemini-cli v0.1.11-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering, SVG support, Cloud Shell auth reuse, extension CLI management, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.11-nightly.250713.4442e893 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.11-nightly.250713.4442e893
└──▷ TRY IT
Restrict which MCP servers are active in a session — useful when you want only a trusted subset of configured servers loaded.
copy
$ gemini --allowed-mcp-server-names server1,server2
Whitelist only specific tools from an MCP server in settings.json to reduce attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. .
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_directory"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are loaded at startup. Not checked yet Adds excludeTools and includeTools fields in mcpServers config to whitelist or blacklist individual MCP tools per server. Not checked yet Adds a command-line option to enable and list extensions (--extensions). Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet Adds startup warnings for users, including a home directory check. Not checked yet
+12 more
show less
Adds .svg file support for inline content handling. Not checked yet Displays YOLO mode shortcut inside /help. Not checked yet Initializes MCP tools once at startup instead of on every auth event, improving startup performance. Not checked yet Improves 429/quota error handling with tier-aware messaging and removes auto-execution on Flash during quota failover. Not checked yet Improves auth environment variable validation logic and messaging to detect conflicting GenAI SDK settings. Not checked yet Improves error messages in isCommandAllowed for clearer shell tool permission feedback. Not checked yet Updates ASCII art to adapt for smaller terminal screens. Not checked yet Formats tool execution time as minutes and seconds. Not checked yet Adds general usage message to --help output. Not checked yet Respects respectGitIgnore=false config when using @file references. Not checked yet Requires minimum Node.js version 20. Not checked yet Consolidates all CLI flags to use hyphens; underscore variants are deprecated. Not checked yet
17 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; setups running Node.js <20 will no longer work.! All underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated in favor of hyphen-style equivalents (e.g. --allowed-mcp-server-names); underscore variants may stop working in a future release.! The /chat command now requires a tag argument; existing usage of /chat without a tag will fail.
gemini-cli v0.1.10 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and per-server tool inclusion controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.10 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.10
└──▷ TRY IT
Restrict the CLI to only connect to specific MCP servers, reducing attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. in automated pipelines.
copy
$ gemini --allowed-mcp-server-names my-server,trusted-server
Limit which tools a specific MCP server can expose, scoping permissions per server in settings.json.
json
copy
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_directory"],
"excludeTools": ["exec_shell"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers the CLI connects to at startup. Not checked yet Adds excludeTools and includeTools options to mcpServers config for fine-grained per-server tool filtering. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Enables reuse of the user's existing auth in Google Cloud Shell, avoiding re-authentication. Not checked yet Adds .svg file support for inline content handling. Not checked yet
+10 more
show less
Adds user startup warnings and a home directory check to surface misconfigurations early. Not checked yet Adds improved error messages in isCommandAllowed for clearer shell command policy feedback. Not checked yet Displays the YOLO mode shortcut inside /help for discoverability. Not checked yet Initializes MCP tools once at startup instead of on every auth event, improving startup performance. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Improves 429/quota error handling with tier-aware messaging and removes auto-execution Flash fallback on quota failure. Not checked yet Improves auth environment variable validation to detect settings that confuse the GenAI SDK. Not checked yet Updates ASCII art to scale for smaller terminal screens. Not checked yet Respects DEBUG and CLI_TITLE environment variables. Not checked yet Enables backtick usage in shell tool invocations. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! All CLI flags are consolidated to use hyphens; underscore-style flags (e.g. --allowed_mcp_server_names) are deprecated — existing scripts using underscore flags will need to be updated.! Minimum required Node.js version is raised to 20; setups running Node.js < 20 will no longer work.! The /chat command now requires a tag argument; bare /chat invocations without a tag will fail.
gemini-cli v0.1.11 adds NO_BROWSER env var for headless/offline OAuth flows.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.11 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.11
└──▷ TRY IT
Authenticate in a headless SSH session or CI environment where no browser is available.
copy
$ NO_BROWSER=1 gemini
Adds NO_BROWSER environment variable to trigger an offline OAuth flow without opening a browser — useful in headless or remote environments. Not checked yet Indents subcommands in help output for improved readability. Not checked yet
2 details in Everything
v0.1.9-nightly.250710.da50a1ee
Prerelease
Jul 10, 2025
· release notes
gemini-cli v0.1.9-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool filtering, SVG support, extension listing, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9-nightly.250710.da50a1ee https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9-nightly.250710.da50a1ee
└──▷ TRY IT
Limit which MCP servers are loaded at startup — useful in CI or locked-down environments where only approved servers should be active.
copy
$ gemini --allowed-mcp-server-names server1,server2
Filter which tools are exposed from a specific MCP server to reduce the model's tool surface.
json
copy
# in settings.json
{
"mcpServers": {
"my-server": {
"command": "npx my-mcp-server",
"includeTools": ["run_query", "list_tables"],
"excludeTools": ["drop_table"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at launch. Not checked yet Adds excludeTools and includeTools fields to mcpServers config for per-server tool filtering. Not checked yet Adds .svg file support for inline content. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Enables Gemini CLI to reuse the user's existing auth in Google Cloud Shell. Not checked yet
+11 more
show less
Adds startup warnings and home directory check to surface configuration issues early. Not checked yet Displays the YOLO mode shortcut inside /help output. Not checked yet Improves error messages in isCommandAllowed for blocked shell commands. Not checked yet Initializes MCP tools once at startup instead of on every auth cycle, reducing latency. Not checked yet Updates minimum Node.js requirement to v20. Not checked yet Formats tool execution time as minutes and seconds in the UI. Not checked yet Updates ASCII art to adapt to smaller terminal screens. Not checked yet Improves 429/quota error handling with Code Assist customer tier awareness and removes auto-execution on Flash failover. Not checked yet Improves auth environment variable validation and messaging to detect GenAI SDK configuration conflicts. Not checked yet Re-enables backtick usage in shell tool invocations. Not checked yet Adds general usage message to --help output and uses full terminal width for its display. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! All CLI flags previously using underscores are consolidated to use hyphens (e.g., --allowed_mcp_server_names is deprecated in favor of --allowed-mcp-server-names); underscore variants are deprecated and may stop working in a future release.! Node.js v20 is now the minimum required version; setups running on older Node.js versions will break.! The /chat command now requires a tag argument; invocations without a tag will fail.
v0.1.9-nightly.250709.c8cf954e
Prerelease
Jul 9, 2025
· release notes
gemini-cli v0.1.9-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, extension listing, Cloud Shell auth reuse, and startup warnings.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9-nightly.250709.c8cf954e https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9-nightly.250709.c8cf954e
└──▷ TRY IT
Restrict which MCP servers are loaded at startup — useful in hardened environments where only approved servers should be reachable.
copy
$ gemini --allowed-mcp-server-names my-approved-server,another-server
Allowlist only specific tools from an MCP server to reduce the attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. exposed to the model.
json
copy
# In settings.json or gemini config
{
"mcpServers": {
"my-server": {
"command": "npx",
"args": ["my-mcp-server"],
"includeTools": ["read_file", "list_dir"]
}
}
}
New --allowed-mcp-server-names flag restricts which MCP servers the CLI connects to at runtime. Not checked yet New excludeTools and includeTools fields in mcpServers config allow per-server tool allowlisting and blocklisting. Not checked yet Adds a command-line option to enable and list extensions. Not checked yet Supports .svg files as inline content input. Not checked yet Reuses existing user auth automatically when running inside Google Cloud Shell. Not checked yet
+7 more
show less
Adds user startup warnings including a home directory check to catch common misconfiguration. Not checked yet Improves auth environment variable validation with clearer error messaging when settings confuse the GenAI SDK. Not checked yet MCP tools now initialize once at startup instead of on every auth event, reducing latency. Not checked yet Execution time is now formatted as minutes and seconds in the UI. Not checked yet YOLO mode shortcut is now displayed inside /help. Not checked yet Improves error messages in isCommandAllowed for shell tool permission denials. Not checked yet Updates minimum Node.js requirement to v20. Not checked yet
12 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum supported Node.js version is now 20; setups running Node.js < 20 will break on upgrade.! /chat now requires a tag argument; existing workflows that invoke /chat without a tag will fail.
v0.1.9-nightly.250708.137ffec3
Prerelease
Jul 8, 2025
· release notes
gemini-cli v0.1.9-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, Cloud Shell auth reuse, and per-server tool inclusion/exclusion controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9-nightly.250708.137ffec3 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9-nightly.250708.137ffec3
└──▷ TRY IT
Limit which MCP servers are loaded at startup — useful in hardened environments where only approved servers should be active.
copy
$ gemini --allowed-mcp-server-names my-approved-server,another-server
Restrict or allowlist specific tools exposed by an MCP server to reduce the attack surface attack surface The exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. in automated pipelines.
json
copy
# In settings.json or .gemini/settings.json
{
"mcpServers": {
"my-server": {
"command": "my-mcp-server",
"includeTools": ["read_file", "list_dir"],
"excludeTools": ["exec_shell"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are activated at startup. Not checked yet Adds excludeTools and includeTools fields to mcpServers config to control which tools are exposed per MCP server. Not checked yet Enables auth reuse from Google Cloud Shell so users don't need to re-authenticate. Not checked yet Adds SVG file support for @file references. Not checked yet Adds user startup warnings and home directory check to surface environment issues early. Not checked yet
+6 more
show less
MCP tools now initialize once at startup instead of on every auth event, reducing latency. Not checked yet Displays YOLO mode shortcut inside /help output. Not checked yet Improves error messages in isCommandAllowed to surface clearer diagnostics when a shell command is blocked. Not checked yet Execution time is now formatted as minutes and seconds for long-running operations. Not checked yet Raises minimum Node.js version requirement to 20. Not checked yet Re-enables backtick usage in the shell tool. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; setups running older Node.js versions will break on upgrade.! The flag --allowed_mcp_server_names was renamed to --allowed-mcp-server-names; scripts using the underscore form will break.
v0.1.9-nightly.250708.a4097ae6
Prerelease
Jul 8, 2025
· release notes
gemini-cli v0.1.9-nightly adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server filtering flags, SVG support, Cloud Shell auth reuse, and per-server tool inclusion/exclusion.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9-nightly.250708.a4097ae6 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9-nightly.250708.a4097ae6
└──▷ TRY IT
Restrict an automated session to only specific MCP servers to limit tool exposure in CI or sandboxed environments.
copy
$ gemini --allowed-mcp-server-names filesystem,github
Allowlist or blocklist specific tools on a per-MCP-server MCP-server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. basis so only vetted tools are available to the model.
json
copy
# in settings.json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/workspace"],
"includeTools": ["read_file", "list_directory"]
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"excludeTools": ["create_issue", "delete_repository"]
}
}
}
Adds --allowed-mcp-server-names flag to restrict which MCP servers are active at launch. Not checked yet Adds excludeTools and includeTools options per MCP server entry in mcpServers config to control which tools each server exposes. Not checked yet Adds .svg file support for @file context inclusion. Not checked yet Enables Gemini CLI to reuse existing user auth when running inside Google Cloud Shell. Not checked yet Adds startup warnings and home directory checks to alert users to potential misconfigurations at launch. Not checked yet
+4 more
show less
Initializes MCP tools once at startup instead of re-initializing on every auth cycle, reducing latency. Not checked yet Displays the YOLO mode shortcut inside /help output. Not checked yet Improves error messages in isCommandAllowed for blocked shell commands. Not checked yet Updates minimum required Node.js version to 20. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! The minimum required Node.js version is now 20; setups running Node.js <20 will break on upgrade.
v0.1.9-nightly.250707.d1c0a211
Prerelease
Jul 7, 2025
· release notes
gemini-cli v0.1.9-nightly raises minimum Node.js to v20 and requires a tag argument for /chat sessions.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9-nightly.250707.d1c0a211 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9-nightly.250707.d1c0a211
Requires Node.js 20+ as the new minimum runtime version. Not checked yet Makes the tag argument required for the /chat command. Not checked yet Updates ASCII art rendering to adapt to smaller terminal screens. Not checked yet Adds inline content modification handling in the tool scheduler. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Node.js versions below 20 are no longer supported; upgrade your runtime before upgrading gemini-cli.! The /chat command now requires a tag argument; invocations without a tag will fail.
v0.1.9-nightly.250704.23eea823
Prerelease
Jul 4, 2025
· release notes
gemini-cli v0.1.9-nightly now requires a tag for /chat and adapts ASCII art for smaller screens.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9-nightly.250704.23eea823 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9-nightly.250704.23eea823
Requires a tag argument for the /chat command, enforcing named chat sessions. Not checked yet Updates ASCII art to scale appropriately for smaller terminal screens. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The /chat command now requires a tag argument; existing workflows that invoke /chat without a tag will break.
gemini-cli v0.1.9 adds infinite loop protection, extension tool exclusions, and session ID support in API calls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.9 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.9
Adds infinite loop protection to the client to prevent runaway agentic cycles. Not checked yet Supports excludedTools in extensions, letting extension authors block specific tools from being used. Not checked yet Supports session_id in API calls for session-scoped request tracking. Not checked yet
3 details in Everything
gemini-cli v0.1.8 adds audio/video file reading, modular GEMINI.md imports, remote MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. custom headers, and per-command shell restrictions.
└──▷ GET THIS VERSION
copy
$ git clone --branch v0.1.8 https://github.com/google-gemini/gemini-cli.git
$ git checkout v0.1.8
└──▷ USE IT
Suppress startup tips when running gemini-cli in non-interactive or scripted pipelines.
json
copy
# In settings.json
{ "hideTips": true }
Adds audio and video support to the read_file tool, enabling multimodal multimodal Able to work with more than one type of input or output, such as text, images and audio. A multimodal model can combine information across those formats. analysis of media files. Not checked yet Supports modular GEMINI.md imports using @file.md syntax, allowing shared instruction fragments across projects. Not checked yet Adds hideTips setting to suppress startup tips in automated or distraction-free workflows. Not checked yet Adds custom HTTP headers support for remote MCP servers, enabling authenticated MCP connections. Not checked yet Enables command-specific restrictions for ShellTool, including prefix matching for flexible command validation. Not checked yet
+6 more
show less
Adds VSCodium editor support for the external editor integration. Not checked yet Adds Neovim editor support for the external editor integration. Not checked yet Adds a new Shades of Purple UI theme. Not checked yet Adds markdown table rendering support in CLI output. Not checked yet Expands /stats command to include more detailed token/usage breakdowns. Not checked yet Highlights previous user input in the terminal UI for improved session readability. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The AuthType value LOGIN_WITH_GOOGLE_PERSONAL is renamed to LOGIN_WITH_GOOGLE; any config or scripts referencing the old value will break.