CrewAI

No entries match these filters. Clear filters

1. 1.15.23 Sep 28, 2026 · release notes

   CrewAI v1.15.23 adds Gemini 3.8 Flash support and eval tracing fixes

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.23 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.23

2. 1.15.22 Sep 16, 2026 · release notes

   CrewAI v1.15.22 adds LLMLLMA 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. overlay routing, OpenRouterOpenRouterA unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code. embeddingsembeddingsLists 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., and platform catalog access.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.22 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.22

   • Adds llm_overlay context variable to route agent roles to specific models
   • Adds OpenRouter as a supported embeddingembeddingLists 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. provider

   2 details in Everything

3. 1.15.21 Sep 9, 2026 · release notes

   CrewAI v1.15.21 adds telemetry for checkpoint runtime and CLI usage tracking.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.21 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.21

   • telemetry captures checkpoint runtime metrics and CLI command usage data.

   1 detail in Everything

4. 1.15.19 Sep 4, 2026 · release notes

   CrewAI 1.15.19 adds Clipper integration, CELCELCommon Expression Language, an open-source expression language maintained by Google, used to embed lightweight, safe policy evaluation logic into tools without running a full scripting engine. now(), injectable platform tool client, and machine size reporting.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.19 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.19

   • Adds Clipper integrations client for connecting to external systems
   • Adds now() function to the CEL expression environment for time-based logic
   • Adds an injectable client for CrewAI platform tools to enable custom service wiring

   3 details in Everything

5. 1.15.18 Aug 27, 2026 · release notes

   CrewAI 1.15.18 stabilizes conversational flows with new deployment recording and declarative state/router capabilities.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.18 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.18

   • crewai deploy records the created deployment by its UUIDUUIDA 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.
   • Declarative chat flows can now declare their own state shape via state_shape
   • Declarative chat flows can name the router's response format via response_format
   • Conversational declarations accept crew-style LLM config in addition to standard formats
   • project_id is always emitted by project creation commands, distinguishing absent from empty

   5 details in Everything

6. 1.15.17 Aug 20, 2026 · release notes

   Declarative conversational flows now drive agent interactions with declarations configuration.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.17 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.17

   • Enable declarations to drive conversational mode in your crew configuration
   • Synthesize built-in conversational methods for declarations via the new config schema

   2 details in Everything

7. 1.15.16 Aug 14, 2026 · issue 045

   CrewAI 1.15.16 adds execution context management with UUIDUUIDA 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. support, flow exception recording, and enhanced AMP deployment telemetry.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.16 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.16

   • Introduces execution context management with UUID support for tracking individual flow and agent executions.
   • Records the type of exception that ended a flow, giving observability pipelines structured failure context.
   • Records when a trace batch is shared with AMP, enabling auditable telemetry handoff visibility.
   • Counts deployments from any origin and records where they started, supporting multi-origin deployment tracking in AMP.

   4 details in Everything

8. 1.15.15 Aug 12, 2026 · issue 043

   CrewAI 1.15.15 adds flow outcome, duration, and human-in-the-loophuman-in-the-loopHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues. signal reporting to flow telemetry.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.15 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.15

9. 1.15.12 Aug 5, 2026 · issue 037

   CrewAI 1.15.12 adds URLReadTool, unified crewai create <resource> scaffolding, and platform action tool metadata.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch 1.15.12 https://github.com/crewAIInc/crewAI.git
   # already have the repo? check out this version:
   $ git checkout 1.15.12

   └──▷ TRY IT
   Scaffold a new CrewAI resource (crew, flow, etc.) using the unified create command.
   copy

   $ crewai create <resource>

   • Unifies project scaffolding under crewai create <resource>, replacing separate scaffold commands.
   • Adds URLReadTool for reading arbitrary URLs inside agent workflows.
   • Adds app metadata to platform action tools.

   3 details in Everything

10. 1.15.11 Aug 5, 2026 · issue 036

    CrewAI 1.15.11 adds an IBM Db2 search tool, enterprise project_id linking, AMP surfacing in AGENTS.md, and coding-agent telemetry detection.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.11 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.11

    • Adds IBM Db2 search tool, enabling agents to query Db2 databases as a built-in tool.
    • Adds project_id support to link open-source CrewAI usage to an enterprise account.
    • Surfaces CrewAI AMP in AGENTS.md and adds detection of coding agents in telemetry.
    • Tracks interception-hook dispatches in telemetry for improved observability of agent execution.

    4 details in Everything

11. 1.15.10 Jul 31, 2026 · release notes

    CrewAI 1.15.10 adds skill usage event collection for agent observability.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.10 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.10

    • Collects skill usage events, enabling observability into which agent skills are invoked during crew runs.

    1 detail in Everything

12. 1.15.9 Jul 30, 2026 · issue 030

    CrewAI 1.15.9 surfaces tool failures explicitly, emits FlowFailedEvent on flow errors, and adds progressive disclosure for skills.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.9 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.9

    • Surfaces tool failures as actual failures instead of silently reporting them as success, enabling agents to react correctly to tool errors.
    • Emits a new FlowFailedEvent when a flow execution fails, allowing event-driven error handling and observability hooks in Flows.
    • Adds progressive disclosure for skills, surfacing contextually relevant skill guidance incrementally rather than all at once.

    3 details in Everything

13. 1.15.8 Jul 28, 2026 · issue 028

    CrewAI 1.15.8 adds WaitTool to let agents pause execution while waiting on long-running async jobs.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.8 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.8

14. 1.15.7 Jul 26, 2026 · issue 027

    CrewAI 1.15.7 adds runtime skill usage event emission for observability.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.7 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.7

    • Emits skill usage events at runtime, enabling observability pipelines to trace which skills agents invoke during execution.

    1 detail in Everything

15. 1.15.7a1 Prerelease Jul 26, 2026 · issue 027

    CrewAI 1.15.7a1 adds runtime skill usage event emission for improved observability.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.7a1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.7a1

    • Emits skill usage events at runtime, enabling observability pipelines to track which skills agents invoke during execution.

    1 detail in Everything

16. 1.15.5 Jul 20, 2026 · issue 021

    CrewAI 1.15.5 adds authentication support for skill registry downloads.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.5 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.5

    • Supports authenticated downloads from the skill registry, enabling access to private or restricted skills.

    1 detail in Everything

17. 1.15.4 Jul 17, 2026 · issue 018

    CrewAI 1.15.4 promotes the Skills Repository to stable, making AI coding-agent guidance an officially supported feature.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.4 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.4

    └──▷ TRY IT
    Install the now-stable CrewAI Skills into Claude Code so it automatically applies CrewAI best practices when you scaffold Flows, configure Crews, or design agents.
    copy

    $ /plugin marketplace add crewAIInc/skills
    /plugin install crewai-skills@crewai-plugins
    /reload-plugins

    Install the stable CrewAI Skills into Cursor, Codex, Windsurf, or any other coding agent via the skills.sh registry.
    copy

    $ npx skills add crewaiinc/skills

18. 1.15.3 Jul 16, 2026 · issue 018

    CrewAI 1.15.3 adds step interception hooks with @on, org ID support in PlusAPI, and declarative Flow execution in the TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency..

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.3 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.3

    └──▷ USE IT
    Intercept execution boundaries in a crew or flow to log, audit, or gate agent activity at specific lifecycle points.
    python copy

    from crewai import on
    
    @on("before_llm_call")
    def audit_llm_input(context):
        print("LLM about to be called with:", context)
    
    @on("after_llm_call")
    def log_llm_output(context):
        print("LLM responded with:", context)

    • Adds step interception points and a generic hook dispatcher, enabling fine-grained execution-boundary callbacks via @on decorators.
    • Adds organization_id parameter to the PlusAPI client for multi-org deployments.
    • Supports running declarative Flows on the TUI with headless terminal fallback.

    3 details in Everything

19. 1.15.3a1 Prerelease Jul 16, 2026 · issue 018

    CrewAI 1.15.3a1 adds step interception hooks via @on, declarative flow support in the TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency., and an organization ID parameter for the PlusAPI client.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.3a1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.3a1

    • Adds step interception points and a generic hook dispatcher, enabling @on-decorated callbacks at execution boundaries for fine-grained observability and control.
    • Supports running declarative flows on the TUI with a headless terminal fallback.
    • Adds an organization ID parameter to the PlusAPI client for multi-org deployments.
    • Improves custom OpenAI URL handling for self-hosted or proxy LLMLLMA 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. endpoints.

    4 details in Everything

20. 1.15.2 Jul 8, 2026 · issue 009

    CrewAI 1.15.2 adds inline skill definitions, templated Flow action inputs, stream frame protocol, and AgentExecutor feedback handling.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.2 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.2

    • Supports inline skill definitions, eliminating the need for separate skill files in crew/flow configurations.
    • Adds templated Flow action inputs, enabling dynamic parameterization of Flow actions at runtime.
    • Defines a stream frame protocol for Flows, enabling structured streaming output from Flow executions.
    • Adds a generated Flow Definition authoring skill to guide AI coding agents when scaffolding Flows.
    • Implements message setup and feedback handling in AgentExecutor for richer agent interaction loops.

    +4 more show less

    • Adds repository agents to Flow definitions, enabling agent-backed steps directly in Flow authoring.
    • Adds text helpers for Flow CELCELCommon Expression Language, an open-source expression language maintained by Google, used to embed lightweight, safe policy evaluation logic into tools without running a full scripting engine. prompts and skill examples, streamlining expression authoring in Flows.
    • Types tool and app fields in CrewDefinition, providing stronger schema validation for crew configs.
    • Pulls latest LLMLLMA 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. models dynamically in the crew wizard, keeping model selection current without manual updates.

    9 details in Everything

21. 1.15.2a1 Prerelease Jun 30, 2026 · issue 002

    CrewAI 1.15.2a1 adds inline skill definitions, a stream frame protocol for Flows, and new tool/app types in CrewDefinition.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.2a1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.2a1

    • Supports inline skill definitions, enabling skills to be declared directly within agent or crew configurations without separate files.
    • Introduces a stream frame protocol for Flows, defining a structured message format for streaming Flow execution events.
    • Adds tool and app type options to CrewDefinition, expanding the kinds of crew artifacts that can be declared.
    • Adds a generated Flow Definition authoring skill for AI coding agents, guiding them when scaffolding or editing Flow definitions.

    4 details in Everything

22. 1.15.1 Jun 27, 2026 · issue 001

    CrewAI 1.15.1 auto-initializes Git repos for new projects, enforces explicit crew definitions, and opens the deployment page post-deploy.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.1

    • Automatically initializes a Git repository when generating a new CrewAI project via the CLI.
    • Requires explicit CrewAI project definitions, enforcing structured crew configuration at project creation.
    • Opens the deployment page automatically in the browser after a successful crewai deploy command.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !Explicit CrewAI project definitions are now required (#6358)
23. 1.15.1a1 Prerelease Jun 26, 2026 · issue 001

    CrewAI 1.15.1a1 adds TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. button telemetry, enforces explicit project definitions, and auto-opens the deployment page after CLI deploy.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.1a1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.1a1

    • Adds telemetry tracking for TUI button interactions, enabling usage analytics on crew terminal UI actions.
    • Requires explicit CrewAI project definitions, enforcing stricter project structure as a breaking change for existing setups.
    • Automatically opens the deployment page in the browser after a successful crewai deploy CLI command.

    3 details in Everything

24. 1.15.0 Jun 25, 2026 · issue 001

    CrewAI 1.15.0 adds declarative Flow definitions with crew/agent actions, each composite steps, conditional expressions, and DMN mode support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.15.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.15.0

    • Adds unified declarative Flow loading, letting flows be defined and loaded from configuration rather than pure Python code.
    • Adds declarative Flow CLI support so flows defined in config files can be kicked off directly from the command line.
    • Adds each composite action to FlowDefinition for iterating over collections within a flow step.
    • Adds optional if expression to each.do steps, enabling conditional execution inside iteration blocks.
    • Adds single-agent action support in Flow definitions, allowing a lone agent call to be wired directly into a flow without a full crew.

    +7 more show less

    • Adds crew actions to FlowDefinition, enabling inline crew execution as a named step in a declarative flow.
    • Adds inline crew definition loading so a crew can be fully specified inside a FlowDefinition without a separate crew config file.
    • Implements DMN (Decision Model and Notation) mode support in crew creation and execution for structured decision logic.
    • Tracks conversational flow turn usage in telemetry for visibility into multi-turn conversation costs.
    • Supports conversational flows in the CLI TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency., surfacing turn-by-turn flow progress in the terminal UI.
    • Consolidates crewai run and crewai flow kickoff into a single command entry point (breaking change for scripts that invoked them separately).
    • Removes StateProxy from flow state access, providing direct state access in flow methods (breaking change).

    12 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The StateProxy has been removed from flow state access
25. 1.14.8a5 Prerelease Jun 25, 2026 · issue 001

    CrewAI 1.14.8a5 enables declarative refs to work seamlessly across both Flows and Crews.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.8a5 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.8a5

    • Enables declarative references to be resolved across Flow and Crew boundaries, allowing shared state and configuration to be referenced from either context.

    1 detail in Everything

26. 1.14.8a4 Prerelease Jun 24, 2026 · issue 001

    CrewAI 1.14.8a4 adds conversational flow support in the CLI TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency..

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.8a4 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.8a4

    • Supports conversational flows in the CLI text-based UI (TUI), enabling interactive multi-turn flow execution from the terminal.

    1 detail in Everything

27. 1.14.8a3 Prerelease Jun 23, 2026 · issue 001

    CrewAI 1.14.8a3 adds declarative Flow loading, unified CLI commands, router-as-start support, and typed tool output schemas.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.8a3 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.8a3

    └──▷ USE IT
    Define a Flow whose entry point is a router for immediate conditional branching at startup.
    python copy

    from crewai.flow.flow import Flow, router, listen, start
    
    class TriageFlow(Flow):
        @router()
        @start()
        def triage(self):
            if self.state.priority == 'high':
                return 'urgent'
            return 'normal'
    
        @listen('urgent')
        def handle_urgent(self): ...
    
        @listen('normal')
        def handle_normal(self): ...

    • Adds unified declarative Flow loading, enabling Flows to be defined and loaded via configuration rather than only imperative Python.
    • Consolidates crewai run and crewai flow kickoff into a single command, simplifying the CLI surface.
    • Adds declarative Flow CLI support, letting practitioners launch declaratively defined Flows from the command line.
    • Enables @router() to be used as the start method of a Flow, allowing conditional branching logic at Flow entry points.
    • Adds typed output schemas for CrewAI tools, enabling structured, validated outputs from tool calls.

    +1 more show less

    • Keeps flow method progress visible for nested Crews, improving observability when Crews are embedded inside Flows.

    6 details in Everything

28. 1.14.8a2 Prerelease Jun 18, 2026 · issue 001

    CrewAI 1.14.8a2 adds single-agent actions inside Flow definitions and CELCELCommon Expression Language, an open-source expression language maintained by Google, used to embed lightweight, safe policy evaluation logic into tools without running a full scripting engine. expression validation at load time.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.8a2 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.8a2

    • Adds support for single agent actions directly within Flow definitions, enabling lightweight LLMLLMA 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. calls alongside full Crew steps without spinning up a multi-agent Crew.
    • Validates Flow CEL (Common Expression Language) expressions at definition load time, catching misconfigured routing conditions before runtime.

    2 details in Everything

29. 1.14.8a1 Prerelease Jun 18, 2026 · issue 001

    CrewAI 1.14.8a1 adds optional if expressions to each.do loop steps in Flows.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.8a1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.8a1

    • Supports optional if conditional expressions on each.do steps, enabling per-iteration filtering without wrapping logic in separate tasks.

    1 detail in Everything

30. 1.14.8a Prerelease Jun 18, 2026 · issue 001

    CrewAI 1.14.8a introduces JSON-first crew definitions, FlowDefinition actions, DMN mode, and a new crewai run --definition CLI flag.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.8a https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.8a

    └──▷ TRY IT
    Run a flow defined entirely in a JSON/definition file — no Python code required — to execute a crew-based automation.
    copy

    $ crewai run --definition

    • Adds crewai run --definition experimental CLI flag to run flows directly from a flow definition file without writing Python code.
    • Introduces JSON-first crew projects, enabling crew creation, configuration, and execution entirely through JSON rather than Python.
    • Adds script/code block, crew, and each composite actions to FlowDefinition, enabling richer declarative flow composition.
    • Adds expression support to FlowDefinition actions, enabling dynamic values within declarative flow definitions.
    • Implements DMN (Decision Model and Notation) mode support in crew creation and execution.

    +4 more show less

    • Enables human feedback to be driven directly from a flow definition, removing the need for custom Python callbacks.
    • Wires config and persistence settings from FlowDefinition into the runtime, closing the gap between declarative definitions and live execution.
    • Supports ZIP deployment fallback and JSON crew project environment runs, enabling portable crew packaging and deployment.
    • Enhances memory reset functionality with improved JSON crew handling.

    9 details in Everything

31. 1.14.7 Jun 11, 2026 · issue 001

    CrewAI 1.14.7 adds a chat API, Snowflake Cortex LLMLLMA 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., pluggable memory/RAGRAGRetrieval-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. backends, richer LLM event metadata, and route-aware Flow decorators.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.7 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.7

    └──▷ USE IT
    Route a flow's next step based on a condition using the new route-aware DSL decorator syntax.
    python copy

    from crewai.flow.flow import Flow, listen, router, start
    
    class TriageFlow(Flow):
        @start()
        def ingest(self):
            self.state.severity = classify_alert()
    
        @router(ingest)
        def route_by_severity(self):
            if self.state.severity == "critical":
                return "escalate"
            return "log_only"
    
        @listen("escalate")
        def escalate(self):
            ...
    
        @listen("log_only")
        def log_only(self):
            ...

    Use Snowflake Cortex as the LLM provider for an agent that queries internal data warehouses.
    python copy

    from crewai import Agent, LLM
    
    analyst = Agent(
        role="Data Analyst",
        goal="Summarize query results from Snowflake",
        backstory="Expert in SQL and data warehousing.",
        llm=LLM(model="snowflake/snowflake-arctic-instruct"),
    )

    • Adds a chat API for building conversational flows, enabling back-and-forth interaction patterns within CrewAI Flows.
    • Adds native Snowflake Cortex as a supported LLM provider.
    • Introduces pluggable default backends for memory, knowledge, RAG, and flow — allowing custom storage and retrieval engines without subclassing core internals.
    • Surfaces real finish_reason, sampling parameters, and response.id on LLM events for richer observability.
    • Introduces route-aware decorators for typing DSL triggers in Flows, enabling cleaner conditional routing definitions.

    +4 more show less

    • Supports building a FlowDefinition from Flow DSL metadata, exposing flow structure programmatically.
    • Makes the locking backend overridable for concurrent-run isolation and custom synchronization strategies.
    • Adds crew trained agents file support for persisting and reloading agent training state.
    • Improves import speed via lazy-loading of docling — meaningfully reducing cold-start latency in large deployments.

    9 details in Everything

32. 1.14.6 May 28, 2026 · release notes

    CrewAI 1.14.6 adds env-var isolation in StdioTransport, Databricks env_var declarations, and enhanced planning configuration.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.6 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.6

    • Adds env_vars declaration support on DatabricksQueryTool for explicit credential scoping.
    • Improves planning configuration and observation handling in agent execution.
    • Moves Skills Repository behind the CREWAI_EXPERIMENTAL gate as an experimental feature.

    3 details in Everything

33. 1.14.5 May 18, 2026 · release notes

    CrewAI 1.14.5 adds state-restore kickoff, ExaSearchTool highlights, and Daytona sandbox improvements.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.5 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.5

    └──▷ USE IT
    Resume a long-running Crew from a checkpoint state ID instead of restarting from scratch.
    python copy

    result = my_crew.kickoff(restore_from_state_id="<state_id>")

    • Adds restore_from_state_id kickoff parameter to resume a Crew run from a previously saved state.
    • Adds highlight results support to ExaSearchTool (formerly EXASearchTool).
    • Improves Daytona sandbox tool integration.
    • Defaults Crew agents to AgentExecutor, deprecating CrewAgentExecutor.

    4 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The EXASearchTool is renamed to ExaSearchTool; imports using the old name will break.
34. 1.14.4 Apr 30, 2026 · release notes

    CrewAI 1.14.4 adds custom persist keys, Azure OpenAI Responses API, Vertex AI workload identityworkload identityAn identity assigned to software, such as a service or container, rather than a person. It lets the workload authenticate and receive permissions without sharing a user's credentials., Tavily Research, and You.com MCPMCPModel 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. tools.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.4 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.4

    • Supports custom persistence keys in the @persist decorator for fine-grained checkpoint control.
    • Adds Responses API support for the Azure OpenAI provider.
    • Forwards credential_scopes to the Azure AI Inference client for scoped authentication.
    • Adds Vertex AI workload identity setup for credential-free GCP deployments.
    • Adds Tavily Research and Get Research tools for AI-powered web research workflows.

    +1 more show less

    • Adds You.com MCP tools covering search, research, and content extraction.

    6 details in Everything

35. 1.14.3 Apr 24, 2026 · release notes

    CrewAI 1.14.3 adds lifecycle events for checkpoints, e2b/Daytona sandbox support, Bedrock V4, Azure DefaultAzureCredential fallback, and ~29% cold-start reduction.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.3 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.3

    └──▷ USE IT
    Use keyless Azure auth in environments where injecting an API key is not possible (e.g., managed identity on Azure).
    python copy

    from crewai import LLM
    
    # No api_key provided — CrewAI falls back to DefaultAzureCredential automatically
    llm = LLM(
        model="azure/<your-deployment>",
        azure_endpoint="https://<your-resource>.openai.azure.com/",
        api_version="2024-02-01",
    )

    • Adds lifecycle events for checkpoint operations, enabling observability hooks around checkpoint create, resume, and fork actions.
    • Supports e2b sandbox integration for secure code execution within crews.
    • Adds Daytona sandbox tools for enhanced sandboxed functionality.
    • Adds checkpoint and fork support to standalone agents, not just full crews.
    • Falls back to DefaultAzureCredential when no API key is provided in the Azure integration, enabling keyless auth flows.

    +2 more show less

    • Adds Bedrock V4 support for AWS-hosted model access.
    • Optimizes MCPMCPModel 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 and event types to reduce cold start by ~29%, unlocking faster agent startup in latency-sensitive deployments.

    7 details in Everything

36. 1.14.2 Apr 17, 2026 · release notes

    CrewAI 1.14.2 adds checkpoint resume/fork/prune, template management, and enriched LLMLLMA 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. token tracking.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.2 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.2

    └──▷ USE IT
    Resume a failed crew run from a checkpoint instead of restarting from scratch.
    python copy

    result = crew.kickoff(from_checkpoint=<checkpoint_id>)

    • Adds checkpoint resume, diff, and prune commands for managing crew execution checkpoints.
    • Adds from_checkpoint parameter to Agent.kickoff and related methods to restart runs from a saved state.
    • Adds checkpoint forking with lineage tracking, enabling branched execution from any saved checkpoint.
    • Adds template management commands for creating and managing project templates.
    • Adds deploy validation CLI for pre-flight checks before deploying crews.

    +1 more show less

    • Enriches LLM token tracking with reasoning tokensreasoning tokensIntermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. and cache creation tokens.

    6 details in Everything

37. 1.14.1 Apr 8, 2026 · release notes

    CrewAI 1.14.1 adds async checkpoint TUITUIA text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. browser and proper resource management for streaming outputs.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.1

    • Adds async checkpoint TUI browser for interactive inspection of crew checkpoints.
    • Adds aclose()/close() methods and async context manager support to streaming outputs for proper resource cleanup.

    2 details in Everything

38. 1.14.0 Apr 7, 2026 · release notes

    CrewAI 1.14.0 adds runtime state checkpointing with SQLite storage, automatic checkpoint config, and new CLI commands for checkpoint management.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.14.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.14.0

    └──▷ TRY IT
    List all saved checkpoints for a crew run to find a resume point after an interrupted execution.
    copy

    $ crewai checkpoint list

    Inspect details of a specific checkpoint before deciding whether to resume from it.
    copy

    $ crewai checkpoint info <checkpoint-id>

    • Adds checkpoint list and checkpoint info CLI commands to inspect saved crew execution states.
    • Introduces SqliteProvider for persistent checkpoint storage backend.
    • Adds CheckpointConfig for configuring automatic checkpointing of crew runs.
    • Implements runtime state checkpointing and an event system so long-running crews can be resumed after interruption.
    • Adds guardrail_type and name fields to traces to distinguish guardrail events in observability pipelines.

    +1 more show less

    • Exports JsonProvider as an additional checkpoint storage option alongside SqliteProvider.

    6 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !CodeInterpreterTool is removed and code execution parameters are deprecated — any crew or agent config referencing CodeInterpreterTool or those parameters will break on upgrade.
39. 1.13.0 Apr 2, 2026 · release notes

    CrewAI 1.13.0 adds unified runtime state serialization, richer telemetry spans, token usage events, and an A2UI extension.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.13.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.13.0

    └──▷ USE IT
    Capture token usage from every LLMLLMA 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. call — useful for cost attribution or rate-limit monitoring in a pipeline.
    python copy

    from crewai.events import LLMCallCompletedEvent
    from crewai.event_bus import event_bus
    
    @event_bus.on(LLMCallCompletedEvent)
    def on_llm_done(event: LLMCallCompletedEvent):
        print(event.token_usage)

    • Adds RuntimeState RootModel for unified state serialization across crew runs.
    • Enhances the event listener with new telemetry spans covering skill and memory events.
    • Adds A2UI extension with v0.8/v0.9 support, schemas, and documentation.
    • Emits token usage data in LLMCallCompletedEvent for per-call cost and usage tracking.
    • Reduces framework overhead via a lazy event bus and skips tracing entirely when disabled.

    5 details in Everything

40. 1.12.1 Mar 26, 2026 · release notes

    CrewAI 1.12.1 adds Qdrant memory backend, agent skills, native OpenAI-compatible providers, and automatic hierarchical memory isolation.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.12.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.12.1

    └──▷ USE IT
    Connect CrewAI to a self-hosted Ollama instance as a native OpenAI-compatible provider, bypassing LiteLLM.
    python copy

    from crewai import LLM
    
    llm = LLM(
        model="ollama/llama3",
        base_url="http://localhost:11434"
    )

    • Adds request_id to HumanFeedbackRequestedEvent for tracking human-in-the-loophuman-in-the-loopHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues. feedback requests.
    • Adds Qdrant Edge storage backend for the memory system.
    • Adds agent skills support.
    • Implements automatic root_scope for hierarchical memory isolation across agents.
    • Supports native OpenAI-compatible providers: OpenRouterOpenRouterA unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code., DeepSeek, Ollama, vLLM, Cerebras, and Dashscope.

    +2 more show less

    • Adds logout command to the CLI.
    • Adds docs-check command to analyze changes and generate docs with translations.

    7 details in Everything

41. 1.12.0 Mar 26, 2026 · release notes

    CrewAI 1.12.0 adds Qdrant memory backend, agent skills, native OpenAI-compatible providers, hierarchical memory isolation, and a CLI logout command.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.12.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.12.0

    └──▷ TRY IT
    Log out of the CrewAI platform from the terminal to rotate credentials or switch accounts.
    copy

    $ crewai logout

    • Adds Qdrant Edge as a storage backend for the memory system.
    • Introduces agent skills as a new first-class capability for agents.
    • Implements automatic root_scope for hierarchical memory isolation across crews.
    • Supports native OpenAI-compatible providers: OpenRouterOpenRouterA unified API gateway that routes requests to dozens of LLM providers under one endpoint, letting cyber tools swap or compare models without rewriting provider-specific integration code., DeepSeek, Ollama, vLLM, Cerebras, and Dashscope — without requiring LiteLLM.
    • Adds a logout command to the CrewAI CLI.

    +1 more show less

    • Adds a docs-check CLI command to analyze changes and generate translated documentation.

    6 details in Everything

42. 1.11.1 Mar 23, 2026 · release notes

    CrewAI 1.11.1 adds flow_structure() serializer for programmatic Flow class introspection.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.11.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.11.1

    └──▷ USE IT
    Inspect the structure of a defined Flow programmatically — useful for debugging or generating visual representations of agent pipelines.
    python copy

    flow = MyFlow()
    structure = flow.flow_structure()
    print(structure)

43. 1.10.0 Feb 27, 2026 · release notes

    CrewAI 1.10.0 adds user input handling in Flows, enhanced MCPMCPModel 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 resolution, and auto-updating tool specs.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.10.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.10.0

    • Adds user input handling in Flows, enabling human-in-the-loophuman-in-the-loopHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues. data collection mid-flow execution.
    • Enhances MCP tool resolution and emits related events for better observability of MCP-based tool usetool useA 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..
    • Adds started_event_id tracking on the event bus for correlating flow and agent lifecycle events.
    • Introduces auto-update of tools.specs, keeping tool specifications current without manual intervention.
    • Enhances HITLHITLHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues. (Human-in-the-Loop) self-loop functionality in human feedback integration.

    +4 more show less

    • Improves JSON argument parsing and validation in CrewAgentExecutor and BaseTool for more robust tool invocation.
    • Migrates CLI HTTP client from requests to httpx, enabling async-compatible CLI operations.
    • Adds versioned documentation support and yanked-version detection in release notes.
    • Updates LanceDB version and adds lance-namespace packages for expanded vector storevector storeA database built to store embeddings and find the nearest ones to a query quickly. It is the retrieval half of most RAG systems. integration.

    9 details in Everything

44. 1.9.1 Jan 28, 2026 · release notes

    CrewAI 1.9.1 adds before/after tool call hooks and structured outputstructured outputForcing 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. support across providers

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.9.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.9.1

    • Adds before and after tool call hooks in CrewAgentExecutor for intercepting and acting on tool invocations.
    • Supports structured outputsstructured outputsForcing 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. and response_format parameter across LLMLLMA 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. providers for typed agent responses.

    2 details in Everything

45. 1.9.0 Jan 27, 2026 · release notes

    CrewAI 1.9.0 adds A2AA2AAgent2Agent, 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. task execution, Keycloak SSOSSOSingle sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management., structured outputsstructured outputsForcing 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., and native multimodalmultimodalAble 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. file handling.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.9.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.9.0

    └──▷ USE IT
    Enforce a typed JSON schema on LLMLLMA 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. output so downstream code can safely parse structured results.
    python copy

    from pydantic import BaseModel
    from crewai import Agent, Task, Crew
    
    class ThreatReport(BaseModel):
        severity: str
        affected_systems: list[str]
        recommendation: str
    
    analyst = Agent(role="Threat Analyst", goal="Analyze security incidents", backstory="...", verbose=False)
    task = Task(
        description="Analyze the attached incident log and produce a threat report.",
        expected_output="A structured threat report",
        agent=analyst,
        response_format=ThreatReport,
    )
    crew = Crew(agents=[analyst], tasks=[task])
    result = crew.kickoff()
    report: ThreatReport = result.pydantic

    • Adds structured outputs and response_format support across providers for typed, schema-constrained LLM responses.
    • Adds response_id field in streaming responses for tracking and correlating streamed completions.
    • Adds event ordering and parent-child hierarchy to the event system for richer execution tracing.
    • Adds Keycloak SSO provider support for enterprise authentication integration.
    • Adds native multimodal file handling with OpenAI Responses API support.

    +5 more show less

    • Adds agent-to-agent (A2A) task execution utilities for orchestrating inter-agent workflows.
    • Adds A2A server config and agent card generation for declaring and advertising agent capabilities.
    • Adds additional A2A events with enriched event metadata for deeper observability into A2A interactions.
    • Adds additional A2A transports for flexible agent-to-agent communication.
    • Adds Galileo integration for LLM evaluation and observability.

    10 details in Everything

46. 1.8.1 Jan 15, 2026 · release notes

    CrewAI 1.8.1 adds Agent-to-AgentAgent-to-AgentAgent2Agent, 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. (A2AA2AAgent2Agent, 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.) task execution, server configuration, agent card generation, and new transports.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.8.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.8.1

    • Adds A2A task execution utilities for orchestrating agent-to-agent workflows.
    • Adds A2A server configuration and agent card generation to expose CrewAI agents as A2A-compatible services.
    • Adds additional A2A transports, broadening connectivity options between agents.
    • Adds Galileo to the integrations page, enabling Galileo observability for CrewAI workflows.

    4 details in Everything

47. 1.8.0 Jan 8, 2026 · release notes

    CrewAI 1.8.0 adds Agent-to-AgentAgent-to-AgentAgent2Agent, 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. async/streaming/push update mechanisms and Human-in-the-Loop support for Flows.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.8.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.8.0

    • Adds native async chain support for agent-to-agent (A2AA2AAgent2Agent, 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.
    • Introduces A2A update mechanisms — poll, stream, and push — with configurable handlers.
    • Adds Human-in-the-Loop (HITLHITLHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues.) feedback support directly within Flows via global flow configuration.
    • Adds streaming tool call events for real-time observability of tool execution.
    • Introduces production-ready Flows and Crews architecture.

    +1 more show less

    • Improves EventListener and TraceCollectionListener for enhanced event handling.

    6 details in Everything

48. 1.7.1 Dec 16, 2025 · release notes

    CrewAI 1.7.1 adds a --no-commit flag to the bump command and switches to JSON schema for tool argument serialization.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.7.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.7.1

    └──▷ TRY IT
    Bump the project version without creating a git commit, useful in CI pipelines where you control commits separately.
    copy

    $ crewai bump --no-commit

    • Adds --no-commit flag to the bump command, allowing version bumps without auto-committing changes.
    • Switches tool argument serialization to use JSON schema for more structured, interoperable tool definitions.

    2 details in Everything

49. 1.7.0 Dec 9, 2025 · release notes

    CrewAI 1.7.0 adds comprehensive async support across flows, crews, tasks, tools, memory, knowledge, and LLMsLLMsA 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..

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.7.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.7.0

    └──▷ USE IT
    Run a full crew asynchronously to avoid blocking the event loop in an async application or service.
    python copy

    import asyncio
    from crewai import Crew, Agent, Task
    
    agent = Agent(role="Analyst", goal="Analyze data", backstory="Expert analyst")
    task = Task(description="Summarize the report", agent=agent, expected_output="Summary")
    crew = Crew(agents=[agent], tasks=[task])
    
    async def main():
        result = await crew.kickoff_async()
        print(result)
    
    asyncio.run(main())

    Kick off a Flow asynchronously so multiple flows can run concurrently in the same process.
    python copy

    import asyncio
    from crewai.flow.flow import Flow, start
    
    class MyFlow(Flow):
        @start()
        async def run_step(self):
            return "done"
    
    async def main():
        flow = MyFlow()
        result = await flow.kickoff_async()
        print(result)
    
    asyncio.run(main())

    • Adds async flow kickoff, enabling non-blocking orchestration of multi-agent pipelines.
    • Adds async crew support so entire crews can be run concurrently without blocking the event loop.
    • Adds async task support for individual task execution within crews.
    • Adds async knowledge and memory support for non-blocking retrieval and storage operations.
    • Adds async support for tools and the agent executor with improved typing.

    +4 more show less

    • Adds native async tool support, allowing tools to be defined and invoked asynchronously.
    • Adds async LLMLLMA 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. support for non-blocking model inference calls.
    • Implements the agent-to-agent (A2AA2AAgent2Agent, 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.) extensions API with async agent card caching.
    • Introduces system event types and a handler for observability and lifecycle events.

    9 details in Everything

50. 1.6.0 Nov 25, 2025 · release notes

    CrewAI 1.6.0 adds streaming results for flows and crews, Entra IDEntra IDMicrosoft's cloud-based identity and access management service, formerly Azure Active Directory, used by cyber tools to authenticate users and enforce access policies in Microsoft 365 and Azure environments. CLI login, a Merge Agent Handler tool, and Gemini 2.5 Pro preview support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.6.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.6.0

    • Adds streaming result support to flows and crews, enabling real-time output consumption.
    • Supports CLI login with Entra ID (Microsoft Entra / Azure AD) for enterprise SSOSSOSingle sign-on, using one identity provider to sign in to multiple applications. It reduces separate passwords and centralizes account and access management. authentication.
    • Adds Merge Agent Handler tool for combining agent outputs.
    • Enhances flow event state management for improved control over flow lifecycle events.

    4 details in Everything

51. 1.5.0 Nov 16, 2025 · release notes

    CrewAI 1.5.0 adds LLMLLMA 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. call hooks, exposes messages to task outputs, and improves A2AA2AAgent2Agent, 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. trust and Okta data.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.5.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.5.0

    └──▷ USE IT
    Inspect the full message history attached to a task result for auditing or downstream processing.
    python copy

    result = crew.kickoff()
    for task_output in result.tasks_output:
        print(task_output.messages)

    • Adds before and after LLM call hooks in CrewAgentExecutor for observability and control around every LLM invocation.
    • Exposes messages to TaskOutput and LiteAgentOutputs, giving callers access to the full message history from a task run.
    • Adds A2A trust remote completion status flag for agent-to-agent trust workflows.
    • Fetches and stores richer data about Okta authorization servers for enhanced auth integrations.
    • Enhances schema description of QdrantVectorSearchTool for improved usability and discoverability.

    5 details in Everything

52. 1.4.0 Nov 7, 2025 · release notes

    CrewAI 1.4.0 adds first-class MCPMCPModel 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, LLMLLMA 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. message interceptor hooks, and enhances the QdrantVectorSearchTool.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.4.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.4.0

    • Adds first-class support for MCP (Model Context ProtocolModel Context ProtocolModel 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.) with improved concurrent tool execution handling.
    • Enhances QdrantVectorSearchTool with new capabilities for vector search workflows.
    • Adds support for non-ASTASTAn abstract syntax tree, a structured representation of parsed code. Tools inspect or transform this tree to understand expressions and statements rather than just matching text. plot routes, expanding flow visualization options.
    • Caches i18n prompts for more efficient repeated use across agents.

    4 details in Everything

53. 1.3.0 Nov 1, 2025 · release notes

    CrewAI 1.3.0 enhances the QdrantVectorSearchTool with improved vector search capabilities.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.3.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.3.0

54. 1.2.1 Oct 27, 2025 · release notes

    CrewAI 1.2.1 adds Datadog observability integration and MCPMCPModel 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./app support in LiteAgent.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.2.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.2.1

    • Adds Datadog integration for observability and tracing of CrewAI agent runs.
    • Enables apps and MCPs (Model Context ProtocolModel Context ProtocolModel 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) as supported resources in LiteAgent.

    2 details in Everything

55. 1.1.0 Oct 21, 2025 · release notes

    CrewAI 1.1.0 adds multi-provider LLMLLMA 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. support in InternalInstructor, a mypy plugin base, and improves QdrantVectorSearchTool.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.1.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.1.0

    • Adds multi-provider LLM support to InternalInstructor, enabling structured outputstructured outputForcing 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. extraction across different LLM backends.
    • Introduces a mypy plugin base for improved static type checking of CrewAI code.
    • Improves QdrantVectorSearchTool for better vector search integration.

    3 details in Everything

56. 1.0.0 Oct 20, 2025 · release notes

    CrewAI 1.0.0 adds enhanced knowledge/guardrail event handling and tool repository credential injection for the run command.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 1.0.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 1.0.0

    • Enhances knowledge and guardrail event handling in the Agent class for more robust agent lifecycle control.
    • Injects tool repository credentials automatically in the crewai run command, enabling authenticated tool source access.

    2 details in Everything

57. 0.201.1 Sep 26, 2025 · release notes

    CrewAI 0.201.1 adds ChromaDB support for WatsonX and VoyageAI embeddingembeddingLists 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. providers.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.201.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.201.1

    └──▷ BREAKING ON UPGRADE

    • !The watson embedding provider is renamed to watsonx; environment variable prefixes are updated accordingly — any config using the old watson provider name or its env var prefixes will break on upgrade.
58. 0.201.0 Sep 26, 2025 · release notes

    CrewAI 0.201.0 adds a crewai uv CLI wrapper, custom embeddingembeddingLists 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. types, thread-safe platform context, and failed-trace marking for observability.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.201.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.201.0

    └──▷ USE IT
    Set batch_size on an embedder to avoid hitting token limits when indexing large document sets.
    python copy

    embedder_config = {
        "provider": "openai",
        "config": {
            "model": "text-embedding-3-small",
            "batch_size": 50
        }
    }

    • Adds crewai uv wrapper command to invoke uv directly through the CrewAI CLI.
    • Supports batch_size configuration on embedders to stay within token limits.
    • Introduces thread-safe platform context management for concurrent crew workflows.
    • Enables marking traces as failed in observability workflows.
    • Adds custom embedding types and provider migration support.

    +3 more show less

    • Upgrades ChromaDB dependency to v1.1.0 with type improvements.
    • Introduces Pydantic v2 support along with pydantic-settings and dependency group reorganization.
    • Adds Pydantic-compatible import validation, replacing legacy utilities.

    8 details in Everything

59. 0.193.0 Sep 19, 2025 · release notes

    CrewAI 0.193.0 makes RAGRAGRetrieval-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./knowledge/memory search params fully configurable and enables ChromaDB OpenAI embeddingsembeddingsLists 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..

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.193.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.193.0

    • Makes search parameters for RAG, knowledge, and memory fully configurable.
    • Enables ChromaDB to use OpenAI API as an embeddingembeddingLists 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. function.
    • Adds deeper observability tools for user-level insights.
    • Introduces thread-safe platform context management.
    • Unifies RAG storage system with instance-specific client support.

    +2 more show less

    • Adds ephemeral trace improvements for better trace control.
    • Adds missing event exports to __init__.py for consistent module behavior.

    7 details in Everything

60. 0.186.0 Sep 10, 2025 · release notes

    CrewAI 0.186.0 adds Qdrant RAGRAGRetrieval-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. support, partial flow resumability, auto-injection of trigger payloads, and a new config reset command.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.186.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.186.0

    └──▷ TRY IT
    Reset stored auth/API tokens without being prompted for email — useful when rotating credentials in CI.
    copy

    $ crewai config reset

    • Adds support for crewai_trigger_payload auto-injection into crew/flow executions.
    • Introduces a centralized RAG configuration system with optional imports, including Qdrant as a new RAG provider.
    • Implements generic clients for ChromaDB and Qdrant storage backends.
    • Enables partial flow resumability, allowing interrupted flows to resume mid-execution.
    • Displays task names in verbose output for clearer runtime observability.

    +3 more show less

    • Introduces crewai config reset command for resetting authentication tokens.
    • Adds additional parameters to Flow.start() methods for more flexible flow invocation.
    • Introduces centralized configuration for embeddingembeddingLists 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. types and a base embedding client.

    8 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !A deprecation warning is now emitted for Task.max_retries; callers using this field should migrate before it is removed.
61. 0.175.0 Aug 28, 2025 · release notes

    CrewAI 0.175.0 adds Qdrant RAGRAGRetrieval-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. support, crewai config reset, auto-injected trigger payloads, and a centralized embeddingembeddingLists 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. client system.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.175.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.175.0

    └──▷ TRY IT
    Clear cached login tokens from the local crewAI config when rotating credentials or switching accounts.
    copy

    $ crewai config reset

    • Adds Qdrant as a RAG provider, with a new generic Qdrant client alongside an existing ChromaDB client.
    • Introduces a centralized embedding types system and a base embedding client for standardized embedding configuration.
    • Adds crewai config reset command to clear stored tokens.
    • Enables crewai_trigger_payload auto-injection into flows triggered by automation.
    • Adds support for additional parameters in Flow.start() methods.

    +3 more show less

    • Displays task names in verbose CLI output for better observability.
    • Simplifies RAG client initialization with a new RAG configuration system.
    • Adds support to remove Auth0 and email entry on crewai login.

    8 details in Everything

62. 0.165.1 Aug 19, 2025 · release notes

    CrewAI 0.165.1 adds agent message history to ExternalMemory, auto-injects trigger payloads, and links memory entries to agent IDs in Mem0.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.165.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.165.1

    • Includes exchanged agent messages in ExternalMemory metadata for richer memory context.
    • Automatically injects crewai_trigger_payload into crew execution context.
    • Adds support for agent_id-linked memory entries in Mem0 integration.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The internal flag inject_trigger_input is renamed to allow_crewai_trigger_context; any code or config referencing the old name will break.
    • !The AgentOps integration has been removed; any setup relying on it will no longer function.
63. 0.165.0 Aug 19, 2025 · release notes

    CrewAI 0.165.0 enriches ExternalMemory with agent messages, auto-injects trigger payloads, and adds agent_id-linked Mem0 entries.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.165.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.165.0

    • Includes exchanged agent messages in ExternalMemory metadata for richer memory context.
    • Automatically injects crewai_trigger_payload into crew runs triggered externally.
    • Adds support for agent_id-linked memory entries in Mem0 integration.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The internal flag inject_trigger_input is renamed to allow_crewai_trigger_context; any configuration or code referencing inject_trigger_input will break.
    • !The AgentOps integration has been removed; any setup relying on it will stop working.
64. 0.159.0 Aug 13, 2025 · release notes

    CrewAI 0.159.0 adds enterprise CLI setup command and partial flow resumability support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.159.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.159.0

    └──▷ TRY IT
    Configure enterprise credentials and parameters without manually editing config files.
    copy

    $ crewai enterprise configure

    • Adds enterprise configure CLI command for streamlined enterprise setup.
    • Introduces partial flow resumability, enabling flows to resume from an intermediate state rather than restarting entirely.

    2 details in Everything

65. 0.157.0 Aug 6, 2025 · release notes

    CrewAI 0.157.0 adds a crewai config CLI command group, Okta device authorization, LangDB integration, and initial tracing capabilities.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.157.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.157.0

    └──▷ TRY IT
    Inspect or set CrewAI CLI configuration without manually editing config files.
    copy

    $ crewai config

    • Adds crewai config CLI command group for managing CLI configuration.
    • Supports device authorization with Okta for authenticated flows.
    • Adds LangDB integration for observability and query tracing.
    • Introduces initial tracing capabilities for crew and flow execution.
    • Enables persisting Flow state with BaseModel entries.

    +1 more show less

    • Adds default value support for crew.name.

    6 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !Support for the deprecated User Memory system has been dropped; any setup relying on it will stop working after upgrading.
66. 0.152.0 Jul 30, 2025 · release notes

    CrewAI 0.152.0 adds custom Flow names, a dedicated RAGRAGRetrieval-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. module, and timezone-aware event timestamps.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.152.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.152.0

    • Supports custom flow names on the Flow class for clearer identification of flows.
    • Refactors RAG components into a dedicated top-level module for cleaner imports and organization.
    • Adds timezone support to event timestamps for accurate time-based event tracking.

    3 details in Everything

67. 0.150.0 Jul 23, 2025 · release notes

    CrewAI 0.150.0 adds ad-hoc tool callingtool callingA 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., Mem0 v2 storage, SerperScrapeWebsiteTool, and Bedrock AgentCore browser/code interpreter toolkits.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.150.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.150.0

    • Adds support for ad-hoc tool calling via the internal LLMLLMA 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. class, enabling on-demand tool invocation outside of standard crew/agent flows.
    • Upgrades Mem0 Storage integration from v1.1 to v2.
    • New SerperScrapeWebsiteTool extracts clean content from URLs using Serper.
    • Integrates Bedrock AgentCore browser and code interpreter toolkits for use with Bedrock agents.
    • Adds UserMemory deprecation notice to signal future removal.

    5 details in Everything

68. 0.148.0 Jul 16, 2025 · release notes

    CrewAI 0.148.0 introduces Agent evaluation functionality with thread-safe AgentEvaluator and neatlogs integration.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.148.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.148.0

    • Introduces Agent evaluation functionality with AgentEvaluator, supporting regression testing and experiment methods for both Agent and LiteAgent.
    • Enables event emission during Agent evaluation for observability into evaluation runs.
    • Adds crew context tracking for LLMLLMA 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. guardrail events.
    • Adds integration with neatlogs for structured agent log management.

    4 details in Everything

69. 0.141.0 Jul 9, 2025 · release notes

    CrewAI 0.141.0 adds crew context tracking for LLMLLMA 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. guardrail events.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.141.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.141.0

70. 0.140.0 Jul 2, 2025 · release notes

    CrewAI 0.140.0 adds LLMLLMA 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. call tracking by task/agent, MemoryEvents monitoring, and a WorkOS CLI login command.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.140.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.140.0

    • Tracks LLM calls broken down by task and agent for observability into crew execution costs and patterns.
    • Introduces MemoryEvents to monitor memory usage within a crew run.
    • Adds console logging for memory system and LLM guardrail events.
    • Improves data training support for models up to 7B parameters.
    • Adds workos login command to the CLI for WorkOS-based authentication.

    5 details in Everything

71. 0.134.0 Jun 25, 2025 · release notes

    CrewAI 0.134.0 adds MCPMCPModel 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. multi-tool agent support, Tool-attribute initialization, and Oxylabs web scraping tools.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.134.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.134.0

    • Supports initializing a tool directly from defined Tool attributes, enabling programmatic tool construction.
    • Adds an official way to use MCP Tools within a CrewBase class.
    • Enhances MCP tools support to allow selecting multiple tools per agent inside CrewBase.
    • Adds Oxylabs Web Scraping tools as a built-in integration.

    4 details in Everything

72. 0.130.0 Jun 12, 2025 · release notes

    CrewAI 0.130.0 adds LiteAgent with Guardrail integration, async tool execution, and multi-org CLI support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.130.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.130.0

    • Introduces LiteAgent with built-in Guardrail integration for lightweight, constrained agent workflows.
    • Enables async tool execution for more efficient, non-blocking agent workflows.
    • Adds support for multi-org actions in the CLI.
    • Upgrades LiteLLM to support the latest OpenAI version.

    4 details in Everything

73. 0.126.0 Jun 5, 2025 · release notes

    CrewAI 0.126.0 adds Python 3.13 support, streamable-HTTP MCPMCPModel 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, prompt/memory transparency, and tool-logging.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.126.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.126.0

    • Adds Python 3.13 support.
    • Adds streamable-HTTP transport support in MCP integration.
    • Enables tools to be loaded from an Agent repository via their own module.
    • Persists available tools from a Tool repository across sessions.
    • Logs tool usage when called by an LLMLLMA 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. for observability.

    +2 more show less

    • Introduces transparency features for prompts and memory systems.
    • Adds community analytics support.

    7 details in Everything

74. 0.121.0 May 22, 2025 · release notes

    CrewAI 0.121.0 adds markdown rendering for Tasks, reasoning for Agents, automatic date injection, and a HallucinationGuardrail.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.121.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.121.0

    └──▷ USE IT
    Enable markdown output for a task so results are returned as formatted markdown.
    python copy

    from crewai import Task
    
    task = Task(
        description="Summarize the latest threat intelligence report.",
        expected_output="A structured summary of key findings.",
        markdown=True
    )

    Enable reasoning on an agent and inject today's date automatically for time-sensitive analysis workflows.
    python copy

    from crewai import Agent
    
    analyst = Agent(
        role="Threat Analyst",
        goal="Identify emerging threats from recent feeds.",
        backstory="Expert in cyber threat intelligence.",
        reasoning=True,
        inject_date=True
    )

    • Adds markdown attribute to the Task class for controlling markdown-formatted output.
    • Adds reasoning attribute to the Agent class to enable or configure agent reasoning behavior.
    • Adds inject_date flag to Agent for automatic date injection into agent context.
    • Implements HallucinationGuardrail for detecting and guarding against hallucinated outputs.

    4 details in Everything

75. 0.120.0 May 14, 2025 · release notes

    CrewAI 0.120.0 adds agent-from-repository loading, empty Task context, and direct knowledge initialization.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.120.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.120.0

    • Supports loading an Agent directly from a repository.
    • Enables setting an empty context for a Task.
    • Introduces direct initialization of knowledge, bypassing knowledge_sources.

    3 details in Everything

76. 0.119.0 May 8, 2025 · release notes

    CrewAI 0.119.0 adds parent flow identification for Crew and LiteAgent and knowledge retrieval prompt rewriting in Agent.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.119.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.119.0

    • Enables parent flow identification for Crew and LiteAgent, improving traceability in nested flow architectures.
    • Introduces knowledge retrieval prompt rewriting in Agent for improved tracking and debugging of RAGRAGRetrieval-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.-based workflows.

    2 details in Everything

77. 0.118.0 Apr 30, 2025 · release notes

    CrewAI 0.118.0 adds no-code Guardrail creation and renames TaskGuardrail to LLMGuardrail.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.118.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.118.0

    • Adds support for no-code Guardrail creation to simplify AI behavior controls without writing custom guardrail logic.

    1 detail in Everything

    └──▷ BREAKING ON UPGRADE

    • !TaskGuardrail is renamed to LLMGuardrail; any code importing or referencing TaskGuardrail will break on upgrade.
78. 0.117.0 Apr 28, 2025 · release notes

    CrewAI 0.117.0 adds result_as_answer decorator support, GPT-4.1/Gemini-2.x models, and a HuggingFace CLI provider.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.117.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.117.0

    └──▷ USE IT
    Return a tool's output directly as the agent's final answer, bypassing further LLMLLMA 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. reasoning — useful for deterministic lookup tools where you trust the result completely.
    python copy

    from crewai.tools import tool
    
    @tool(result_as_answer=True)
    def lookup_cve(cve_id: str) -> str:
        """Fetch CVE details from internal database."""
        return fetch_cve_record(cve_id)

    • Adds result_as_answer parameter to the @tool decorator, allowing a tool's output to be used directly as the agent's final answer.
    • Supports new language models: GPT-4.1, Gemini-2.0, and Gemini-2.5 Pro.
    • Adds HuggingFace as a provider option in the CrewAI CLI.
    • Enhances knowledge management capabilities.

    4 details in Everything

79. 0.114.0 Apr 10, 2025 · release notes

    CrewAI 0.114.0 lets agents run standalone, adds custom LLMLLMA 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. support, external memory, and Opik observability.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.114.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.114.0

    └──▷ USE IT
    Run a single agent as a standalone unit — useful in Flows or one-off tasks without assembling a full Crew.
    python copy

    from crewai import Agent
    
    researcher = Agent(
        role="Research Analyst",
        goal="Find the latest CVEs for Apache HTTP Server",
        backstory="You are an expert in vulnerability research.",
        llm="gpt-4o"
    )
    
    result = researcher.kickoff()
    print(result)

    • Enables agents as atomic, standalone units — call Agent(...).kickoff() without a full Crew.
    • Supports custom LLM implementations for bringing your own model client.
    • Integrates External Memory for persistent agent knowledge across runs.
    • Adds Opik observability integration for tracing and monitoring agent workflows.
    • Adds wildcard support to emit() for flexible event broadcasting.

    +3 more show less

    • Introduces secure fingerprints for agents and crews to uniquely identify and track them.
    • Adds multimodalmultimodalAble 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. agent validation to enforce correct configuration of multimodal agents.
    • Enhanced YAML extraction for more robust crew and agent definition parsing.

    8 details in Everything

80. 0.108.0 Mar 17, 2025 · release notes

    CrewAI 0.108.0 adds agent fingerprints, richer event listener visualization, and improved LLMLLMA 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. streaming event handling.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.108.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.108.0

    • Adds fingerprints to agents/tasks for unique identity tracking across runs.
    • Enhances LLM streaming response handling with an improved event system for real-time observability.
    • Enriches the event listener with rich visualization and improved logging output.
    • Includes model_name in relevant model representations for better introspection.

    4 details in Everything

81. 0.105.0 Mar 9, 2025 · release notes

    CrewAI 0.105.0 adds Flow state export, an event emitter for LLMLLMA 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. observability, multi-router support, and Python 3.10 compatibility.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.105.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.105.0

    • Adds Flow state export and improved state utilities for inspecting and persisting Flow execution state.
    • Introduces an event emitter for observability, enabling tracking of LLM calls and agent events.
    • Supports multiple router calls within a single Flow, enabling more complex routing logic.
    • Adds support for Python 3.10.
    • Adds ChatOllama integration via langchain_ollama for local LLM usage.

    +3 more show less

    • Adds context windowcontext windowThe 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 support for the o3-mini model.
    • Enhances agent knowledge setup with an optional crew-level embedder configuration.
    • Adds QdrantVectorSearchTool guide and event listener usage documentation.

    8 details in Everything

82. 0.102.0 Feb 13, 2025 · release notes

    CrewAI 0.102.0 adds QdrantVectorSearchTool, JSON logging, multi-tab Excel knowledge, and custom embedder support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.102.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.102.0

    └──▷ USE IT
    Search a Qdrant vector collection from within a CrewAI agent tool to ground responses in your own embeddingsembeddingsLists 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..
    python copy

    from crewai_tools import QdrantVectorSearchTool
    
    tool = QdrantVectorSearchTool(
        collection_name="security-advisories",
        url="http://localhost:6333",
        api_key="<your-qdrant-api-key>"
    )
    agent = Agent(role="Threat Analyst", tools=[tool], ...)

    • Adds QdrantVectorSearchTool for vector similarity search against Qdrant collections.
    • Supports JSON format for logging output, improving observability pipeline integration.
    • Enables multi-tab Excel file processing in excel_knowledge_source.py for richer knowledge ingestion.
    • Adds a reset_memories function to the Crew class for programmatic memory management.
    • Supports custom embedder configuration for enhanced embeddingembeddingLists 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. setup in knowledge sources.

    +1 more show less

    • Integrates MLflow tracing support for agent execution observability.

    6 details in Everything

83. 0.100.0 Jan 28, 2025 · release notes

    CrewAI 0.100.0 adds Amazon SageMaker as a supported LLMLLMA 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. provider.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.100.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.100.0

    • Supports Amazon SageMaker as an LLM provider for running agents against hosted SageMaker endpoints.

    1 detail in Everything

84. 0.98.0 Jan 20, 2025 · release notes

    CrewAI 0.98.0 adds Conversation Crew, flow state persistence with @persist, and SambaNova/NVIDIA NIM/VoyageAI integrations.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.98.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.98.0

    └──▷ USE IT
    Persist flow state across runs so a long-running security workflow can resume where it left off after interruption.
    python copy

    from crewai.flow.persistence import persist, FlowPersistence
    
    class MySecurityFlow(Flow):
        @persist
        def analyze_targets(self):
            # state is automatically saved after this method completes
            ...

    • New Conversation Crew v1 enables interactive, dialogue-driven crew execution.
    • Adds unique IDs to flow states for tracking and referencing individual flow runs.
    • New @persist decorator with FlowPersistence interface enables durable flow state persistence across runs.
    • Adds SambaNova as a new LLMLLMA 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. provider integration.
    • Adds NVIDIA NIM as a new provider via the CrewAI CLI.

    +1 more show less

    • Introduces VoyageAI as a new embeddingembeddingLists 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./model integration.

    6 details in Everything

85. 0.95.0 Jan 4, 2025 · release notes

    CrewAI 0.95.0 adds multimodalmultimodalAble 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. agents, programmatic guardrails, multi-round HITLHITLHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues., Gemini 2.0, Langfuse, Portkey, Docling, and Weaviate support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.95.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.95.0

    • Adds multimodal abilities to Crew, enabling agents to process image and other non-text inputs.
    • Introduces programmatic guardrails for enforcing constraints on agent outputs at runtime.
    • Supports multiple rounds of Human-in-the-Loop (HITL) interaction within a single crew run.
    • Adds Gemini 2.0 model support.
    • Delivers CrewAI Flows improvements for more capable workflow orchestration.

    +6 more show less

    • Adds workflow permissions to control agent and task access within a crew.
    • Supports Langfuse observability via LiteLLM integration.
    • Adds Portkey integration for LLMLLMA 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. gateway and observability.
    • Introduces interpolate_only method on prompt/template handling for targeted variable substitution.
    • Adds Docling support for document ingestion and parsing.
    • Adds Weaviate support as a vector storevector storeA database built to store embeddings and find the nearest ones to a query quickly. It is the retrieval half of most RAG systems. for agent knowledge.

    11 details in Everything

86. 0.86.0 Dec 5, 2024 · release notes

    CrewAI 0.86.0 adds multi-round Human-in-the-Loop follow-up and expanded knowledge tooling

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.86.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.86.0

    • Supports multiple rounds of Human-in-the-Loop (HITLHITLHuman in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues.) follow-up, enabling iterative human feedback within a crew's execution flow.
    • Adds Nvidia NIM as a supported provider for custom LLMLLMA 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. configuration.
    • Introduces a knowledge demo and improved knowledge documentation to help practitioners integrate knowledge sources into crews.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !All references to Pipeline and PipelineRouter have been removed; any working setup that uses these constructs will break on upgrade.
87. 0.85.0 Dec 4, 2024 · release notes

    CrewAI 0.85.0 adds agent-level knowledge, removes LangChain dependency, and improves typed task outputs.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.85.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.85.0

    • Adds knowledge support at the individual agent level, enabling per-agent knowledge bases alongside crew-level knowledge.
    • Removes LangChain as a dependency, reducing the library's footprint and eliminating LangChain version conflicts.
    • Improves typed task outputs for stronger, more predictable structured results from tasks.
    • Adds Tool Repository authentication via crewai login, enabling access to hosted tools.

    4 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !LangChain has been removed as a dependency; any code or configuration that imports or relies on LangChain internals through CrewAI will break on upgrade.
88. v0.83.0 Nov 25, 2024 · release notes

    CrewAI v0.83.0 adds crew lifecycle callbacks, agent knowledge pre-seeding, and Mem0 memory/preference retrieval.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.83.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout v0.83.0

    └──▷ USE IT
    Run setup or teardown logic around a crew execution using the new lifecycle hooks.
    python copy

    @crew
    def my_crew(self) -> Crew:
        return Crew(
            agents=self.agents,
            tasks=self.tasks,
            before_kickoff=self.before_kickoff,
            after_kickoff=self.after_kickoff,
        )

    • Adds before_kickoff and after_kickoff crew callbacks for hooking into crew lifecycle events.
    • Supports pre-seeding agents with Knowledge so agents start with domain context before execution begins.
    • Adds Mem0 integration for retrieving user preferences and memories during agent runs.

    3 details in Everything

89. 0.79.0 Nov 10, 2024 · release notes

    CrewAI 0.79.0 adds flow inputs, IBM Watson memory integration, and broader log storage data type support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.79.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.79.0

    └──▷ USE IT
    Build a custom tool using the now top-level BaseTool import rather than reaching into submodules.
    python copy

    from crewai import BaseTool
    
    class MyScanner(BaseTool):
        name: str = "Port Scanner"
        description: str = "Scans open ports on a given host."
    
        def _run(self, host: str) -> str:
            # tool logic here
            return f"Scanning {host}"

    • Adds inputs parameter support to flows, enabling dynamic data to be passed into flow execution.
    • Enhances log storage to support a wider range of data types beyond strings.
    • Moves BaseTool to the main package and centralizes tool description generation, simplifying custom tool authoring.
    • Raises an explicit error when an LLMLLMA 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. returns no response, making silent failures visible.

    4 details in Everything

90. 0.76.9 Oct 30, 2024 · release notes

    CrewAI 0.76.9 adds crewai flow add-crew and updates the flow plot command to crewai flow plot.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.76.9 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.76.9

    └──▷ TRY IT
    Add a new crew to an existing flow without manually editing boilerplate — useful when extending a flow with a parallel or sequential crew.
    copy

    $ crewai flow add-crew

    Visualize your flow's structure to review crew connections and routing logic before deploying.
    copy

    $ crewai flow plot

    • New crewai flow add-crew CLI command lets you scaffold and add additional crews to an existing flow.
    • Flow visualization command updated to crewai flow plot.
    • Forwards install command options to uv sync for more flexible dependency management.
    • Python 3.10 support added via tomli dependency.

    4 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The flow plot command is renamed from its previous form to crewai flow plot; any scripts or docs referencing the old command will break.
91. 0.76.0 Oct 23, 2024 · release notes

    CrewAI 0.76.0 adds unsafe code execution support with Docker install and runtime checks.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.76.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.76.0

92. 0.74.0 Oct 18, 2024 · release notes

    CrewAI 0.74.0 adds model selection and API key submission via CLI, a new Memory Base, and migrates tooling to UV.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.74.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.74.0

    • Migrates the project toolchain from Poetry to UV, with CLI adapted for UV workflows.
    • New CLI capability to select models and submit API keys directly from the command line.
    • Introduces a new Memory Base foundation for agent memory management.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !Project toolchain has migrated from Poetry to UV; existing Poetry-based setups will require migration to continue working.
93. 0.70.1 Oct 11, 2024 · release notes

    CrewAI 0.70.1 adds Flows with a visual debugger, plus new CLI commands for scaffolding flows and tools.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.70.1 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.70.1

    └──▷ TRY IT
    Scaffold a new Flow project to start building multi-step agentic pipelines.
    copy

    $ crewai create flow

    Scaffold a new custom tool ready for implementation and publishing.
    copy

    $ crewai tool create <tool>

    • New Flow feature enables structured, multi-step agentic pipelines.
    • Flow visualizer lets practitioners inspect and debug Flow execution graphs.
    • New crewai create flow command scaffolds a Flow project from the CLI.
    • New crewai tool create <tool> command scaffolds a custom tool from the CLI.
    • Adds Git validations when publishing tools to enforce clean repository state.

    5 details in Everything

94. 0.64.0 Sep 27, 2024 · release notes

    CrewAI 0.64.0 introduces an initial Tools API and raises the default max iterations to 20.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch 0.64.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout 0.64.0

    • Adds an initial Tools API for programmatic tool management.
    • Increases default max iterations from its previous limit to 20, enabling more complex agent reasoning loops out of the box.

    2 details in Everything

95. v0.63.0 Sep 24, 2024 · release notes

    CrewAI v0.63.0 adds a unified LLMLLMA 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. class, custom memory interfaces, and switches the default model to GPT-4o-mini.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.63.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout v0.63.0

    └──▷ USE IT
    Instantiate an agent with the new LLM class to explicitly target a specific model via LiteLLM, decoupling model selection from environment defaults.
    python copy

    from crewai import Agent, LLM
    
    llm = LLM(model="gpt-4o")
    agent = Agent(
        role="Security Analyst",
        goal="Identify vulnerabilities in the provided code.",
        backstory="Expert in application security.",
        llm=llm
    )

    • New LLM class provides a unified interface for interacting with language models via LiteLLM.
    • Supports custom memory interfaces, enabling practitioners to plug in their own memory backends.
    • Changes the default model to GPT-4o-mini.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The default model is now GPT-4o-mini; crews that relied on the previous default model will use GPT-4o-mini after upgrading unless an explicit model is set.
96. v0.60.0 Sep 16, 2024 · release notes

    CrewAI v0.60.0 drops LangChain, rebuilds the executor, and adds o1-model support with new agent controls.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.60.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout v0.60.0

    └──▷ USE IT
    Use CrewAI with an o1-series model that doesn't support system prompts or stop words.
    python copy

    from crewai import Agent
    
    agent = Agent(
        role="Analyst",
        goal="Analyze the dataset",
        backstory="You are a data expert.",
        llm="o1-preview",
        use_system_prompt=False,
        use_stop_words=False
    )

    Cap API usage and prevent runaway agent loops by setting rate limits and a max iteration count.
    python copy

    from crewai import Agent
    
    agent = Agent(
        role="Researcher",
        goal="Find key insights",
        backstory="You are a senior researcher.",
        max_rpm=10,
        max_iter=5
    )

    • Removes LangChain dependency with a fully rebuilt internal executor for improved reliability.
    • New use_system_prompt flag on Agent lets you disable system prompts for models that don't support them.
    • New use_stop_words flag on Agent allows disabling stop words to support o1-series models.
    • Adds configurable max requests per minute at the crew/agent level.
    • Adds a configurable maximum number of iterations before an agent is forced to produce a final answer.

    +3 more show less

    • New token calculation flow for accurate usage tracking across agent runs.
    • New logging of crew and agent execution for improved observability.
    • sliding_context_window is renamed to respect_context_window and is now enabled by default.

    8 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The sliding_context_window setting is renamed to respect_context_window; any existing config or code referencing sliding_context_window will break.
    • !Delegation is now disabled by default; crews that relied on agents delegating tasks without explicit configuration will stop delegating on upgrade.
97. v0.55.2 Sep 13, 2024 · release notes

    CrewAI v0.55.2 adds auto-complete, enriched TaskOutput fields, new install/deploy CLIs, and Pipeline cleanup.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.55.2 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout v0.55.2

    └──▷ TRY IT
    Set up a new CrewAI project and its dependencies in one step.
    copy

    $ crewai install

    Deploy a CrewAI project to a hosted environment after building it locally.
    copy

    $ crewai deploy

    Inspect the name and expected output of a completed task result for downstream processing or logging.
    python copy

    result = crew.kickoff()
    for task_output in result.tasks_output:
        print(task_output.name, task_output.expected_output)

    • Adds auto-complete support for CrewAI inputs.
    • Adds name and expected_output fields to TaskOutput for richer task result inspection.
    • New crewai install CLI command for streamlined project setup.
    • New crewai deploy CLI command to deploy CrewAI projects.
    • Cleans up and stabilizes the Pipeline feature.

    5 details in Everything

98. v0.51.0 Aug 11, 2024 · release notes

    CrewAI v0.51.0 adds crew testing/evaluation, pipelines, four new tools (Vision, DALL-E, MySQL, NL2SQL), and a sliding context windowcontext windowThe 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..

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.51.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout v0.51.0

    └──▷ USE IT
    Assign a cheaper or faster LLMLLMA 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. specifically to the planning step so your expensive model is reserved for agent execution.
    python copy

    from crewai import Crew, Agent, Task, Process
    from langchain_openai import ChatOpenAI
    
    planner_llm = ChatOpenAI(model="gpt-4o-mini")
    
    crew = Crew(
        agents=[...],
        tasks=[...],
        process=Process.sequential,
        planning=True,
        planning_llm=planner_llm
    )
    crew.kickoff()

    Give agents the ability to generate images on demand during a workflow using the new DALL-E Tool.
    python copy

    from crewai_tools import DallETool
    from crewai import Agent
    
    image_agent = Agent(
        role="Image Creator",
        goal="Generate visuals from descriptions",
        backstory="You create images for marketing campaigns.",
        tools=[DallETool()]
    )

    Enable natural-language database querying so agents can answer data questions without writing SQL manually.
    python copy

    from crewai_tools import NL2SQLTool
    from crewai import Agent
    
    db_agent = Agent(
        role="Data Analyst",
        goal="Answer business questions from the database",
        backstory="You query databases using plain English.",
        tools=[NL2SQLTool(db_uri="mysql+pymysql://user:pass@host/dbname")]
    )

    • Adds crew testing and evaluation framework for assessing crew performance.
    • Introduces Pipeline structure for composing multi-crew workflows.
    • Adds sliding context window to manage long-running agent context automatically.
    • Supports setting a dedicated LLM for the planning step, separate from agent LLMsLLMsA 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..
    • New crew run CLI command for executing CrewAI projects.

    +8 more show less

    • Allows all agent/task attributes to be defined in YAML project configuration.
    • New Vision Tool for enabling agents to process and reason about images.
    • New DALL-E Tool for generating images from within agent workflows.
    • New MySQL Tool for querying MySQL databases from agents.
    • New NL2SQL Tool for translating natural language queries into SQL.
    • File-saving now serializes dict outputs as JSON when writing to disk.
    • Enables verbose settings for tool outputs to aid in debugging and observability.
    • Adds new GitHub project templates for bootstrapping CrewAI projects.

    13 details in Everything

99. v0.41.0 Jul 19, 2024 · release notes

    CrewAI v0.41.0 adds crew planning, task replay, memory reset, LLMLLMA 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. retry, and type-safe outputs.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.41.0 https://github.com/crewAIInc/crewAI.git
    # already have the repo? check out this version:
    $ git checkout v0.41.0

    └──▷ USE IT
    Enable pre-execution planning so your crew deliberates a strategy before assigning tasks — useful for complex, multi-step investigations.
    python copy

    from crewai import Crew
    
    crew = Crew(
        agents=[...],
        tasks=[...],
        planning=True
    )
    result = crew.kickoff()

    Replay from a specific failed task after a partial run, without restarting the entire crew from scratch.
    copy

    $ crewai replay <task_id>

    Clear stale crew memory before re-running to ensure the crew starts fresh without prior context contaminating results.
    copy

    $ crewai reset-memory

    • Adds planning=True to Crew instances so crews reason through a plan before executing tasks.
    • Introduces a CLI replay feature to list tasks from the last run and re-execute from a specific task.
    • Enables resetting crew memory before a run via a new reset-memory capability.
    • Adds LLM call retry support so a failed LLM call no longer halts crew execution.
    • All crews and tasks now return typed CrewOutput and TaskOutput objects instead of raw strings.

    +3 more show less

    • Adds ability to customize the output converter on agents/tasks.
    • Enhances tools with type hinting and new attributes.
    • Adds MultiON Tool integration.

    8 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !All crews and tasks now return TaskOutput and CrewOutput objects instead of plain strings — code that treats crew/task return values as strings will break.
100. v0.36.0 Jul 6, 2024 · release notes

     CrewAI v0.36.0 adds AgentOps native support, Firecrawl Tools, and tool-result-as-agent-result capability

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.36.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.36.0

     • Adds native AgentOps integration for agent observability and monitoring.
     • Adds Firecrawl Tools for web scraping and crawling within CrewAI agents.
     • Adds the ability to return a tool's result directly as an agent result.
     • Improves the coding Interpreter tool.
     • Adds the ability to create a custom converter class.

     5 details in Everything

101. v0.35.0 Jun 29, 2024 · release notes

     CrewAI v0.35.0 adds code execution for agents, third-party agent integration, and a new crewai train CLI command.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.35.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.35.0

     └──▷ TRY IT
     Train your crew for a fixed number of iterations before a production run to improve output consistency.
     copy

     $ crewai train -n 5

     • New crewai train -n <X> CLI command lets you train a crew for a specified number of iterations before execution to produce more consistent results.
     • Agents can now execute code directly as part of a crew workflow.
     • Supports integrating third-party agents — including LlamaIndex, LangChain, and Autogen agents — as first-class crew members.

     3 details in Everything

102. v0.32.0 Jun 21, 2024 · release notes

     CrewAI v0.32.0 adds async and per-item kickoff methods, LlamaIndex hub support, and usage metrics on crew output.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.32.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.32.0

     └──▷ USE IT
     Run the same crew independently for each item in a list — useful for processing multiple targets in parallel without managing async yourself.
     python copy

     results = my_crew.kickoff_for_each(inputs=[{"target": "host1"}, {"target": "host2"}, {"target": "host3"}])

     Kick off a long-running crew without blocking — lets you launch a crew and continue other work while it runs.
     python copy

     import asyncio
     
     async def main():
         result = await my_crew.kickoff_async(inputs={"target": "host1"})
         print(result)
     
     asyncio.run(main())

     Inspect token consumption after a crew run to track LLMLLMA 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. costs per execution.
     python copy

     result = my_crew.kickoff(inputs={"target": "host1"})
     print(result.usage_metrics)

     • Adds kickoff_for_each, kickoff_async, and kickoff_for_each_async methods to the crew kickoff API for parallel and per-item execution control.
     • Adds usage_metrics field to full crew output, exposing token and resource consumption data.
     • Adds support for all LlamaIndex hub integrations as crew tools.
     • Adds support for multiple crews in the new YAML format.
     • Changes the default LLM model to gpt-4o.

     +1 more show less

     • Adds timestamps to log output.

     6 details in Everything

     └──▷ BREAKING ON UPGRADE

     • !The default model is now gpt-4o; crews that relied on the previous default model will switch automatically on upgrade.
103. v0.30.4 May 13, 2024 · release notes

     CrewAI v0.30.4 adds manager agent override, prompt/response templates for OSSOSSOpen-source software: code whose licence permits anyone to inspect, modify, and redistribute it. Cyber tools build on it to reuse auditable libraries without licensing fees. models, and Browserbase and Exa Search tools.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.30.4 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.30.4

     • Adds ability to designate a specific agent as crew manager instead of having the crew auto-generate one.
     • Adds system, prompt, and response templates so practitioners can tune LLMLLMA 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. interaction for open-source and smaller models.
     • Adds initial support for bringing your own prompts to override built-in crew prompts.
     • Adds two new built-in tools: Browserbase and Exa Search.
     • Improves JSON and Pydantic output handling for better compatibility with smaller models.

     +2 more show less

     • Improves tool name recognition for better compatibility with smaller models.
     • Adds ability to automatically create a directory when saving output as a file.

     7 details in Everything

     └──▷ BREAKING ON UPGRADE

     • !Dependencies have been updated — verify your tool integrations after upgrading.
104. v0.27.0 Apr 4, 2024 · release notes

     CrewAI v0.27.0 adds shared crew memory, native human input, universal RAGRAGRetrieval-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. tool support, and custom cache control.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.27.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.27.0

     └──▷ USE IT
     Enable shared crew memory so agents retain context across tasks, improving consistency in multi-step workflows.
     python copy

     crew = Crew(
         agents=[researcher, writer],
         tasks=[research_task, write_task],
         memory=True
     )

     Use a custom cache function on a tool to control exactly when results are cached, e.g. skipping cache for volatile data.
     python copy

     from crewai_tools import tool
     
     @tool
     def my_tool(query: str) -> str:
         ...
     
     my_tool.cache_function = lambda args, result: 'volatile' not in args['query']

     • Adds memory=True parameter to crew configuration to enable shared crew memory, improving outcome reliability (disabled by default).
     • Adds cache_function attribute to tools for custom caching logic per tool invocation.
     • Adds native human input support, allowing agents to pause and request input from a human during execution.
     • Extends RAG tools support to any embedding modelembedding modelLists 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. and provider, no longer limited to OpenAI.
     • Adds cross-agent delegation, enabling smoother cooperation and task handoff between agents.

     5 details in Everything

105. v0.22.0 Mar 11, 2024 · release notes

     CrewAI v0.22.0 adds a crewai create CLI command and dictionary-based agent/task definitions.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.22.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.22.0

     └──▷ TRY IT
     Bootstrap a new CrewAI project scaffold from the command line.
     copy

     $ crewai create

     Define an agent using a dictionary instead of a class instance, useful for dynamic or config-driven crew setups.
     python copy

     from crewai import Agent, Task, Crew
     
     agent = Agent(**{
         "role": "Researcher",
         "goal": "Find the latest AI news",
         "backstory": "You are an expert at finding information."
     })
     
     task = Task(**{
         "description": "Search for the top 5 AI news stories today",
         "agent": agent
     })

     • Adds crewai create CLI command for bootstrapping new CrewAI projects from the command line.
     • Enables agents and tasks to be defined using Python dictionaries as an alternative to class-based definitions.
     • Adds clearer agent logging output to improve observability during crew execution.

     3 details in Everything

106. v0.19.0 Mar 4, 2024 · release notes

     CrewAI v0.19.0 adds execution metrics, input passing at kickoff, and function-callingfunction-callingA 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. LLMLLMA 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. fallback for agents and crews.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.19.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.19.0

     └──▷ USE IT
     After a crew run, inspect tool usage metrics to audit how many tools were called and where errors occurred.
     python copy

     result = crew.kickoff(inputs={'domain': 'example.com'})
     print(crew.usage_metrics)

     Fall back to function-calling mode on an agent when the default tool-use strategy is unreliable with your LLM.
     python copy

     agent = Agent(
         role='Analyst',
         llm=my_llm,
         function_calling_llm=my_function_llm,
         tools=[my_tool]
     )

     • Adds function_calling_llm parameter on Agent or Crew to fall back to function calling when standard tool usage fails.
     • Adds crew.usage_metrics to retrieve execution metrics after a kickoff call, exposing tool usage statistics.
     • Adds inputs parameter to crew.kickoff(inputs={'key': 'value'}) so runtime values can be injected at execution time.
     • Enhances delegation capabilities for agents within a crew.

     4 details in Everything

107. v0.16.0 Feb 28, 2024 · release notes

     CrewAI v0.16.0 adds inputs interpolation and telemetry for tools usage, errors, and token tracking.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.16.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.16.0

     • Adds initial support for inputs interpolation, enabling dynamic input substitution in crew workflows.
     • Adds ability to track tools usage, tools errors, formatting errors, and token usage within crew runs.

     2 details in Everything

     └──▷ BREAKING ON UPGRADE

     • !The crewai_tools dependency has been removed; any setup relying on it will break on upgrade.
108. v0.14.0rc0 Prerelease Feb 20, 2024 · release notes

     CrewAI v0.14.0rc0 adds crewai-tools integration, Pydantic/JSON task output formatting, and file output support.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.14.0rc0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.14.0rc0

     • Adds support for crewai-tools integration.
     • Adds support for formatting task output as Pydantic objects or JSON.
     • Adds support for saving task output to a file.
     • Supports tools with no arguments.
     • Revamps tools usage logic to properly use function callingfunction callingA 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..

     +1 more show less

     • Improves reliability for inter-agent delegation.

     6 details in Everything

109. v0.10.0 Feb 10, 2024 · release notes

     CrewAI v0.10.0 adds full task output capture, step callbacks, multi-argument tool support via JSON, and shared caching across agents.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.10.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.10.0

     └──▷ USE IT
     Stream every agent reasoning step in real time — useful for debugging long-running autonomous crews.
     python copy

     def my_callback(step):
         print(step)
     
     agent = Agent(..., step_callback=my_callback)
     crew = Crew(agents=[agent], ..., step_callback=my_callback)

     • Adds full_output return from crew kickoff, exposing all individual task outputs in a single result.
     • Adds step_callback parameter for both Agents and Crews to receive all intermediate reasoning steps during execution.
     • New tool usage internals now use JSON, unlocking support for tools that require multiple arguments.
     • Rebuilt caching structure so multiple agents can share the same cache across a crew run.
     • Adds opt-in sharing of complete crew run data with the crewAI team.

     5 details in Everything

     └──▷ BREAKING ON UPGRADE

     • !Removes CrewAgentOutputParser — any code that imports or references it directly will break on upgrade.
110. v0.5.0 Feb 4, 2024 · release notes

     CrewAI v0.5.0 adds task callbacks, hierarchical process support, task references, and parallel task execution.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.5.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.5.0

     • Adds task callbacks, enabling post-execution hooks on individual tasks.
     • Adds support for a hierarchical process model for structuring agent workflows.
     • Adds the ability to reference specific tasks from within another task.
     • Adds parallel task execution, allowing multiple tasks to run concurrently.

     4 details in Everything

111. v0.1.32 Jan 14, 2024 · release notes

     CrewAI v0.1.32 adds per-agent iteration limits, RPM throttling, and initial i18n support

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.1.32 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.1.32

     • Adds ability to limit the maximum number of iterations for an agent, preventing runaway agent loops.
     • Adds Request Per Minute (RPM) throttling configurable for both individual Agents and Crews.
     • Adds initial internationalization (i18n) support with a Greek translation included.

     3 details in Everything

112. v0.1.14 Dec 30, 2023 · release notes

     CrewAI v0.1.14 adds tool caching, loop execution prevention, verbose logging levels, and pydantic v2 support.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.1.14 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.1.14

     • Adds verbose levels to the logger for finer-grained output control.
     • Adds tool caching to avoid redundant tool calls during agent execution.
     • Adds loop execution prevention to stop agents from cycling indefinitely.
     • Expands delegation guidelines to give agents more precise rules for task hand-off.
     • Updates support to pydantic v2.

     5 details in Everything

     └──▷ BREAKING ON UPGRADE

     • !Upgrades to pydantic v2, which may break existing model definitions that rely on pydantic v1 behaviour.
113. v0.1.1 Nov 19, 2023 · release notes

     CrewAI v0.1.1 adds verbose mode for inspecting task execution in real time.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.1.1 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.1.1

     • Adds Crew verbose mode to inspect tasks as they are being executed.

     1 detail in Everything

114. v0.1.0 Nov 14, 2023 · release notes

     CrewAI v0.1.0 debuts a Python framework for orchestrating collaborative, role-based autonomous AI agents.

     └──▷ GET THIS VERSION

     copy

     $ git clone --branch v0.1.0 https://github.com/crewAIInc/crewAI.git
     # already have the repo? check out this version:
     $ git checkout v0.1.0

     └──▷ USE IT
     Stand up a minimal crew where two specialized agents tackle a research-then-write task sequentially.
     python copy

     from crewai import Agent, Task, Crew, Process
     
     researcher = Agent(
         role='Researcher',
         goal='Find key facts about quantum computing',
         tools=[search_tool]
     )
     
     writer = Agent(
         role='Writer',
         goal='Summarize research into a short briefing',
         tools=[]
     )
     
     research_task = Task(description='Research recent quantum computing breakthroughs', tools=[search_tool])
     write_task    = Task(description='Write a 200-word executive summary', tools=[])
     
     crew = Crew(
         agents=[researcher, writer],
         tasks=[research_task, write_task],
         process=Process.sequential
     )
     
     result = crew.kickoff()
     print(result)

     • Introduces the Agent class for defining autonomous agents with specific roles, goals, and assigned tools.
     • Introduces the Task class for dynamically creating and assigning tasks with per-task tool specifications.
     • Introduces the Crew class for grouping agents and coordinating collaborative workflows.
     • Introduces the Process class supporting sequential task execution for organized, predictable agent pipelines.
     • Enables inter-agent delegation, allowing agents to autonomously redistribute subtasks among team members at runtime.

     5 details in Everything