Strix

No entries match these filters. Clear filters

1. v1.7.0 Oct 5, 2026 · issue 095

   Strix v1.7.0 adds --fail-on severity gating, STRIX_API_TYPE forcing, budget_policy=pause, lazy 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. connections, and an interactive --resume picker.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.7.0 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.7.0

   └──▷ TRY IT
   Fail a CI job automatically when Strix finds any high- or critical-severity vulnerability during a headless scan.
   copy

   $ strix --target ./app-directory --fail-on high

   Force Strix to use the Responses API instead of chat completions when your provider or model requires it.
   copy

   $ export STRIX_API_TYPE=responses
   export STRIX_LLM="openai/gpt-4o"
   export LLM_API_KEY="your-api-key"
   strix --target ./app-directory

   Resume a previous scan interactively when you do not remember the exact run name.
   copy

   $ strix --resume

   • Adds --fail-on flag to the CLI to gate headless exit code on finding severity, enabling CI pipelines to fail on configurable severity thresholds.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠
   • Adds STRIX_API_TYPE environment variable to force the Responses API vs chat completions endpoint, overriding model-based auto-detection.
   • Adds budget_policy=pause to park every agent at the cost limit until the operator explicitly resumes, preventing runaway spend.
   • Adds a structured per-attempt provider request log with provider request IDs 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. call traceability.
   • Adds lazy initialization of MCP connections so connections are not established until actually needed.

   +7 more show less

   • Adds interactive run picker when --resume is supplied with no run name, letting operators choose from prior runs in the terminal.
   • Adds the ability for agents to delete a vulnerability report they previously filed.
   • Requires http_exchange_ids for proxy-validated findings, linking HTTP exchange evidence directly to reported vulnerabilities.
   • Prompts agents to include local Git blame in technical details of findings.
   • Makes read_only local sources become :ro bind mounts in the container runtime.
   • Animates the wait_for_agents indicator 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..
   • Lets the verified user define and change scope interactively in chat.
   • Adds --fail-on flag to the CLI to gate headless exit code on finding severity, enabling CI pipelines to fail on configurable severity thresholds.⁠︀︄︇︀︅︉︀︅︀︀︃︀︀︅︅︀︅︊︀︄︆︀︃︄⁠
   • Adds STRIX_API_TYPE environment variable to force the Responses API vs chat completions endpoint, overriding model-based auto-detection.
   • Adds budget_policy=pause to park every agent at the cost limit until the operator explicitly resumes, preventing runaway spend.
   • Adds a structured per-attempt provider request log with provider request IDs 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. call traceability.
   • Adds the ability for agents to delete a vulnerability report they previously filed.

   7 more in Everything

2. v1.6.2 Sep 5, 2026 · issue 065

   Strix v1.6.2 adds Exa as a web search provider alongside Perplexity and improves error telemetry with phase and exception-class classification.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.6.2 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.6.2

   • Adds Exa as a web search provider alongside Perplexity for agent-driven reconnaissance.
   • Classifies error beacons by phase and exception class in telemetry for richer operational diagnostics.
   • Adds Exa as a web search provider alongside Perplexity for agent-driven reconnaissance.

   1 more in Everything

3. v1.6.1 Sep 2, 2026 · issue 063

   Strix v1.6.1 adds GLM-5.3, Fable 5.1, and Gemini 3.7 Flash to the recommended model list, with openrouter/z-ai/glm-5.3 as the new top pick.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.6.1 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.6.1

   └──▷ TRY IT
   Switch to the new top-pick model for a pentest scan without editing config files.
   copy

   $ export STRIX_LLM="openrouter/z-ai/glm-5.3"
   export LLM_API_KEY="your-api-key"
   strix --target ./app-directory

   • Adds openrouter/z-ai/glm-5.3 as the new top recommended model, with GLM-5.3, Fable 5.1, and Gemini 3.7 Flash added to the recommended model list.
   • 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. call errors no longer quarantine the connection, keeping MCP integrations live after transient failures.

   2 details in Everything

4. v1.6.0 Sep 1, 2026 · issue 062

   Strix v1.6.0 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. server support, a managed cloud CLI, workspace file injection, OWASP LLM Top 10OWASP LLM Top 10A ranked list of the ten most critical security risks specific to large language model applications, maintained by OWASP, giving cyber tool developers a shared taxonomy for prioritizing LLM attack surfaces. 2026 skills, and contextual CVSSCVSSCommon Vulnerability Scoring System, a method for describing a vulnerability's characteristics and severity. Its score is not the probability that attackers will exploit it. dependency reports.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.6.0 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.6.0

   └──▷ TRY IT
   Inject a custom config or seed file into the sandbox so agents can reference it during a pentest without baking it into the target directory.
   copy

   $ strix --target ./my-app --workspace-file ./fixtures/test-users.json

   Expose the scan results viewer on all interfaces at a fixed port when reviewing findings on a remote dev box over SSH.
   copy

   $ strix view my-run-name --host 0.0.0.0 --port 8080 --no-open

   • Adds --workspace-file CLI flag and extra_files config key to place caller-provided files into the sandbox workspace before a scan starts.
   • Adds strix cloud subcommand for the managed platform CLI, covering login, scans, billing, and the full cloud API.
   • Adds update_vulnerability_report agent API so an agent can revise an already-filed finding during a run.
   • Adds --host option to strix view to expose the local results viewer on a custom interface (e.g. --host 0.0.0.0).
   • Adds MCP server support, with connections isolated per task, on-demand tool resolution instead of bulk registration, and connection status surfaced in the UI; connections survive transient transport failures.

   +11 more show less

   • Adds contextual CVSS breakdown and required usage evidence on dependency vulnerability reports.
   • Adds OWASPOWASPA nonprofit foundation that publishes open standards, guides, and ranked vulnerability lists—most famously the OWASP Top 10—giving cyber tools a vendor-neutral benchmark to test or report against. 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. Top 10 2026 skill coverage.
   • Adds Azure and Entra security skill.
   • Adds argument injection security skill.
   • Adds ecosystem supply-chain security skills.
   • Adds Hurl and Hypothesis security playbooks.
   • Adds semantic browser and Electron security skills.
   • Promotes coverage as a first-class artifact with evidence discipline in the agent layer.
   • Hardens CSV injection in report output.
   • Bootstraps Caido concurrently with scan start, reducing scan startup latency.
   • Moves heavy imports off the startup path and pre-warms them in the background, reducing CLI startup time.

   16 details in Everything

5. v1.5.1 Aug 7, 2026 · issue 039

   Strix v1.5.1 expands Firebase Storage rules coverage in its vulnerability scanner.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.5.1 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.5.1

6. v1.5.0 Aug 7, 2026 · issue 038

   Strix v1.5.0 adds LLM_EXTRA_HEADERS, LLM_DISABLE_STREAMING, STRIX_REASONING_EFFORT, API spec/Postman targets, a Go/Bubble Tea 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 richer SCASCASoftware composition analysis, identifying third-party dependencies and checking them for known vulnerabilities and license issues. It covers software a team uses rather than writes itself. reporting.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.5.0 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.5.0

   └──▷ TRY IT
   Route Strix through an 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. gateway that requires a custom auth header, without modifying your API key setup.
   copy

   $ export LLM_EXTRA_HEADERS='{"X-Gateway-Token": "my-gateway-secret"}'
   export STRIX_LLM="openai/gpt-4o"
   export LLM_API_KEY="your-api-key"
   strix --target https://your-app.com

   Scan every endpoint declared in an OpenAPIOpenAPIA vendor-neutral specification for describing REST APIs in a machine-readable format, maintained by the OpenAPI Initiative. Cyber tools use it to auto-generate clients, documentation, and validation from a single source of truth. spec against a live staging server, skipping crawl-based discovery.
   copy

   $ strix --target ./openapi.yaml

   Push the LLM to use maximum reasoning effort on a complex target when using a provider that supports the setting.
   copy

   $ export STRIX_REASONING_EFFORT=max
   strix --target https://your-app.com

   • Adds LLM_EXTRA_HEADERS environment variable to inject custom request headers into any OpenAI-compatible endpoint, enabling use with proxies, gateways, or auth-requiring local models.
   • Adds LLM_DISABLE_STREAMING environment variable as an opt-in flag to disable streaming for OpenAI-compatible endpoints that don't support it.
   • Adds STRIX_REASONING_EFFORT=max config option for providers that expose a reasoning-effort control.
   • Supports API specs (OpenAPI/Swagger) and Postman collections as scan targets, letting agents test every declared endpoint without crawling.
   • Replaces the Python/Textual TUI with a Go/Bubble Tea interface for the interactive terminal UI.

   +7 more show less

   • SCA findings now record the full transitive dependency chain, showing how a vulnerable package is pulled in.
   • SCA findings now include a structured reachability evidence ladder for dependency vulnerabilities, grading confidence from theoretical to exploitable.
   • Dependency CVE findings now require a repo-relative manifest_path field, giving precise location context in reports.
   • Mounts local targets into the sandbox instead of copying them, reducing startup overhead for local directory scans.
   • Credential files are now created with owner-only permissions, hardening local secret storage.
   • Delivers ~10x faster CLI startup via lazy imports.
   • Adds installable SKILL.md skills and AGENTS.md support for extending agent capabilities.

   12 details in Everything

7. v1.4.0 Jul 27, 2026 · issue 027

   Strix v1.4.0 adds self-update, ChatGPT inference, Linux ARM64ARM64The 64-bit instruction set architecture from ARM Holdings, used in modern mobile chips, Apple Silicon, and cloud server CPUs; tools target it to run natively on those platforms without emulation overhead., Bedrock prompt caching, and smarter context management for long scans.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.4.0 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.4.0

   └──▷ TRY IT
   Keep Strix up to date without reinstalling — run this after any release to pull the latest version in place.
   copy

   $ strix --update

   After a scan finishes (Strix no longer auto-opens the viewer), inspect results in the local dashboard.
   copy

   $ strix view my-run-name

   • Adds strix --update command for in-place CLI self-update and automatic update notifications.
   • Supports signing in with a ChatGPT subscription as an inference provider.
   • Adds Linux ARM64 standalone release builds.
   • Enables AWS Bedrock/Anthropic prompt caching for Claude models to reduce latency and cost on repeated context.
   • Adds a dedicated deduplication model to reduce duplicate findings across scan runs.

   +5 more show less

   • Adds list_reports and get_report read-only tools for programmatic report access.
   • Introduces model-aware conversation compaction to keep long scans within context limits.
   • Bounds per-tool output before it enters agent history, and spills oversized output to the sandbox workspace instead of dropping it.
   • Adds graduated wrap-up warnings, a budget reserve, and an interactive budget pause/continue flow during scans.
   • CLI now exits after a scan completes instead of launching a local viewer — use strix view to open results separately.

   10 details in Everything

   └──▷ BREAKING ON UPGRADE

   • !Strix now quits after a scan completes instead of hosting a local viewer — workflows that relied on the viewer launching automatically must now run strix view separately.
8. v1.3.0 Jul 22, 2026 · issue 023

   Strix v1.3.0 adds a Feedback & support tab and a prominent scan switcher with pentest terminology to the local viewer UI.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.3.0 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.3.0

   • Adds a Feedback & support tab to the local viewer UI.
   • Adds a prominent scan switcher to the local viewer with renamed pentest terminology.
   • Shrinks the sandbox Docker image from 7.2 GB to 3.8 GB via cache cleanup, multi-stage Go build, and dropping ZAP — enabling use on disk-constrained environments.

   3 details in Everything

9. v1.2.0 Jul 21, 2026 · issue 022

   Strix v1.2.0 adds recon asset-discovery skill, AD/KerberosKerberosA network authentication protocol that uses tickets issued by a trusted service. Users and services can prove their identities without sending a password to each application. testing, Docker resource limits, shared-network port resolution, and a local run viewer with email reports.

   └──▷ GET THIS VERSION

   copy

   $ git clone --branch v1.2.0 https://github.com/usestrix/strix.git
   # already have the repo? check out this version:
   $ git checkout v1.2.0

   • Adds a recon asset-discovery skill for automated attack surfaceattack surfaceThe exposed systems, interfaces and access points an attacker could try to use. It includes internet-facing services as well as identities, software and other reachable resources. enumeration.
   • Adds an Active DirectoryActive DirectoryMicrosoft's directory service for Windows networks that centralises authentication and authorisation; cyber tools target or integrate with it because it controls identity and access across most enterprise environments. / Kerberos domain testing skill for enterprise network assessments.
   • Adds a Grafana/Prometheus observability pivot skill to identify exposed monitoring infrastructure.
   • Enables opt-in resource limits (CPUCPUThe main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware./memory) for Docker sandbox containers to cap agent resource usage.
   • Introduces a local run viewer with email report delivery, run history, and access to the full platform suite.

   5 details in Everything

10. v1.1.0 Jul 14, 2026 · issue 020

    Strix v1.1.0 adds 9 new security skills, SARIF 2.1.0SARIF 2.1.0A JSON-based file format, standardized by OASIS, for expressing static analysis results so that cyber tools from different vendors can share findings through a single, machine-readable schema. output, budget controls, and multi-target list scanning.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v1.1.0 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v1.1.0

    └──▷ TRY IT
    Scan a list of targets (e.g., all apps in scope for a bug-bounty engagement) from a file rather than passing each on the command line.
    copy

    $ strix --target-list ./targets.txt

    • Adds weak-password detection and 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. prompt-injectionprompt-injectionAn attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. security skills.
    • Adds GCP and Auth0 reconnaissance skills.
    • Adds five new security skills covering OAuth, AWS, prototype pollution, deserializationdeserializationTurning stored or transmitted data back into objects a program can use. Unsafe handling of untrusted data can allow unexpected behavior or code execution., and Django.
    • Adds skill-directory registration for extending the skill set.
    • Emits SARIFSARIFStatic Analysis Results Interchange Format, a standard for sharing code-analysis findings, including locations and rule details. It lets scanners report results to a common review interface. 2.1.0 output for GitHub code-scanning and ASPMASPMApplication security posture management, combining findings about applications from multiple tools and relating them to business context. It helps teams decide which fixes matter most. ingestion.

    +10 more show less

    • Tags SARIF rules with STRIDE categories derived from CWECWECommon Weakness Enumeration, a catalog of recurring software and hardware weakness types. It describes classes of mistakes, such as injection, rather than individual vulnerability instances. mappings.
    • Adds --max-budget-usd flag to cap token/cost spend per scan.
    • Adds bind-mount option to handle large target repositories without copying them into the sandbox.
    • Adds --target-list CLI option to supply multiple targets from a file.
    • Adds new dependency reporting fields and requires advisory_cvss for dependency findings, with a new SCASCASoftware composition analysis, identifying third-party dependencies and checking them for known vulnerabilities and license issues. It covers software a team uses rather than writes itself. 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. renderer.
    • Adds force_required_tool_choice setting for finer LLM 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. control.
    • Warns when the configured LLM is not a recommended or frontier model.
    • Routes ollama models through ollama_chat provider so tool calling works correctly.
    • Reports cost for streamed 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. calls and attributes OpenRouter usage to the Strix app.
    • Adds TUI More content available hint for long views and throttled refresh with render caching to reduce scroll stutter.

    15 details in Everything

11. v1.0.3 Jun 9, 2026 · release notes

    Strix v1.0.3 adds LiteLLM cost visibility, 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. status updates, and registry-gated reasoning.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v1.0.3 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v1.0.3

    • reasoning_effort is now gated by the LiteLLM model registry; effort parameters are only sent when the underlying model supports them
    • Use observed LiteLLM cost for LiteLLM-routed calls instead of estimated costs

    2 details in Everything

12. v1.0.0 May 26, 2026 · release notes

    Strix v1.0.0 adds native 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., save/resume, multi-agent control, new skills and providers

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v1.0.0 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v1.0.0

    • Enables save and resume workflow for long-running agent sessions
    • Adds native tool calling capability for integrated cyber tooling
    • Supports multi-agent control workflows
    • Adds Kubernetes security testing skill
    • Adds NoSQL injection vulnerability skill

    +2 more show less

    • Adds SSTISSTIServer-Side Template Injection, a vulnerability class where attacker-controlled input is evaluated by a server-side template engine, enabling remote code execution or data exfiltration. and Header Injection vulnerability skills
    • Adds Novita AI 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

    7 details in Everything

13. v0.8.3 Mar 23, 2026 · release notes

    Strix v0.8.3 adds NestJS skills, interactive agent loop mode, and OpenTelemetryOpenTelemetryAn open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tracing support.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.8.3 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.8.3

    • feat(skills): adds a NestJS security testing module for skill-based scanning
    • feat: adds interactive mode for the agent loop to allow manual stepping through prompts

    2 details in Everything

14. v0.8.2 Feb 24, 2026 · release notes

    Strix v0.8.2 exposes the Caido proxy port for 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. workflows.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.8.2 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.8.2

15. v0.8.0 Feb 19, 2026 · release notes

    Strix v0.8.0 adds mouse text selection auto-copy in 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 nested XML vulnerability reports

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.8.0 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.8.0

    • Adds mouse text selection auto-copy to clipboard in the terminal UI (TUI)
    • Redesigns vulnerability reporting output to include nested XML code locations and CVSSCVSSCommon Vulnerability Scoring System, a method for describing a vulnerability's characteristics and severity. Its score is not the probability that attackers will exploit it. scores

    2 details in Everything

16. v0.7.0 Jan 23, 2026 · release notes

    Strix v0.7.0 adds --config for .env overrides and migrates skills to Markdown

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.7.0 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.7.0

    • Accepts --config flag to override .env variables at runtime
    • Skills now use Markdown format instead of Jinja templates

    2 details in Everything

17. v0.6.0 Jan 12, 2026 · release notes

    Strix v0.6.0 adds STRIX_REASONING_EFFORT env var, 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. deduplication, persistent config to ~/.strix/cli-config.json, and a live 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. panel

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.6.0 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.6.0

    • STRIX_REASONING_EFFORT environment variable controls reasoning depth and latency/quality tradeoffs for agents.
    • LLM-based vulnerability deduplication detects semantically similar findings and merges them into a single canonical entry.
    • Centralized configuration persists settings to ~/.strix/cli-config.json across sessions.

    3 details in Everything

    └──▷ BREAKING ON UPGRADE

    • !The --run-name CLI argument has been removed.
18. v0.5.0 Dec 15, 2025 · release notes

    Strix v0.5.0 adds configurable scan modes, a standalone binary installer, and an agent todo tool

    └──▷ GET THIS VERSION

    copy

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

    └──▷ USE IT
    Run a fast scan focused on recent changes for CI/CD pipelines
    shell copy

    strix --scan-mode quick

    Install Strix as a standalone binary without Python dependencies
    shell copy

    curl -sSL https://strix.ai/install | bash

    • --scan-mode CLI flag with quick, standard, and deep options for controlling scan depth
    • Standalone binary installation via the curl -sSL https://strix.ai/install | bash one-liner
    • Agent todo system allowing tasks to be tracked as pending or done

    3 details in Everything

19. v0.4.0 Nov 25, 2025 · release notes

    Strix v0.4.0 adds --instruction file support, real-time result persistence to disk, live stats panel, and IP scanning

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.4.0 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.4.0

    └──▷ USE IT
    Run a pentest using instructions defined in an external YAML file rather than a long CLI string.
    shell copy

    strix scan --instruction ./pentest_instructions.yaml

    Scan a raw IP address directly when the target has no hostname or DNS record.
    shell copy

    strix scan 192.168.1.50

    • Adds --instruction flag to accept file-based pentest configs instead of CLI strings
    • Enables real-time results persistence: findings are written to disk as they are discovered
    • Adds a live agent stats panel (vulnerabilities, tokens, cost, active agents) in both 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 CLI
    • Adds IP address scanning support for targets not fronted by hostnames
    • Adds prompt modules for Open Redirect, Subdomain Takeover, and Info Disclosure

    5 details in Everything

20. v0.3.1 Nov 1, 2025 · release notes

    Strix v0.3.1 adds headless CLI mode via --non-interactive, multi-target scanning, and per-severity findings summary.

    └──▷ GET THIS VERSION

    copy

    $ git clone --branch v0.3.1 https://github.com/usestrix/strix.git
    # already have the repo? check out this version:
    $ git checkout v0.3.1

    └──▷ TRY IT
    Run Strix in CI/CD without an interactive REPL and fail the pipeline if vulnerabilities are detected.
    copy

    $ strix --non-interactive --target https://example.com

    Scan multiple components (a local repo and a staging API) simultaneously to perform a full-stack assessment.
    copy

    $ strix --target ./my-repo --target https://staging-api.example.com

    • Adds --non-interactive flag to run Strix in headless mode for automation and CI/CD integration
    • Enables multi-target scanning to assess repos, URLs, and APIs in a single execution
    • Includes color-coded per-severity vulnerability counts in the completion panel
    • Increases default agent max_iterations limit from prior version to 300

    4 details in Everything