Strix

The open-source AI pentesting tool. Autonomous AI hackers that find and fix your app’s vulnerabilities.

Strix Overview

Strix are autonomous AI penetration testing agents that act just like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proofs-of-concept. Built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools.

Key Capabilities:

• Full pentesting toolkit - reconnaissance, exploitation, and validation out of the box

• Multi-agent orchestration - teams of AI pentesters that collaborate and scale

• Real exploit validation - working PoCs, not false positives like legacy vulnerability scanners

• Developer‑first CLI - actionable findings with remediation guidance

• Auto‑fix & reporting - generate patches and compliance-ready pentest reports

Related MCP server: Kali MCP Server

Use Cases

• Application Security Testing - Detect and validate critical vulnerabilities in your applications

• Rapid Penetration Testing - Get penetration tests done in hours, not weeks, with compliance reports

• Bug Bounty Automation - Automate bug bounty research and generate PoCs for faster reporting

• CI/CD Integration - Run tests in CI/CD to block vulnerabilities before reaching production

🤖 Agentic Mode (OpenCode — no LLM keys for Strix)

Run Strix's full pentest muscle directly out of OpenCode: the OpenCode agent (the model you already configured there) becomes the pentest brain, and Strix's Kali sandbox is exposed as its hands over MCP. Strix itself needs zero API keys — nmap, sqlmap, ffuf, chromium and friends run in the sandbox container, driven by plain MCP tool calls.

One-command setup

powershell -ExecutionPolicy Bypass -File setup.ps1 -SeedTestSite

That script verifies Docker, creates the Python venv, pulls the sandbox image (ghcr.io/usestrix/strix-sandbox), registers the MCP server in the project's opencode.json, and (with -SeedTestSite) starts a legal local pentest target (OWASP Juice Shop) on http://localhost:4321.

Run a scan

Open this folder in OpenCode and type:

/runscan http://localhost:4321

The pentest agent (.opencode/agents/pentest.md) will:

1. health-check the sandbox (strix_sandbox_health),

2. recon + map the target (strix_sandbox_exec: nmap, curl, httpx, katana...),

3. create its own account through the real UI (strix_browser → Chromium) if the app requires one, using throwaway credentials,

4. probe for vulnerabilities, capture evidence, and record each finding with strix_report_finding,

5. write strix_runs/runscan-*/penetration_test_report.md and hand you a summary.

Point it at your own site only when you are authorized to test it.

How the pieces fit

OpenCode agent (your selected model)          this repo / MCP          Docker
─────────────────────────────────            ───────────────          ──────
/runscan <target>  ─►  pentest agent  ─►  strix_sandbox_exec ─►  Kali sandbox container
                        (brain, no keys)  strix_browser            (nmap, sqlmap, chromium,
                                          strix_report_finding      Caido proxy...)
                                          strix_finish_report  ─►  strix_runs/runscan-*/report.md

Files: mcp/server.py (the MCP stdio server — tools: sandbox_health, sandbox_exec, sandbox_write_file, sandbox_read_file, browser, report_finding, finish_report, sandbox_stop), .opencode/agents/pentest.md (the brain), .opencode/commands/runscan.md (the slash command), mcp/smoke_test.py (transport smoke test).

🚀 Quick Start

Prerequisites:

• Docker (running)

• An LLM API key from any supported provider (OpenAI, Anthropic, Google, etc.)

Installation & First Scan

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

# One-time guided setup: pick a model, paste your key (masked), verify the
# connection, and everything is saved for every future run
strix setup

# Run your first security assessment — URL, directory, or code
strix --target https://your-app.com

No env exports or config files required: strix setup writes ~/.strix/cli-config.json, and future scans are a single command. Prefer the explicit form (great for CI)? Set everything on the command line:

strix --target ./app-directory --llm "openrouter/z-ai/glm-5.3" --api-key "your-api-key"

While a scan runs, a live dashboard in your terminal shows every agent, what it is doing right now, the shared plan (steps remaining), findings as they are filed, and tokens/cost so far.

Free-tier providers run out of quota mid-scan? Add a failover chain in the same strix setup pass (or re-run it): when the main provider hits a wall, Strix switches to the next backup automatically and keeps scanning. See Free-quota failover chain below.

Updating

# Self-update the standalone binary to the latest release
strix --update

# ...or re-run the installer
curl -sSL https://strix.ai/install | bash

Installed with pipx, uv, or pip? strix --update prints the matching upgrade command instead (pipx upgrade strix-agent, uv tool upgrade strix-agent, pip install --upgrade strix-agent). Strix also shows a notice with the right command when a new version is available.

Ways to Run Strix

• Open Source - free, runs locally with Docker and your own LLM key. Quick Start

• Strix Cloud - no setup, validated findings, one-click autofix, and PR reviews. Run a pentest →

• Enterprise - SSO, compliance-ready reports, VPC or self-hosted deployment. Try Strix Enterprise →

☁️ Strix Cloud

Try the Strix full-stack penetration testing platform at app.strix.ai - sign up for free, connect your repos and domains, and launch a pentest in minutes.

• Validated findings with PoCs - every vulnerability includes a working proof-of-concept exploit and reproduction steps

• One-click autofix - AI-generated security patches as ready-to-merge pull requests

• Continuous pentesting - always-on vulnerability scanning that keeps pace with your deployments

• DevSecOps integrations - GitHub, GitLab, Bitbucket, Slack, Jira, Linear, and CI/CD pipelines

• Continuous learning - AI that builds on past findings, adapts to your codebase, and reduces false positives over time

Run a pentest →

🏢 Enterprise

Get the same Strix experience with enterprise-grade controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support and SLA, custom deployment options (VPC or self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment.

Try Strix Enterprise →

🤖 Use Strix from Your Coding Agent

Strix is agent-ready. Give Claude Code, Cursor, Codex, or any SKILL.md-compatible agent the ability to run pentests, fix findings, and set up CI scanning:

npx skills add usestrix/strix

This installs nine skills for running pentests, fixing findings, and CI scanning, against code, web apps, APIs, and the OWASP Top 10. Agents can use the local CLI or the managed cloud with the same engine.

See AGENTS.md for the quick reference, docs.strix.ai/llms.txt for the CLI, and docs.app.strix.ai for the API.

✨ Features

Agentic Pentesting Tools

Strix agents come equipped with a comprehensive offensive security toolkit - the same tools used by professional penetration testers and ethical hackers:

• HTTP Interception Proxy - Full request/response manipulation and analysis with Caido

• Browser Exploitation - Automated browser for testing XSS, CSRF, clickjacking, and auth bypass flows

• Shell & Command Execution - Interactive terminal for exploit development and post-exploitation

• Custom Exploit Runtime - Python sandbox for writing and validating proof-of-concept exploits

• Reconnaissance & OSINT - Automated attack surface mapping, subdomain enumeration, and fingerprinting

• Static & Dynamic Code Analysis - SAST + DAST capabilities for comprehensive application security testing

• Vulnerability Knowledge Base - Structured findings with CVSS scoring and OWASP classification

Comprehensive Vulnerability Scanner

Strix identifies, validates, and exploits a wide range of security vulnerabilities across the OWASP Top 10 and beyond:

• Broken Access Control - IDOR, privilege escalation, auth bypass

• Injection Attacks - SQL injection, NoSQL injection, OS command injection, SSTI

• Server-Side Vulnerabilities - SSRF, XXE, insecure deserialization, RCE

• Client-Side Attacks - XSS (stored/reflected/DOM), prototype pollution, CSRF

• Business Logic Flaws - Race conditions, payment manipulation, workflow bypass

• Authentication & Session - JWT attacks, session fixation, credential stuffing vectors

• Infrastructure & Cloud - Misconfigurations, exposed services, cloud security issues

• API Security - Broken authentication, mass assignment, rate limiting bypass

Graph of Agents (Multi-Agent Pentesting)

Advanced multi-agent orchestration for comprehensive automated penetration testing:

• Distributed Pentesting - Specialized AI agents for recon, exploitation, and post-exploitation

• Scalable Security Testing - Parallel execution across multiple targets for fast, comprehensive coverage

• Dynamic Coordination - Agents share discoveries, chain vulnerabilities, and collaborate like a red team

🖥️ Local Web Viewer

Every scan writes its results to disk as it runs. Bring them up in a local dashboard with a single command:

# Open the most recent run
strix view

# ...or open a specific run by name
strix view my-run-name

# Expose the viewer on all IPv4 interfaces at a fixed port
strix view --host 0.0.0.0 --port 8080 --no-open

The dashboard shows the findings, a live map of the agent team, and past runs. Nothing leaves your machine, and the UI ships prebuilt. strix view binds to 127.0.0.1 and prints a tokened link that grants access to the run, so share it carefully.

See the viewer documentation for the options and for reaching the viewer from another machine.

Usage Examples

Basic Usage

# Scan a local codebase
strix --target ./app-directory

# Security review of a GitHub repository
strix --target https://github.com/org/repo

# Black-box web application assessment
strix --target https://your-app.com

API Testing (OpenAPI / Swagger / Postman)

Point Strix at an API contract and it tests every declared endpoint instead of having to discover them by crawling. Pair the spec with the live base URL so the agent knows where to send traffic:

# OpenAPI / Swagger file, Postman export, or a live collection by id
strix --target ./openapi.yaml --target https://api.your-app.com
strix --target postman://<collection-uuid> --target https://api.your-app.com

Advanced Testing Scenarios

# Grey-box authenticated testing
strix --target https://your-app.com --instruction "Perform authenticated testing using credentials: user:pass"

# Multi-target testing (source code + deployed app)
strix -t https://github.com/org/app -t https://your-app.com

# Targets from a file, one target per non-empty, non-comment line
strix --target-list ./targets.txt

See the CLI reference for every option, including scan modes, diff scope, instruction files, and budgets.

Headless Mode

Run Strix programmatically without interactive UI using the -n/--non-interactive flag - perfect for servers and automated jobs. The CLI prints real-time vulnerability findings and the final report before exiting. Exits with non-zero code when vulnerabilities are found.

strix -n --target https://your-app.com

CI/CD (GitHub Actions)

Strix can be added to your pipeline to run a security test on pull requests with a lightweight GitHub Actions workflow:

name: strix-penetration-test

on:
  pull_request:

jobs:
  security-scan:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v6
        with:
          fetch-depth: 0

      - name: Install Strix
        run: curl -sSL https://strix.ai/install | bash

      - name: Run Strix
        env:
          STRIX_LLM: ${{ secrets.STRIX_LLM }}
          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}

        run: strix -n -t ./ --scan-mode quick

Configuration

export STRIX_LLM="openrouter/z-ai/glm-5.3"
export LLM_API_KEY="your-api-key"

# Optional
export LLM_API_BASE="your-api-base-url"  # if using a local model, e.g. Ollama, LMStudio

Free-quota failover chain

A scan can outlive a provider's free quota. Configure sticky failover backups so the scan continues on the next provider instead of stopping:

strix setup    # answer "y" to "Set up a failover chain?" and paste the backup keys

• Presets cover gemini/gemini-2.5-flash (AI Studio free tier) and groq/llama-3.3-70b-versatile (Groq free tier); option 3 accepts any OpenAI-compatible endpoint (custom base URL), e.g. https://api.tokenrouter.com/v1.

• Every entry is verified with one real round-trip before it is saved; dead keys are dropped.

• A provider is switched away from when it keeps rate-limiting (3 consecutive failures inside 5 minutes) or immediately on an auth/billing error. The switch is sticky for the rest of the scan and the dashboard prints it live.

• The chain resets on the next run, so the primary is retried first again.

Equivalent env/config form (STRIX_FALLBACK_LLMS, saved to ~/.strix/cli-config.json by the wizard):

export STRIX_FALLBACK_LLMS='[{"model": "gemini/gemini-2.5-flash", "api_key": "your-key"}, {"model": "groq/llama-3.3-70b-versatile", "api_key": "your-key"}]'

Sign in with a ChatGPT subscription

Instead of a metered API key, you can run Strix on your ChatGPT Plus/Pro subscription:

strix auth login chatgpt             # sign in with your ChatGPT account
export STRIX_LLM="chatgpt/gpt-5.4"   # chatgpt/<model> runs on the subscription
strix auth status                    # show the active sign-in, or logout to forget it

Use the managed platform: strix cloud

Run scans on app.strix.ai from the terminal, without Docker or an LLM key:

strix cloud login                                  # browser sign-in, one credential per install
strix cloud scans start --source . --yes --wait    # scan local code, approving the upload
strix cloud scans start --engagement-type live_test --domain-ids <uuid> --wait
strix cloud vulns list --severity critical

Every REST API operation has a matching strix cloud <resource> <verb> command. Run strix cloud to list the resources, and add help to a resource to list its verbs. Output is JSON when stdout is not a terminal or when you pass --json. Binary downloads are the exception: redirect the raw bytes, or combine --output FILE --json for download metadata.

See the cloud CLI documentation for scopes, workspaces, billing, and source-upload options.

Connect your own MCP servers

Strix can connect to Model Context Protocol (MCP) servers you list and expose their tools to the agent during a run. Create ~/.strix/mcp-servers.json with a JSON list of local stdio servers or remote http servers:

[
  {
    "name": "github",
    "transport": "http",
    "url": "https://api.githubcopilot.com/mcp/",
    "auth": { "kind": "bearer", "token": "your-token" },
    "allowed_tools": ["list_issues"]
  }
]

Each server's tools are namespaced by name, for example github_list_issues. See the MCP documentation for the full schema, tool filtering, and stdio servers.

Recommended models for best results:

• Z.ai GLM-5.3 on OpenRouter - openrouter/z-ai/glm-5.3 (the default pick)

• OpenAI GPT-5.4 - openai/gpt-5.4

• Anthropic Claude Sonnet 4.6 - anthropic/claude-sonnet-4-6

• Google Gemini 3 Pro Preview - vertex_ai/gemini-3-pro-preview

• DeepSeek V4 Pro - deepseek/deepseek-v4-pro

• Moonshot Kimi K3 - moonshot/kimi-k3

See the LLM Providers documentation for all supported providers including Vertex AI, Bedrock, Azure, and local models.

Documentation

Full documentation is available at docs.strix.ai - including detailed guides for usage, CI/CD integrations, skills, and advanced configuration.

Contributing

We welcome contributions of code, docs, and new skills - check out our Contributing Guide to get started or open a pull request/issue.

Join Our Community

Have questions? Found a bug? Want to contribute? Join our Discord!

Support the Project

Love Strix? Give us a ⭐ on GitHub!

Acknowledgements

Strix builds on the incredible work of open-source projects like LiteLLM, Caido, Nuclei, Playwright, and Bubble Tea. Huge thanks to their maintainers!