Tools for reviewing security, secret exposure, admin surfaces, RLS, and risky automation paths in AI agent workflows.
Use this collection when a project has repo imports, admin panels, API keys, or automated analysis workflows that need standardized safety checks.
Local GitHub Actions runner for AI agents — test CI/CD workflows locally before pushing.
Useful for security review, trust scoring, and sensitive workflow checks.
First open-source testing agent — handles UI, API, Security, Accessibility, and Visual validations without writing code.
Useful for security review, trust scoring, and sensitive workflow checks.
Continuous background code review database for agents — tracks accountability for every line of AI-generated code.
Useful for security review, trust scoring, and sensitive workflow checks.
Secure cloud sandboxes for AI agents. Run AI-generated code safely in isolated environments.
Useful for security review, trust scoring, and sensitive workflow checks.
Auto-updating documentation for AI coding agents — keeps docs current with your codebase via MCP.
Useful for security review, trust scoring, and sensitive workflow checks.
AI-powered documentation generator. Write code comments and Mintlify generates beautiful, interactive docs automatically.
Useful for security review, trust scoring, and sensitive workflow checks.
Open-source Playwright library for AI browser regression testing with intelligent caching and auto-healing selectors.
Useful for security review, trust scoring, and sensitive workflow checks.
OpenClaw that runs entirely on GitHub Actions — autonomous coding agent powered by scheduled workflows.
Useful for security review, trust scoring, and sensitive workflow checks.
Headless spreadsheet runtime for AI agents — edit cells, recalculate formulas, persist JSON, and refresh XLSX without Excel.
Useful for security review, trust scoring, and sensitive workflow checks.
Local-first hybrid semantic code search with pgvector + Ollama embeddings. CLI, MCP server, and web dashboard for 30+ languages.
Useful for security review, trust scoring, and sensitive workflow checks.
Open-source simulation harness for testing AI agents — simulates LLM and tool calls to test edge cases without live API calls.
Useful for security review, trust scoring, and sensitive workflow checks.
Builds a knowledge graph from any codebase with 14 LLM backends, impact analysis, and architecture-aware reasoning.
Useful for security review, trust scoring, and sensitive workflow checks.
