Developer Tools / AI Safety / Agent Skills
A GitHub repository that turns untrusted source material into compact AI skills using evidence gates, validation steps, and audit output.
The page clearly presents a real AI-adjacent developer tool with a specific workflow: it extracts reusable skills from repositories, books, transcripts, and docs while keeping source material quarantined, tracked, and validated. The README gives enough detail to understand the purpose, safeguards, repository layout, usage, and current maturity, making it suitable for a public listing.
The snapshot does not show package installation or dependency setup, and the README says there is no installer. It also leaves a few adoption questions open, such as how the validation gate is configured in practice and what output looks like on a real example beyond the described workflow.
Last evaluated 29 days ago. Current rank #1202. Down 2 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
