Developer Tools / AI Security
A fail-closed execution firewall for AI agents that quarantines MCP tools, proxies OpenAI-compatible requests, and emits signed receipts for offline verification.
The page clearly presents a real AI infrastructure project with a specific purpose: controlling agent execution, quarantining tools, and verifying decisions with signed evidence. The README shows concrete commands for local setup, proxying, MCP serving, and offline verification, plus examples of the project’s security model and intended users.
The crawl does not show full depth of the docs, API references, or whether the project is production-ready beyond the described local proof path. It also does not show the underlying license, release stability, or a concise architecture overview outside the README snippets.
Last evaluated 82 days ago. Current rank #1109. Down 3 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.
