Developer Tools / Agent Infrastructure
A local-first Windows tool for indexing, searching, and loading large agent skill libraries without keeping full skill bodies in context. It supports SQLite FTS5 search, multiple ranking modes, CLI use, HTTP, and MCP stdio.
The page clearly describes a real AI-adjacent developer tool with a specific job: routing large agent skill libraries while keeping context small. The README provides enough detail for a public listing, including how it works, supported interfaces, search modes, build/test steps, and release/security notes. The project is distinct from generic search tooling because it is built around skill discovery, loading, and agent workflows.
The snapshot is Windows-focused, and it’s still unclear how portable the project is beyond Windows x64 or how it performs on larger libraries in practice. The page also does not show screenshots, benchmark numbers, or a fuller end-to-end example of using the router inside an agent workflow.
Last evaluated 36 days ago. Current rank #804. Down 6 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.
