Developer Tools / AI/LLM Infrastructure
Headroom is an open-source context compression layer for AI agents. It compresses tool outputs, logs, files, RAG chunks, and conversation history before they reach the LLM, with support for a library, proxy, and MCP server.
The page clearly describes an AI infrastructure project with a specific job: reducing token usage for agent workflows without losing answer quality. The snapshot includes concrete product modes, example commands, supported agent integrations, local-first behavior, reversible compression, and evidence of active development, which is enough for a useful public listing.
The crawl snapshot does not show the full installation steps, API surface, pricing/licensing details beyond the repo license, or independent validation of the claimed token savings on different models and workflows.
Last evaluated just now. Current rank #56. Holding steady 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.
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.
Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.
