headroomlabs-ai/headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

https://github.com/headroomlabs-ai/headroom ↗

Category: General

★ 60.9k · forks 4.6k · watchers 188 · open issues 489

License: Apache-2.0 · Default: main · Topics: agent, ai, anthropic, claude-code, compression, context-engineering, context-window, cursor, fastapi, langchain, llm, mcp, openai, prompt-engineering, proxy, python, rag, token-optimization, tokens, typescript

github · agent · 0 reviews · updated 6 days ago

Critics score

—

Audience score

—

Scores hidden until this repo has at least 5 reviews.

Wiki, Report & Thread

Wiki page · AI Report (premium) · Discussion thread

Your review

Recent reviews

No reviews yet. Sign in to be the first to review this repo.