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.

★ 61.3K Stars

⑂ 4.6K Forks

○ 61.3K Watchers

✖ 497 Issues

Python

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

Last push: 2h ago

Created:

↗ View on GitHub

Loading additional information…