76,077 stars | 5,913 forks | Python
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.
What it does
Headroom is a powerful open-source library, proxy, and agent wrapper that dramatically reduces the token count of inputs to LLMs (Large Language Models) – up to 95% for JSON and 60% for general text – without sacrificing answer quality. It operates locally, ensuring data privacy and offering features like cross-agent memory, automated correction learning, and reversible compression. This significantly lowers LLM costs and improves performance.
Why it matters: 🤯 Cut your LLM costs by up to 95% with Headroom! Same answers, fewer tokens. 🚀 #LLM #TokenCompression
Trending today with 317 new stars
Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.
