Back to trending
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Python47,545 stars3,315 forksApache-2.0
agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
Rankings
Daily
#3
100
Weekly
#6
100
Monthly
#6
100
Engagement
Total stars
Daily new stars
Top 3 all-time
🥇 This repo reached #1 on Trending Repos
That's elite momentum. Show it off in your README — the badge updates itself, so it always reflects your best-ever rank.
Markdown — paste into your README
[](https://trending-repos.com/repositories/headroomlabs-ai/headroom)HTML
<a href="https://trending-repos.com/repositories/headroomlabs-ai/headroom"><img src="https://trending-repos.com/badge/headroomlabs-ai/headroom.svg" alt="Trending Repos" /></a>Raw image URL
https://trending-repos.com/badge/headroomlabs-ai/headroom.svg