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.
headroomlabs-ai/headroom
View on GitHub ↗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.
headroom grew +5.4% in the last 30 days, ranks 8th of 1,061 in Prompting & Scaffolding, actively maintained, last commit yesterday.
Star trajectory
116 days tracked+5.4% in 30d, above the Prompting & Scaffolding median of +1.4%.
Last commit yesterday, fresher than the median of 28d.
How it compares in Prompting & Scaffolding
Ranked 8th of 1,061 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 348
- Forks
- 6k
- Watchers
- 217
- Open issues
- 289
- Releases
- 174
- Created
- 2026-01-07
- Stars this week
- +1.8k
You've seen where headroom stands today.
Get the moves before everyone else: the 5 Prompting & Scaffolding repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.