headroomlabs-ai/headroom

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

55.8

Score

53,471

Stars

3,835

Forks

0.0

Trend

Details

Language
Python
License
Apache-2.0
Category
AI/ML
Open Issues
427
Contributors
0
Archived
No

Security

OpenSSF Score
N/A
Dependency Risk
Unknown
Activity Health
Unknown

Topics

agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript