headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
GitHub Stars
38,922
User Rating
Not Rated
Favorites
0
Views
72
Forks
2,662
Issues
328
Technical Information
Programming Languages
PythonPrimary Language
System Requirements
No specific requirements are documented
Maintenance Status
ActiveGitHub Topics
APIFile SystemAutomationAI/LLMagentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllm