headroomlabs-ai/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.

语言：Python · GitHub 星标：79,090 · Fork：6,183

话题：agent · ai · anthropic · claude-code · compression · context-engineering · context-window · cursor

在 GitHub 上查看原仓库