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

70

Forks

2,662

Issues

328

Installation

Difficulty

Advanced

Estimated Time

20-45 minutes

Additional Resources

GitHub Repository Official Website

Author Information

0

Followers

0

Repositories

0

Gists

0

Total Contributions

Tags

API File System Automation AI/LLM agent ai anthropic claude-code compression context-engineering context-window cursor fastapi langchain llm

Related MCPs

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

chatgpt-on-wechat

CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.