Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
📊 Project Info
- Language
- Python
- Stars
- ⭐ 12,419
- Forks
- 807
- Today
- +3,142
- Ranking
- #1
- Collection
- Overall
- Trending Date
- June 4, 2026
- Last Push
- 6/4/2026
🏷️ Topics
agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
📸 Screenshots
