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.
Why this repo matters
•Reduces LLM token usage by 60-95% for JSON and 20% for coding agents without accuracy loss.
•Integrates as a library, proxy, or MCP server to compress tool outputs and RAG chunks.
•Offers reversible, content-aware compression specifically designed for AI agent context windows.