Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Pulse
62
Velocity
+129%
Stars
71,650
Compresses LLM inputs by 60-95% via proxy or library, saving tokens.
This library/proxy drastically reduces LLM token usage for RAG and agents, cutting costs significantly.
Cuts LLM token costs and context window usage by 60-95% for all inputs.
Why Trending
Addresses high LLM token costs and context window limitations for AI applications.
Target Audience
Developers building LLM applications, RAG, and AI agents.
Similar Projects