{"slug":"ratel","name":"ratel","author":"ratel-ai","domain":"coding","integrations":["Claude Code","MCP-compatible hosts","BM25 retrieval","semantic search","agent memory"],"language":null,"license":"MIT","stars":425,"traits":["oss","mcp"],"summary":"Context engineering layer for AI agents that cuts token usage by ~80% through in-process BM25 and semantic skill retrieval, progressive tool disclosure, and agent memory. Exposes an MCP server so any coding agent or LLM host can connect to it.","repo":"https://github.com/ratel-ai/ratel","community":true,"tip":{"method":"x402","network":"eip155:8453","endpoint":"/api/tip/ratel","note":"GET with an x402 client to tip the author; returns 402 with payment requirements until paid."}}