Vibe Coding Discoverratel
View on GitHubContext engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.
Rust retrieval engine with TypeScript and Python SDKs that helps AI agents discover relevant tools, skills, and facts on demand. Uses BM25 by default, with optional semantic and hybrid search, to reduce context and avoid loading every capability up front.
Use Cases
Select relevant tools for each agent turnRetrieve skills and instructions on demandReduce prompt tokens from unused tool schemasAdd searchable facts and memory to agentsImprove tool choice in agents with large capability catalogs
Built With
- Language
- Rust
- Frameworks
- Vercel AI SDK · Pydantic AI · Mastra
Tags
context engineering · tool selection · skill retrieval · agent memory · BM25 · semantic search · progressive disclosure · token optimization · tool calling