LibraryAI and agent development
ToolRAG
Retrieve only the most relevant tools for an LLM query
- Stars
- 29
- Forks
- 3
- Updated
- Updated Jul 4, 2026
Apache-2.0
Retrieve only the most relevant tools for an LLM query
ToolRAG registers tools from MCP servers, embeds their descriptions, and uses semantic retrieval to select the functions relevant to a user query. The selected definitions can be passed in an OpenAI-compatible format and executed against the corresponding servers, while LibSQL stores the tool index and embeddings. It is aimed at assistants that need access to many APIs without sending every tool definition on every request.
Resource types
Use cases
Protocols & integrations
Turns GitHub repositories into executable software-engineering tasks for training SWE agents.
Help LangGraph agents retrieve relevant tools from very large registries.
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Studies active tool discovery for autonomous agents with an MCP retrieval dataset and scripts.
Manage one shared skill pool and expose tailored collections to multiple agents.