Ingest LLM-friendly documentation from any site that supports the llms.txt standard

LLMsTxtTools and LLMsTxtReader add native support for the llms.txt standard — a Markdown-based file that websites publish at /llms.txt to provide LLMs with a concise, structured index of their documentation, free of navigation elements, JavaScript, and other noise that wastes context. Agents can now fetch, read, and work with llms.txt files directly, making it straightforward to build agents that are grounded in up-to-date third-party documentation without manual content pipelines.

‍

Details:

LLMsTxtReader ingests any llms.txt file into a knowledge base for retrieval and RAG
LLMsTxtTools lets agents fetch and query llms.txt indexes directly as a tool call
Compatible with any site publishing the standard, including https://docs.agno.com/llms.txt
No preprocessing required — llms.txt files are already structured for LLM consumption

‍

See cookbook for reference