Free medical RAG API for local LLM agents
hyfl.uk is a free RAG API that lets and agents look up medical facts before answering. It is built from medical Wikipedia articles and is meant to help when a model cannot remember a fact correctly from its own stored knowledge. The target is response times under one second, but that is not guaranteed because the service is free and runs on one ARM VPS.
It uses about 2GB of memory. The medical article collection is not complete, so some obvious topics may be missing, and more articles can be requested for inclusion. An agent can be told to use https://hyfl.uk for medical facts.
MCP is also supported, so the service can be connected as a tool. In the example, a small Qwen 3.5 0.8B model gave a wrong explanation of Lhermitte sign without RAG, but produced a more medically grounded answer when using hyfl.uk.
Key points
- The service gives and agents access to medical facts through a free RAG API.
- It uses medical Wikipedia articles, but the collection is not complete.
- It aims for subsecond replies, but speed is not guaranteed on the single ARM VPS.
- It uses about 2GB of memory and supports MCP tool connection.
- The example shows a small Qwen 3.5 0.8B model improving a wrong medical answer when retrieval is added.