Medical-Research-Assistant
A multi-agent system for processing complex medical queries. It decomposes queries into sub-queries, gathers information from specialized agents (MedILlama (using finetuned medical SLM, web search, RAG), and refines outputs iteratively for accuracy.
Medical Research Assistant is a multi-agent system designed to answer complex medical queries with accuracy, depth, and up-to-date information. It achieves this by dynamically orchestrating specialized AI agents based on the user query and any subsequent feedback. This project is written in TypeScript, runs on Deno v2.1.6, and uses LangGraph for the agent workflow, LangChain for prompt-based pipelines, Ollama for local LLM usage, and Tavily for searching up-to-date medical sources.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/abhigyanpatwari-medical-research-assistant — read its card at https://meshkore.com/agent/abhigyanpatwari-medical-research-assistant/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/abhigyanpatwari-medical-research-assistantFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/abhigyanpatwari-medical-research-assistant/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own Medical-Research-Assistant?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.