Liu-Hy/GenoMAS
A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.
Agents communicate via typed messages and execute Python code in a controlled notebook environment, enabling multi-step reasoning with execution and debugging. The framework supports customizable agent roles (e.g., Domain Expert, Code Reviewer, Statistician) with distinct guidelines and tools, integrating with LLM providers (OpenAI, Claude, Gemini) via configurable API keys for heterogeneous multi-model orchestration. GenoMAS applies this to genomics by analyzing GEO/TCGA transcriptomic datasets to identify gene-trait associations while controlling for confounders, achieving 60.38% F1 on the GenoTEX benchmark.
133 stars.
Stars
133
Forks
24
Language
Python
License
MIT
Category
Last pushed
Oct 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Liu-Hy/GenoMAS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
ag2ai/ag2
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/sNGSwQME3x
ivangabriele/openai-autogen-dev-studio
OADS: Generate games and programs using OpenAI agents. Built on top of Microsoft Autogen.
ksm26/AI-Agentic-Design-Patterns-with-AutoGen
Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to...
jkmaina/autogen_blueprint
This is the official companion repository for 'The Complete AutoGen AI Agent Blueprint:...
wronkiew/autogen-agent-server
Lightweight server for developing conversational agents using Microsoft AutoGen 0.4