xjtulyc

xjtulyc / MedgeClaw

Public

Open-source AI research assistant for biomedicine — chat to run RNA-seq, drug discovery, clinical analysis, and more. Built on Claude Code with 140 K-Dense scientific skills, real-time dashboard, and RStudio/JupyterLab integration. | 开源生物医学 AI 研究助手，对话即可驱动转录组、药物发现、临床分析等工作流，集成 140 个科学技能与实时研究看板。

medgeai.cn
448
204
100% credibility
Found Feb 26, 2026 at 51 stars 9x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
HTML
AI Summary

MedgeClaw is an open-source AI assistant that lets biomedical researchers chat via messaging apps to run data analyses and view results in browser-based RStudio or JupyterLab.

How It Works

1
🧑‍🔬 Discover MedgeClaw

You find this helpful AI research buddy on GitHub while looking for tools to make biomedical data analysis easier.

2
📥 Bring it home

You download the project to your computer and run a simple setup helper to get everything ready.

3
🔗 Connect the smart brain

You link it to an AI service, like picking a thinking partner, so it can understand and work with science tasks.

4
🚀 Start the playground

With one easy launch, your private analysis space comes alive, ready for data magic.

5
💬 Chat like a friend

Open WhatsApp, Slack, or Discord and talk to your assistant in everyday words about your research.

6
📊 Ask for analysis

You say things like 'analyze this RNA data' or 'check survival stats', and it gets to work right away.

🎉 See your insights

Beautiful charts, results, and reports appear in easy web viewers, helping you make discoveries faster.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 51 to 448 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is MedgeClaw?

MedgeClaw is a shell-based biomedical AI assistant that lets you chat via WhatsApp, Slack, or Discord to run complex analyses like RNA-seq differential expression, single-cell clustering, or drug virtual screening. Built on OpenClaw and Claude Code with 140 pre-built scientific skills, it spins up a Dockerized R/Python environment exposing RStudio on port 8787 and JupyterLab on 8888 for inspecting outputs. Drop data in a folder, message your request, and get results without manual scripting.

Why is it gaining traction?

It bridges casual chat interfaces to pro biomed tools—say "analyze counts.csv treatment vs control" and watch it dispatch DESeq2 or Seurat workflows via AI. Multi-model support (Anthropic, DeepSeek, Ollama) with easy .env swaps and docker compose up -d keeps costs low and setup dead simple. The hook: instant access to PubMed searches, survival curves, or ChEMBL screens without leaving your messaging app.

Who should use this?

Bioinformaticians grinding RNA-seq or scRNA-seq pipelines, clinical researchers plotting survival data, or drug discovery folks screening compounds. Ideal for wet-lab scientists who want AI to handle ggplot2 visuals or clusterProfiler enrichments via natural language, skipping Jupyter boilerplate.

Verdict

Try MedgeClaw if you're in biomed and need a quick AI sidekick—solid docs and quickstart make it approachable despite 17 stars and 1.0% credibility signaling early maturity. Polish the biomed-dispatch routing for production, but it's a clever OpenClaw hack worth forking now.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.