#5959th of 80 in Agent platformsFor science, health and research, research and papers
dr-claw
Research workspace that drives Claude Code, Gemini CLI or Codex through a paper pipeline
- Stars
- 1.2k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- JavaScript
869 on 21 Apr 20261,199 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Dr. Claw is a Node.js web and Electron desktop workspace that wraps Claude Code, Gemini CLI, Codex and OpenRouter models as execution agents for research projects. It tracks a Survey, Ideation, Experiment, Publication and Promotion pipeline, with 121 built-in skills, a news feed, a file and Git explorer, and one-click Auto Research. Local models can run on Ollama, vLLM or SGLang.
Who it is for: Researchers running literature-to-paper projects with coding agents
Strengths
- Switches between Claude Code, Gemini CLI, Codex and OpenRouter as execution backends
- Produces stage-organized artifacts: survey reports, experiment code, LaTeX paper draft, slides
- Installs via desktop app (macOS arm64, Windows x64), npx, or source
- Terminal options: dr-claw chat for OpenRouter models and a drclaw CLI harness
Weaknesses
- Needs an external agent CLI or OpenRouter key; it is not a standalone model runner
- Desktop installers cover only Apple Silicon macOS and Windows x64; no Linux or Intel Mac
- macOS build is not notarized; first launch needs an xattr command
- npm package can lag behind the desktop release; license is a GPL-3.0 and AGPL-3.0 mix
What it needs
- GPU optional
- Needs Node.js 20+ (22 LTS recommended), Claude Code CLI, Gemini CLI, Codex CLI or OpenRouter API key
- Models: Claude Code, Gemini CLI, Codex, OpenRouter, Ollama
- port 3001
Quick answers
Is dr-claw open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Does dr-claw need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |