Open Source · Multi-Agent · GPL-3.0 + AGPL-3.0
Your AI Research Assistant
From shaping an initial idea to running experiments and preparing publication-ready outputs — Dr. Claw keeps the full research workflow in one place.
What You Get
Dr. Claw's pipeline produces structured, publication-ready outputs at every stage.
Literature reviews with citations from arXiv, Semantic Scholar, and web sources.
Survey/reports/
Brainstorming outputs with multi-persona evaluation scores (SCAMPER, SWOT).
Ideation/ideas/
Implementation from the plan → implement → judge loop.
Experiment/core_code/
Statistical analysis, tables, charts, and paper-ready figures.
Experiment/analysis/
Academic manuscript in IEEE/ACM format with citations and LaTeX math.
Publication/paper/
Slide deck, TTS narration audio, demo video, and project homepage.
Promotion/slides/
Research Pipeline
Each stage is powered by specialized research skills that the agent discovers and follows automatically.
Literature discovery, paper analysis, code survey, and resource preparation.
Structured brainstorming with creative frameworks and multi-persona evaluation.
Plan, implement, judge loop with iterative refinement and statistical analysis.
Paper writing, peer review, humanization, citation audit, and Overleaf sync.
Academic slides, TTS narration, demo video, and project homepage generation.
Capabilities
Structured dashboard for end-to-end research: define your brief, generate a pipeline of tasks, track progress, and inspect artifacts — all at a glance.
One-click sequential task execution from the Project Dashboard. Open the live session and receive an email when the run completes.
A curated library spanning idea generation, code survey, experiment development, paper writing, review response, and delivery.
Describe your research idea in Chat; the agent generates a structured research brief and task list — no manual templates needed.
Seamlessly switch between Claude Code, Gemini CLI, and Codex as your execution engines. Use whichever fits your workflow.
Use the browser UI for visualization or go terminal-only for stability. Both modes share the same skills and project structure.
Get Started
git clone https://github.com/OpenLAIR/dr-claw.git cd dr-claw npm install cp .env.example .env
npm run dev
pip install -e ./agent-harness drclaw auth login --username YOU --password PASS cd /path/to/your/project claude # or: gemini | codex
Open http://localhost:5173 in your browser
Multi-Agent
Dr. Claw works with any of these AI coding agents. Install one (or all) and switch freely.
Anthropic
npm install -g @anthropic-ai/claude-code claude
npm install -g @google/gemini-cli gemini
OpenAI
npm install -g @openai/codex codex
Integrations
See It In Action
Interactive Chat
Project Dashboard
Skill Library
Research Lab
Terminal Workflow
Academic Use
If you find Dr. Claw useful in your research, please cite:
@misc{song2026drclaw,
author = {Dingjie Song and Hanrong Zhang and Dawei Liu
and Yixin Liu and Zhengqing Yuan and Zongxia Li and Siqi Zhang and Lichao Sun},
title = {Dr. Claw: An AI Research Workspace
from Idea to Paper},
year = {2026},
organization = {GitHub},
url = {https://github.com/OpenLAIR/dr-claw},
}