Get Started

From zero to your first autonomous research paper in minutes.

0 Prerequisites

  • ☑ Python 3.10+
  • ☑ Docker with NVIDIA Container Toolkit (for GPU experiments)
  • ☑ An OpenAI-compatible API key (Azure OpenAI, OpenAI, or local LLM)
  • ☑ NVIDIA GPU with 8GB+ VRAM (optional, for Docker sandbox)

1 Clone the Repository

git clone https://github.com/aiming-lab/AutoResearchClaw.git
cd AutoResearchClaw

2 Install Dependencies

pip install -e .

This installs the researchclaw package and all required dependencies.

3 Configure Your LLM

Create a YAML config file (e.g., config.yaml) with your LLM settings:

# config.yaml
project:
  name: "my-first-paper"
  mode: "docs-first"

research:
  topic: "Your research topic here"

llm:
  provider: "openai-compatible"
  base_url: "https://api.openai.com/v1"
  api_key_env: "OPENAI_API_KEY"

experiment:
  backend: "docker" # or "subprocess" for local
  timeout_sec: 1800

4 Set Your API Key

export OPENAI_API_KEY="sk-your-key-here"

5 Build the Docker Image (Optional)

If using the Docker sandbox backend for GPU-accelerated experiments:

docker build -t researchclaw-sandbox -f researchclaw/docker/Dockerfile .

6 Run Your First Paper

python -m researchclaw run --config config.yaml

The pipeline will execute all 23 stages autonomously. Output will be saved to the output/ directory including the paper PDF, LaTeX source, experiment code, and charts.

7 Review Your Paper

After the pipeline completes, find your generated paper at:

output/<run-id>/
  paper.pdf        # Final PDF
  paper.tex        # LaTeX source
  references.bib   # Bibliography
  code/main.py     # Experiment code
  charts/          # Generated figures
  results.json     # Experiment metrics

Tips

  • Use GPT-4.1 or newer for best paper quality
  • Set timeout_sec: 3600 for complex experiments
  • For Azure OpenAI, set provider: "azure_openai" and configure your endpoint
  • The pipeline caches literature results, so re-runs with the same topic are faster
  • Run python -m pytest tests/ -v to verify your installation