Install Now
How to install SakanaAI/AI-Scientist-v2. Official installation instructions. Project installation guide. Framework or library installation. Build installation instructions. How to setup and install from GitHub. Installation steps and setup instructions. Official docs and installation instructions GitHub.
SakanaAI/AI-Scientist-v2 Installation Guide
How to install SakanaAI/AI-Scientist-v2. Official project installation instructions and setup guide.
⚡
Automated Install (Recommended)
Quick installation instructions for SakanaAI/AI-Scientist-v2. This is the fastest way to complete project installation and setup.
Install via curl
curl -fsSL https://hexmos.com/ipm-install | bash &&
ipm i SakanaAI/AI-Scientist-v2or
Install via npx
npx @hexmos/ipm i SakanaAI/AI-Scientist-v2Prerequisites
NVIDIA GPU
hardwareVersion: any
CUDA
softwareVersion: any
PyTorch
softwareVersion: any
conda
softwareVersion: any
pip
softwareVersion: any
Poppler
softwareVersion: any
chktex
softwareVersion: any
AWS CLI
softwareVersion: any
Manual Installation Methods
Manual installation instructions. How to install from GitHub source.
Linux Installation using Conda and Pip
conda create -n ai_scientist python=3.11
conda activate ai_scientist
conda install pytorch torchvision torchaudio pytorch-cuda=12.4 -c pytorch -c nvidia
conda install anaconda::poppler
conda install conda-forge::chktex
pip install -r requirements.txt
export OPENAI_API_KEY="YOUR_OPENAI_KEY_HERE"
export S2_API_KEY="YOUR_S2_KEY_HERE"
export AWS_ACCESS_KEY_ID="YOUR_AWS_ACCESS_KEY_ID"
export AWS_SECRET_ACCESS_KEY="YOUR_AWS_SECRET_KEY"
export AWS_REGION_NAME="your-aws-region"Installation for Claude Models via AWS Bedrock
pip install anthropic[bedrock]Post Installation Steps
- Run ideation script: python ai_scientist/perform_ideation_temp_free.py --workshop-file <path_to_topic.md> --model <llm_model> --max-num-generations <num> --num-reflections <num>
- Run main experiment pipeline: python launch_scientist_bfts.py --load_ideas <path_to_ideas.json> --load_code --add_dataset_ref --model_writeup <model> --model_citation <model> --model_review <model> --model_agg_plots <model> --num_cite_rounds <num>