Karpathy

Note: For more advanced capabilities and end-to-end machine learning, visit www.k-dense.ai.

An agentic Machine Learning Engineer that trains state-of-the-art ML models using the Claude Agent SDK and Google ADK. This is a simple implementation demonstrating the power of Scientific Agent Skills for machine learning.

Prerequisites

• Python 3.13 or higher
• uv package manager
• Claude Code installed and authenticated (see the Claude Code documentation)

Setup

1. Clone the Repository

git clone https://github.com/K-Dense-AI/karpathy.git
cd karpathy

2. Install Dependencies

Install dependencies using uv:

uv sync

3. Environment Variables

Create a .env file in the karpathy directory with your API keys:

OPENROUTER_API_KEY=your_openrouter_api_key_here
AGENT_MODEL=your_model_name_here

The OPENROUTER_API_KEY is required for the agent to function properly.

This is the same environment variable that will be copied to the sandbox directory so the agents can use any API keys you provide here.

Quick Start

Run the startup script to set up the sandbox and start the ADK web interface:

python start.py

This automatically:

1. Creates a sandbox directory with skills from Scientific Agent Skills
2. Sets up a Python virtual environment with ML packages (PyTorch, transformers, scikit-learn, etc.)
3. Copies your .env file to the sandbox
4. Starts the ADK web interface
5. Navigate to http://localhost:8000 in your browser
6. Select karpathy in the top left under 'Select an agent'
7. All outputs will be in the sandbox directory so continue to monitor that as you converse with the agent

Note: Any files you want the agent to use (datasets, scripts, etc.) should be manually added to the sandbox directory.

Community

Join our K-Dense Slack community to connect with other users, share ideas, and get support:

Join K-Dense Slack Community

Scientific Agent Skills

This repository is designed to work with Scientific Agent Skills (formerly Claude Scientific Skills), a collection of 130+ ready-to-use Agent Skills for research, science, engineering, analysis, finance, and writing built on the open Agent Skills standard. The start.py setup script creates a sandbox that includes skills from this collection so the karpathy agent can leverage specialized ML libraries and scientific workflows. For full details on the skills themselves, see the upstream repository's README and documentation here.

Manual Usage

To set up the sandbox without starting the web interface:

python -m karpathy.utils

Note: Any files you want the agent to use (datasets, scripts, etc.) should be manually added to the sandbox directory.

To run the ADK web interface manually:

adk web

Then navigate to http://localhost:8000 in your browser.

Enhanced ML Capabilities

If you want substantially more powerful ML capabilities through a multi-agentic system, sign up for www.k-dense.ai.

Upcoming Features

• Modal sandbox integration - Choose any type of compute you want
• K-Dense Web features - We might make some features from K-Dense Web available here based on interest

Star History

Disclaimer

This project is not endorsed by or affiliated with Andrej Karpathy. The name is used as a tribute and out of deep respect for his contributions to AI and technical leadership.