dorringel/epsiclaw

The Karpathy treatment for OpenClaw - stripped to ε. 515 lines of Python, 6 files, one dependency.

33
/ 100
Emerging

This project helps developers understand the core logic of a sophisticated AI agent, stripped down to its essentials. It takes chat messages as input and processes them through an AI to use various tools (like setting reminders or accessing memory), then produces chat replies. This is ideal for developers who want to grasp the fundamental algorithms behind conversational AI agents without the complexity of a full-fledged production system.

Use this if you are a developer looking to learn and experiment with the core algorithm of an AI agent, specifically how it integrates memory, tools, and a chat interface.

Not ideal if you need a production-ready, secure, scalable, or multi-user AI agent system.

AI-agent-development conversational-AI LLM-tool-integration AI-memory-management developer-learning
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 9 / 25
Community 4 / 25

How are scores calculated?

Stars

30

Forks

1

Language

Python

License

MIT

Last pushed

Mar 26, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/dorringel/epsiclaw"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.