DeepSeek Harness: Everything is a Plugin.

A post-modern modal text editor.

The agent that grows with you

The batteries-included agent harness.

An agentic skills framework & software development methodology that works.

The open agent skills tool - npx skills

Database governance built for humans and agents — controlling changes and access across every major database.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Skills for Real Engineers. Straight from my .agents directory.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

A git client based on the IntelliJ platform

Create, Evaluate, and Connect AI Skills

Let Skills Evolve Collectively with Agentic Evolver

Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tools, with iPhone & Apple Watch companions

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Skills for Designers and Engineers.

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

Wrapper around tool using LLMs for agentic workflows

Extract and compare system prompts and tools from different Claude Code versions

The open source coding agent.

👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

Lightweight coding agent that runs in your terminal

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

Optimize prompts, code, and more with AI-powered Reflective Optimization

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.