Best AI GitHub Repos

Base docker image used in Codex environments

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

DuckDB-powered skills for Claude Code: read any data file, attach and query DuckDB databases, search DuckDB/DuckLake docs, search past session logs, and install/update DuckDB extensions.

OpenAI Frontier Evals

Use Codex from Claude Code to review code or delegate tasks.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Example apps for the Apps SDK

Robust Speech Recognition via Large-Scale Weak Supervision

A programming framework for agentic AI

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

Renderer for the harmony response format to be used with gpt-oss

Learn how to use CUA (our Computer Using Agent) via the API on multiple computer environments.

OpenAI Guardrails - Python

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Starter app to build with OpenAI ChatKit + Agent Builder

Starter app to build with OpenAI ChatKit SDK

The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI

Physical AI Assistant that illuminates your life

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

AI agents running research on single-GPU nanochat training automatically

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Liquid language support plugin for Claude Code

Monitor browser logs directly from Cursor and other MCP compatible IDEs.

Claude Code SDK Demos