AI Tools

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

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

Code for the paper "Language Models are Unsupervised Multitask Learners"

Skills Catalog for Codex

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference

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

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

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

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

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Use Claude Code, OpenCode, Cursor CLI, and Codex on mobile and web with CloudCLI (aka Claude Code UI). CloudCLI is a free open source webui/GUI that helps you manage your Claude Code session and projects remotely.

Generate 3D objects conditioned on text or images

Official JavaScript / TypeScript library for the OpenAI API

PyTorch package for the discrete VAE used for DALL·E.

The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.

Code for the paper "Jukebox: A Generative Model for Music"

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

Point cloud diffusion for 3D model synthesis

Official repo for consistency models.

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

Train the smallest LM you can that fits in 16MB. Best model wins!