openai

Lightweight coding agent that runs in your terminal

Robust Speech Recognition via Large-Scale Weak Supervision

Examples and guides for using the OpenAI API

A toolkit for developing and comparing reinforcement learning algorithms.

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

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

The official Python library for the OpenAI API

A lightweight, powerful framework for multi-agent workflows

Skills Catalog for Codex

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

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

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.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

GPT-3: Language Models are Few-Shot Learners

Generate 3D objects conditioned on text or images

An educational resource to help anyone learn deep reinforcement learning.

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

Official JavaScript / TypeScript library for the OpenAI API

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

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

macOS and Linux VMs on Apple Silicon to use in CI and other automations

OpenAI Plugins

Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.

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

Point cloud diffusion for 3D model synthesis

Demo of a customer service use case implemented with the OpenAI Agents SDK

Official repo for consistency models.

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

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

Get a ChatGPT plugin up and running in under 5 minutes!

A lightweight, powerful framework for multi-agent workflows and voice agents

Release for Improved Denoising Diffusion Probabilistic Models

GLIDE: a diffusion-based text-conditional image synthesis model

React app for inspecting, building and debugging with the Realtime API

Retro Games in Gym

The official Go library for the OpenAI API

Code for the paper "Evaluating Large Language Models Trained on Code"

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Code for openai.fm, a demo for the OpenAI Speech API

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

OpenAI Privacy Filter

The official .NET library for the OpenAI API

Node.js example app from the OpenAI API quickstart tutorial

OpenAPI specification for the OpenAI API

Example apps for the Apps SDK

Code for the paper "Improved Techniques for Training GANs"

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"

Consistency Distilled Diff VAE

DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.

800,000 step-level correctness labels on LLM solutions to MATH problems

Lean certificates accompanying Navier-Stokes and Euler results

Dataset of GPT-2 outputs for research in detection, biases, and more

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

OpenAI Assistants API quickstart with Next.js.

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

GPT-5 coding examples

Python example app from the OpenAI API quickstart tutorial

Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"

Example Discord bot written in Python that uses the completions API to have conversations with the `text-davinci-003` model, and the moderations API to filter the messages.

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

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

A living collection of deep learning problems

Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

Instructions on how to use the Realtime API on Microcontrollers and Embedded Platforms

The official Java library for the OpenAI API

Code for "Learning to Generate Reviews and Discovering Sentiment"

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

Code for the paper Fine-Tuning Language Models from Human Preferences

OpenAI Frontier Evals

Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

Official CLI for the OpenAI API

Build plugins that feel like native, first-class features of ChatGPT.

Base docker image used in Codex environments

A starter agent that can solve a number of universe environments.

Code for reproducing key results in the paper "InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets"

Efficient GPU kernels for block-sparse matrix multiplication and convolution

Code for "Learning to summarize from human feedback"

Code for the paper "On First-Order Meta-Learning Algorithms"