Robust Speech Recognition via Large-Scale Weak Supervision

Examples and guides for using the OpenAI API

Lightweight coding agent that runs in your terminal

A toolkit for developing and comparing reinforcement learning algorithms.

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

The official Python library for the OpenAI API

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.

A lightweight, powerful framework for multi-agent workflows

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

Skills Catalog for Codex

GPT-3: Language Models are Few-Shot Learners

Generate 3D objects conditioned on text or images

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

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

Official JavaScript / TypeScript library for the OpenAI API

An educational resource to help anyone learn deep reinforcement learning.

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