# OpenAI — developer ecosystem report

- GitHub org: `openai`
- Category: ai
- Overall score: 69.0 / 100
- Overall rank: #12
- Last refreshed: 2026-08-20

## Pillar scores

| Pillar | Score / 100 | Rank | Weight in overall |
| --- | --- | --- | --- |
| Code & Polish | 58.0 | #261 | ~22% |
| Education | 70.0 | #298 | ~18% |
| AI readiness | 22.0 | #565 | part of Reach |
| Builder experience | 0.0 | #1 | ~12% |
| Community | 78.0 | #8 | ~16% |
| Reach | 78.0 | #40 | ~18% |
| Momentum | 74.0 | #70 | ~14% |

## Links

- GitHub: https://github.com/openai
- Website: https://openai.com
- Docs: https://openai.com/docs

## Public GitHub totals

| Metric | Value |
| --- | --- |
| Repos analyzed | 12 |
| Stars | 857,598 |
| Forks | 129,489 |
| Open issues | 21,028 |
| Contributors | — |

## Top repositories

| Repo | Stars | Language | Description |
| --- | --- | --- | --- |
| [whisper](https://github.com/openai/whisper) | 107,402 | Python | Robust Speech Recognition via Large-Scale Weak Supervision |
| [codex](https://github.com/openai/codex) | 106,905 | Rust | Lightweight coding agent that runs in your terminal |
| [openai-cookbook](https://github.com/openai/openai-cookbook) | 75,368 | Jupyter Notebook | Examples and guides for using the OpenAI API |
| [gym](https://github.com/openai/gym) | 37,238 | Python | A toolkit for developing and comparing reinforcement learning algorithms. |
| [CLIP](https://github.com/openai/CLIP) | 34,178 | Jupyter Notebook | CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image |
| [codex-plugin-cc](https://github.com/openai/codex-plugin-cc) | 31,592 | JavaScript | Use Codex from Claude Code to review code or delegate tasks. |
| [openai-python](https://github.com/openai/openai-python) | 31,410 | Python | The official Python library for the OpenAI API |
| [openai-agents-python](https://github.com/openai/openai-agents-python) | 28,776 | Python | A lightweight, powerful framework for multi-agent workflows |
| [symphony](https://github.com/openai/symphony) | 26,767 | Elixir | Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supe |
| [gpt-2](https://github.com/openai/gpt-2) | 25,020 | Python | Code for the paper "Language Models are Unsupervised Multitask Learners" |
| [skills](https://github.com/openai/skills) | 24,998 | Python | Skills Catalog for Codex |
| [swarm](https://github.com/openai/swarm) | 21,905 | Python | Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team. |

## Methodology

Scores are computed from public signals only (GitHub, package registries, docs sites, community platforms). Pillar definitions: https://www.smoower.com/docs.md

---

HTML version: https://www.smoower.com/openai
Machine index: https://www.smoower.com/llms.txt · MCP server: https://www.smoower.com/mcp · REST API: https://www.smoower.com/api/v1