What I learned from looking at 900 most popular open source AI tools
Chip Huyen
A researcher analyzed 896 open source repositories related to generative AI and foundation models on GitHub, categorizing them into infrastructure, model development, and application development layers. The analysis found that 845 software repositories have been created by 594 unique GitHub accounts, with 23% hosted by just 20 top accounts that collectively earned 1.65 million stars, and over 20,000 developers contributed nearly 1 million commits to these projects. The findings show rapid growth in application development tools in 2023, the emergence of individual developers as major contributors especially in applications, and a distinct Chinese AI ecosystem diverging from the Western one with 6 of the top 20 accounts originating from China.
Why it matters
[Hacker News discussion, LinkedIn discussion, Twitter thread] Update (Feb 2026): The full list of open source AI repos is hosted at Good AI List, updated daily. It’s balooned to 15K repos, and you can submit missing repos. You can also find some of them on my cool-llm-repos list on GitHub. Four years ago, I did an analysis of the open source ML ecosystem. Since then, the landscape has changed, so I revisited the topic. This time, I focused exclusively on the stack around foundation models. Data I searched GitHub using the keywords gpt, llm, and generative ai. If AI feels so overwhelming right now, it’s because it is. There are 118K results for gpt alone. To make my life easier, I limited my search to the repos with at least 500 stars. There were 590 results for llm, 531 for gpt, and 38 for generative ai. I also occasionally checked GitHub trending and social media for new repos. After MANY hours, I found 896 repos. Of these, 51 are tutorials (e.g. dair-ai/Prompt-Engineering-Guide) and
