Three years of AI repo waves on GitHub, and what is left of them
5,069 AI repos from 2023 to 2025 with 300+ stars, by type, and how many still get commits
Every few months there is a new kind of AI repo everyone is starring, ChatGPT wrappers in 2023, RAG and agent frameworks after that, MCP servers and coding agents in 2025, and I have starred a good chunk of all of them, so I got curious which ones are still alive. I pulled every repo created between 2023 and 2025 with more than 300 stars and one of the usual AI topics, 5,069 of them, had a model sort each one into a type from its name and description, and checked the last commit on each default branch as of November 7.
Table
| Type | Repos | Still active |
|---|---|---|
| Chat apps & UIs | 490 | 238 (49%) |
| Models & training | 672 | 266 (40%) |
| Agent frameworks | 436 | 258 (59%) |
| Learning & lists | 610 | 342 (56%) |
| Voice & audio | 171 | 78 (46%) |
| RAG & knowledge | 386 | 199 (52%) |
| Image & video | 217 | 96 (44%) |
| Browser & computer use | 93 | 57 (61%) |
| Coding agents | 255 | 154 (60%) |
| MCP servers & tools | 412 | 287 (70%) |
| Deep research | 55 | 24 (44%) |
| Multi-agent & swarms | 102 | 68 (67%) |
| Skills, prompts & rules | 184 | 116 (63%) |
| Memory & personal agents | 111 | 82 (74%) |
| Sandboxes | 34 | 24 (71%) |
| Agent managers | 54 | 48 (89%) |
| Other | 786 | 520 (66%) |
201 of the 490 chat apps came out in the first half of 2023, 269 of the 412 MCP servers in the first half of 2025, and skills and agent managers only really show up at the end of 2025.
Only 39% of the repos that came out in 2023 are still active as opposed to 72% of the 2025 repos. Even so, the 2023 chat apps are down to 33% and the 2023 model and training repos to 30%.
opencode-ai/opencode (14k stars) is archived and its README says the project moved to charmbracelet/crush, so if you starred opencode you would never know crush exists unless you went back to the repo page. Some of these repos are finished essays or lists so “dead” is not a fair way to describe them, but if you starred a pile of AI tools in the last few years, odds are a good chunk of them are now abandoned.
That is part of why I built Stars Organizer. The demo if you are interested. Explore tab shows how many of my stars are active, aging or dormant. Running Stars Organizer locally with npx github-stars-organizer adds a health score for every repo and active alternatives.
Topics searched: llm, ai, ai-agents, ai-agent, agents, mcp, mcp-server, llm-agent, rag, generative-ai, chatgpt, claude, agent, openai, large-language-models, gpt, langchain. GitHub search returns at most 1,000 results per query, so I searched each topic one quarter at a time. The types come from a small model and were right for about 9 in 10 of 50 I checked by hand.