A list of 1,325 AI assisted repositories, mined from GitHub
ActuallyTaylor
11 points
14 comments
September 14, 2026
Related Discussions
Found 5 related stories in 71.8ms across 6,607 title embeddings via pgvector HNSW
- Show HN: AI Law Tracker – one audited API for US, EU and global AI law asm28208 · 20 pts · July 16, 2026 · 52% similar
- OpenAI Forked Git on GitHub rahlokzero · 23 pts · July 11, 2026 · 50% similar
- Three sites made 215,128 “best software” pages for AI. Perplexity cites them jakobgreenfeld · 359 pts · September 02, 2026 · 49% similar
- What AI did to stackoverflow in a graph secretslol · 392 pts · July 18, 2026 · 48% similar
- How we measured AI writing across arXiv, and where the measurement breaks dopamine_daddy · 206 pts · July 20, 2026 · 47% similar
Discussion Highlights (5 comments)
unified101
Only python?
lioeters
Related paper in the repo: Changes in Vocabulary Between Human-created and LLM-assisted Code Repositories - Taylor Lineman https://raw.githubusercontent.com/ActuallyTaylor/strata/refs... (PDF)
unixhero
Won't this be all at some point
prologic
What is the point collecting this data? I feel like this is like "A list of N,NNN repositories using IDE(s)" Hmmm I don't get it?
deckar01
There has been a persistent attack on GitHub repos by agents trying to land a commit to become a contributor. The default GitHub permission is to allow contributors to execute actions against the repo’s compute budget, so it could be a botnet. Another possibility is that they are trying to get a Copilot grant. Someone claiming to be in academia was surveying repos when that program first started. I’m guessing the permissions for that are equally as naive.