Vercel's AI SDK agents now author 25-35% of merged PRs as top projects close external contributions
Vercel built an agent pipeline for AI SDK — separate agents reproduce bugs, apply fixes, and review them — and within four weeks it authored 25-35% of merged PRs and closed 70-80% of issues against a backlog of over 1,000 issues and 800 PRs. Astro (62,000 stars) runs the same pattern for auto-triage, while Flue converts every external PR into an issue or discussion and tldraw (50,000 stars) closes them outright. The maintainer logic is trust: a tuned in-house agent with a known success record beats reviewing unvetted community code, so contributing to a major OSS project increasingly means reporting and discussion rather than patches.
Source: latent.space ↗
If we have a very specific agent with a very specific prompt that we optimized — and we know that, over history, it was very successful in fixing a certain category of bugs — then we develop trust in that particular agent configuration.
Why this matters
- → Major OSS projects now trust their own agents over community code, reshaping how open-source contribution work
- → Vercel's AI SDK agents handle 25-35% of merged PRs, proving in-house agent pipelines outperform external revie
- → Community contributions shift from patches to discussion and reporting as maintainers deploy AI-authored code.