Building a software factory for AI SDK - Vercel
We built a software factory that autonomously processes issues and PRs for the AI SDK, with humans in control of every merge. Four weeks in, it authors 25-40% of merged PRs.
The AI SDK is one of the most popular open-source AI projects in the world. It serves over 20 million npm downloads a week and the repo has over 26,000 stars. Maintaining the codebase means tracking four moving targets at once: Model providers: new providers, new capabilities, and new bugs UI frameworks: bindings for React, Next.js, Svelte, Vue, and others Sandboxes: the execution environments agents run code in Harnesses: adapters for Codex, Claude Code, Pi, and others After multiple years of growth, the repo was getting 100+ new issues every month, and when Anthropic's Opus 4.6 model…
saved by
related reading
- The Agent Stackvercel.com
- AI agent evaluation frameworks for production - Vercelvercel.com
- If you are good at code review, you will be good at using AI agentsseangoedecke.com
- AI is removing the middle class of software engineeringblog.florianherrengt.com
- Why I'm Betting Against AI Agents in 2025 (Despite Building Them)utkarshkanwat.com
- dex (@dexhorthy) on Xx.com
- Why We Built Our Own Background Agentbuilders.ramp.com
- Your job is to deliver code you have proven to worksimonwillison.net
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- AI is approving our pull requests: Here’s how we made it safeintercom.com
- Code was our medium for thoughtwattenberger.com
- Building Effective AI Agents \ Anthropicanthropic.com