How Next.js Closed 1,500 GitHub Issues Using AI Agents

ArticleMarcos HernanzNews

The Next.js team built autonomous research agents using Vercel's open-source framework eve to investigate over 2,200 GitHub issues. Within weeks, maintainers closed 1,462 tickets with high precision based on evidence collected by the agents.

Key points

  1. Traditional stale bots failed because inactivity does not distinguish between fixed bugs, obsolete reports, and ignored regressions.
  2. The 'closability' agent runs on Vercel's eve framework using GPT-5.6 Luna with maximum reasoning in isolated Vercel Sandboxes.
  3. Investigations evaluate commit history, pull requests, docs, and attempt bug reproduction using Node.js, Playwright, and Chromium.
  4. The agent operates in read-only mode outside its sandbox and produces structured confidence scores alongside supporting evidence.
  5. Out of 1,462 closed issues, 99.8% remained closed after a 14-day community reopening window, with only three issues reopened.
  6. The pipeline is expanding: a two-agent consensus mechanism now autonomously closes up to 25 obvious issues per week.

Why it matters

As coding agents accelerate issue creation across open-source repositories, maintainers face unsustainable review queues. Next.js illustrates a robust approach to offloading deep verification work to sandboxed AI agents while maintaining human oversight.

Analysis

Vercel's strategy moves beyond blunt time-based stale bots toward contextual code execution and verification. Key architectural decisions include strict sandbox isolation, prompt injection guards, and conservative scoring criteria where failure to reproduce does not automatically justify closure. By dividing tasks across specialized agents (reproduction, verification, fix proposals), the Maintainer Agent framework offers a practical model for managing high-volume software repositories.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:Next.js

    Next.js Clears Issue Backlog Using AI Research Agent and Human Review

    The Next.js team closed nearly 1,500 GitHub issues in one month, bringing their repository backlog down from over 2,200 to under 1,000 open reports. The process was powered by 'closability', a research agent built with Vercel's open-source 'eve' framework and GPT-5.6 Luna.

    503bookmarks178.3kviews

    AI & LLMs· Announcement

  • Link:Vercel

    Eve: Open-Source Framework for Durable Backend AI Agents

    Eve is an Apache-2.0, filesystem-first framework designed for building durable backend AI agents. Currently in beta, it can be deployed on Vercel or self-hosted as a Node service on custom infrastructure.

    AI & LLMs· Tool

  • Video

    Video:ByteGrad

    Next.js 16.3: Runtime Debugging with next-dev-loop and agent-browser

    ByteGrad's Wesley demonstrates the next-dev-loop skill introduced in Next.js 16.3 alongside the agent-browser package. Rather than relying solely on compile or type checks, an AI agent takes control of a real browser, reproduces a visual bug in a chart component, and verifies the fix at runtime.

    AI & LLMs· Demo

  • Repository:vercel-labs/agent-skills

    Vercel Labs Agent Skills: Structured Rules and Audits for AI Coding Agents

    Vercel Labs provides a curated collection of instructions and scripts designed for AI coding agents. Following the Agent Skills specification, the repository covers Vercel cloud optimization, React and Next.js performance, UI best practices, and technical writing.

    31.3kstarsJavaScript

    AI & LLMs· Resource

  • Repository:ShenSeanChen/launch-DeepResearch-Frontend

    Deep Research Agent Frontend: Next.js UI for Streaming Research Workflows

    launch-DeepResearch-Frontend is an open-source Next.js frontend designed for Deep Research Agents. It provides a chat-like interface similar to Perplexity, featuring live streaming of reasoning steps, multi-model support, and document export.

    37starsTypeScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.