Inject version-matched Next.js docs into AI agent context files for retrieval-led coding.
next-agents-md is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo clone gaojude/next-agents-mdOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
This tool helps AI coding agents like Claude or Cursor access the correct Next.js documentation for your project. It detects your Next.js version, downloads the matching docs, and adds a reference index to your CLAUDE.md or AGENTS.md file. The agent then reads the docs from local files instead of relying on outdated training data.
next-agents-md is a command-line tool that bridges the gap between AI coding agents and up-to-date Next.js documentation. When an AI agent works on a Next.js project, it often relies on its training data, which may be outdated or incomplete. This tool solves that by automatically detecting the Next.js version in your project, downloading the corresponding official documentation from the Next.js website, and injecting a compressed index into your CLAUDE.md or AGENTS.md file. The index contains references to documentation files stored in a local `.next-docs/` directory. When the AI agent encounters a Next.js task, it can read the relevant documentation from these local files, ensuring it always uses the correct and most current information. The tool is designed to be non-intrusive: it only modifies the markdown file between special markers (`<!-- NEXT-AGENTS-MD-START -->` and `<!-- NEXT-AGENTS-MD-END -->`), so you can easily update or remove the index. It supports both interactive and non-interactive modes, allowing you to specify the version or target file via command-line flags. This is particularly useful for teams that want to ensure consistent documentation access across different AI agents and projects.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 185 days ago.
5 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Enhance Claude Code's Next.js knowledge by injecting version-specific docs into CLAUDE.md.
Improve Cursor's context awareness for Next.js projects by adding a documentation index.
Standardize documentation access across a team using AGENTS.md in a monorepo.
Automate documentation updates in CI/CD pipelines for Next.js projects.
Quickly onboard new developers by providing AI agents with accurate Next.js references.
Agent instruction templates should be reviewed before use because they can change coding-agent behavior across an entire repository.
Avoid copying rules that grant broad filesystem, shell, network, or secret access without adapting them to your project.
5
Stars
0
Forks
0
Issues
MIT
License
A drop-in AGENTS.md file that makes coding agents behave like senior engineers, eliminating sycophancy and forcing verification.
Convert and sync AI coding-agent rule files between formats with zero dependencies.
Generate AGENTS.md from your codebase in one command. Free, instant, no API key.
Inject version-matched Next.js docs into AI agent context files for retrieval-led coding.
Next.js developers using AI coding assistants like Claude or Cursor., Teams maintaining multiple Next.js projects who want consistent AI agent behavior., Developers building AI-powered tools that need up-to-date framework documentation.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent instruction templates should be reviewed before use because they can change coding-agent behavior across an entire repository. Avoid copying rules that grant broad filesystem, shell, network, or secret access without adapting them to your project.
Similar or complementary options to evaluate include agents-md, agentsync, agentseed.
Jun 7, 2026
2 security/trust notes recorded.
Setup difficulty is 1/5.