Generate AGENTS.md from your codebase in one command. Free, instant, no API key.
agentseed is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo clone avinshe/agentseedOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
Agentseed reads your codebase and automatically creates an AGENTS.md file that tells AI coding agents about your project's languages, frameworks, commands, and conventions. It works instantly without any API key, and can optionally use your own LLM key for richer descriptions. This helps AI tools like Copilot, Claude, and Cursor understand your project better.
Agentseed is a CLI tool that analyzes your codebase and generates a production-quality AGENTS.md file, which is the open standard for AI coding agent instructions. It performs static analysis to detect languages, frameworks, dependencies, build/test/lint commands, directory structure, naming conventions, and monorepo patterns. Optionally, it can use an LLM (Claude, GPT, or Ollama) with your own API key to enhance the output with richer project descriptions. The generated file includes sections like Project Context, Stack, Commands, Conventions, Architecture, and Boundaries. Agentseed supports multiple output formats including AGENTS.md, CLAUDE.md, .cursorrules, copilot instructions, and windsurf rules. It tracks git SHAs to only regenerate changed files, and can be forced to refresh everything. It's free, instant, and requires no API key for the basic static analysis.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 117 days ago.
60 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Generate AGENTS.md for a new or existing repository to improve AI agent interactions
Quickly onboard AI coding assistants like Copilot, Claude, or Cursor to a project's conventions
Automatically document project structure and commands for team collaboration
Create multiple AI tool configuration files (AGENTS.md, CLAUDE.md, .cursorrules) in one command
Enhance AI agent context with LLM-generated descriptions using your own API key
When using LLM enhancement, your code snippets are sent to the LLM provider (e.g., Anthropic, OpenAI). Ensure you trust the provider with your code.
The tool does not send code when using static analysis only (no API key).
60
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.
AGENTS.md rules and skills for AI coding agents, distilled from classic software engineering books.
2 security/trust notes recorded.
Setup difficulty is 1/5.