avinshe

avinshe / agentseed

Public

Generate AGENTS.md from your codebase in one command. Free, instant, no API key

www.npmjs.compackageagentseed agents agents-md ai-coding claude cli
55
0
100% credibility
Found Feb 09, 2026 at 28 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Agentseed analyzes codebases to generate instructional markdown files that help AI coding agents understand project structure, technologies, commands, and conventions.

How It Works

1
🔍 Discover agentseed

You hear about agentseed, a helpful tool that makes AI assistants smarter by reading your project's code and creating easy guides for them.

2
🗂️ Open your project folder

Navigate to the folder containing your code project on your computer.

3
✨ Start agentseed with one click

Give the simple go-ahead instruction, and it instantly scans your entire project to learn about languages, tools, and setup.

4
Choose your scan style
⚡
Quick free scan

Get instant basic guides without any extra setup – perfect for a fast start.

🧠
Boost with smart helper

Link a thinking service you already use to create deeper, more insightful guides.

5
📄 Review new guide files

Agentseed creates special files like AGENTS.md right in your project, summarizing everything an AI needs to know.

🎉 AI assistants are project experts

Now every AI tool that works on your code understands your setup, runs the right steps, and follows your style perfectly.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 28 to 55 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is agentseed?

Agentseed scans your codebase to generate AGENTS.md files in one command: npx agentseed init. It detects languages, frameworks like Next.js or Flask, commands from package.json or Makefiles, and project structure, creating docs that teach AI agents your conventions and boundaries. Free static mode works instantly without API keys; add Claude, OpenAI, or Ollama for richer LLM-enhanced output across formats like Copilot instructions, Cursor rules, or CLAUDE.md.

Why is it gaining traction?

Unlike manual prompts to generate agents.md for Copilot or Cursor, agentseed automates it from your actual codebase, supporting monorepos via npx agentseed scan for subfolder-specific files. Incremental git-based updates skip unchanged sections, and multi-tool output (all formats at once) saves time versus tool-specific generators. At ~$0.08 per LLM run or zero cost static, it's practical for real projects like Express or dbt.

Who should use this?

Backend devs maintaining Express or FastAPI repos who want Copilot to run the right npm test. Frontend teams on Next.js or Svelte tired of AI ignoring their naming conventions. Monorepo owners in Rust workspaces or Python ETL pipelines needing scoped AGENTS.md without duplication.

Verdict

Try it for quick AI agent boosts—solid CLI, great docs, broad ecosystem support—but with 33 stars and 1.0% credibility, it's early; test on your codebase first. Worth npx-ing today if you use Cursor, Copilot, or Claude Code.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.