Agent Smith

Name: Agent Smith
Author: jpoindexter

@jpoindexter

リポジトリ

Agent Smith について

Auto-generate AGENTS.md from your codebase

#agents-md #code-context #ai-coding #cursor #claude #copilot #mcp #cli #typescript #codebase-analysis

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

公開者

jpoindexter

投稿者

Jason

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agentsmith": {
      "command": "npx",
      "args": [
        "-y",
        "@jpoindexter/agent-smith",
        "--mcp"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Agent Smith?

Agent Smith is a CLI tool that auto-generates an AGENTS.md file from your codebase. AGENTS.md is an open standard for giving AI coding assistants context about a project, adopted by 60,000+ projects and supported by tools like Cursor, GitHub Copilot, Claude Code, VS Code, and Gemini CLI. It's for developers who want a comprehensive, automatically maintained context file that AI tools read without any configuration.

How to use Agent Smith?

Run directly with npx @jpoindexter/agent-smith in your project directory or install globally with npm install -g @jpoindexter/agent-smith. Use agentsmith (default), or specify a directory with agentsmith ./my-project. Additional flags include --dry-run (preview without writing), --output <file> (custom output), --force (overwrite existing), and output mode flags: --compact, --compress, --minimal, --xml, and a file tree visualization.

Key features of Agent Smith

Scans codebase for components, hooks, API routes, and more
Detects frameworks like Next.js, shadcn/ui, and Prisma
Generates AGENTS.md with approximately 11K tokens by default
Multiple output modes: compact, compress, minimal, XML
Integrates automatically with AI coding tools (no config needed)
Supports dry-run preview and custom output file location

Use cases of Agent Smith

Quickly generate AGENTS.md for a new or existing project
Refresh AGENTS.md when code structure changes significantly
Create a minimal-context version for faster AI responses
Preview the generated file before writing it (dry run)
Generate an XML-format context file compatible with Repomix

FAQ from Agent Smith

What does Agent Smith generate?

It generates an AGENTS.md file—an open standard context file that AI coding tools automatically discover and read.

How does Agent Smith integrate with AI tools?

AI tools such as Cursor, GitHub Copilot, Claude Code, and VS Code automatically discover and read AGENTS.md files with no configuration needed.

Can I customize the output?

Yes. You can specify a custom output file (--output), choose a compact, compress, or minimal mode, output in XML format, or include a file tree. Use --dry-run to preview.

Do I need to install anything to run Agent Smith?

No. You can run it directly with npx @jpoindexter/agent-smith. Optionally, you can install it globally with npm install -g @jpoindexter/agent-smith.

What kinds of code structures does Agent Smith detect?

It detects components, component variants, color tokens, custom hooks, API routes, environment variables, the framework (e.g., Next.js App Router), design system patterns, code patterns, test coverage, barrel exports, hub files (most imported), Props types, and Prisma schema models.

「AI とエージェント」の他のコンテンツ

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K

Unreal Engine Generative AI Support Plugin

prajwalshettydev

Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti

622

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768