方法论 | 计算机基础教程

# 方法论

AI Code Guide is a roadmap to start coding with AI (opens new window)

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement. (opens new window)

泄露的Claude code (opens new window)

Step 1: Choose the type of server you want Choose one of these URL formats depending on what you want to connect to:

For GitHub repositories: gitmcp.io/{owner}/{repo} For GitHub Pages sites: {owner}.gitmcp.io/{repo} For a generic tool that supports any repository (dynamic): gitmcp.io/docs Replace {owner} with the GitHub username or organization name, and {repo} with the repository name.

Step 2: Connect your AI assistant Select your AI assistant from the options below and follow the configuration instructions:

Connecting Cursor
Update your Cursor configuration file at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "gitmcp": {
      "url": "https://gitmcp.io/{owner}/{repo}"
    }
  }
}
Connecting Claude Desktop
In Claude Desktop, go to Settings > Developer > Edit Config
Replace the configuration with:
{
  "mcpServers": {
    "gitmcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://gitmcp.io/{owner}/{repo}"
      ]
    }
  }
}
Connecting Windsurf
Update your Windsurf configuration file at ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "gitmcp": {
      "serverUrl": "https://gitmcp.io/{owner}/{repo}"
    }
  }
}
Connecting VSCode
Update your VSCode configuration file at .vscode/mcp.json:

{
  "servers": {
    "gitmcp": {
      "type": "sse",
      "url": "https://gitmcp.io/{owner}/{repo}"
    }
  }
}
Connecting Cline
Update your Cline configuration file at ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:

{
  "mcpServers": {
    "gitmcp": {
      "url": "https://gitmcp.io/{owner}/{repo}",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Connecting Highlight AI
Open Highlight AI and click the plugins icon (@ symbol) in the sidebar
Click Installed Plugins at the top of the sidebar
Select Custom Plugin
Click Add a plugin using a custom SSE URL
Plugin name: gitmcp SSE URL: https://gitmcp.io/{owner}/{repo}

For more details on adding custom MCP servers to HighlightAI, refer to the documentation.

Connecting Augment Code
Open Augment Code settings
Navigate to the MCP section
Add a new MCP server with the following details:
Name the MCP server: git-mcp Docs

Use this command:

npx mcp-remote https://gitmcp.io/{owner}/{repo}
Or use the following configuration:

{
  "mcpServers": {
    "git-mcp Docs": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://gitmcp.io/{owner}/{repo}"
      ]
    }
  }
}
Connecting Msty AI
Open Msty Studio
Go to Tools > Import Tools from JSON Clipboard
Paste the following configuration:
{
  "mcpServers": {
    "git-mcp Docs": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://gitmcp.io/{owner}/{repo}"
      ]
    }
  }
}

# 2. 方法2

STEP 1: Injest code - Turn any Git repository into a simple text digest of its codebase. (opens new window)

STEP 2: Feed previous result(Directory Structure AND File Content) to LLM

STEP 3: Give requirement

# Protocol

Model Context Protocol vs Function Calling:

Model Context Protocol Clearly Explained (opens new window)

Sample MCP client (opens new window) Google maps MCP server (opens new window) MCP Schema (opens new window) Simple tool, resource, prompt servers (opens new window) Example servers (opens new window) MCP inspector (postman like tool) (opens new window)

# coding

codex
- CodexPlusPlus (opens new window)
- cc-switch (opens new window)
antigravity (opens new window)
CodeGPT/Continue+ollama/groq
GitHub Copilot https://github.com/google-gemini/gemini-cli

阿里百炼多模态

GitHub Copilot Workspace

编程助手 codey

OpenAI's Code Interpreter open-interpreter https://github.com/lyhistory/tools_aigc_open-interpreter

AutoGLM: Autonomous Foundation Agents for GUIs (opens new window)

Omni Engineer：无需等待，几秒内生成应用程序！（支持 Ollama & Code Agent ） (opens new window)

Open Interpreter lets LLMs run code (Python, Javascript, Shell, and more) locally. (opens new window)

OpenDevin (opens new window)

A framework to enable multimodal models to operate a computer (opens new window)

# UI

https://typedream.com/ 前端v0.dev (opens new window)

Google lab stitch

Draw a ui and make it real https://github.com/tldraw/make-real

# GPT+DB

An intelligent and versatile general-purpose SQL client and reporting tool for databases which integrates ChatGPT capabilities.(智能的通用数据库SQL客户端和报表工具) https://github.com/chat2db/Chat2DB

# GPT GAMES World

虚拟世界的人 Generative Agents: Interactive Simulacra of Human Behavior https://github.com/joonspk-research/generative_agents

# hardware

Create hardware prototype designs by chatting with AI (opens new window)

LeRobot: Making AI for Robotics more accessible with end-to-end learning (opens new window)

LeKiwi - Low-Cost Mobile Manipulator (opens new window)

玩转树莓派4B-部署LLM大模型-1 (opens new window)

A wireless mod for the TI-84 (not CE). (opens new window)

# open glass

Turn any glasses into AI-powered smart glasses (opens new window)

# GPT+Eyes

https://www.youtube.com/watch?v=w-wxguIs-0I

# GPT Robot

https://hackaday.io/project/189041-a-workbench-companion-from-an-amazon-echo-dot https://www.youtube.com/watch?v=bO-DWWFolPw&embeds_referring_euri=https%3A%2F%2Fhackaday.io%2F&source_ve_path=MjM4NTE&feature=emb_title

花60元，DIY了一个AI机器人，能聊天，会认人…… (opens new window)