Ever stared at a new codebase written by others feeling completely lost? This tutorial shows you how to build an AI agent that analyzes GitHub repositories and creates beginner-friendly tutorials explaining exactly how the code works.

This is a tutorial project of Pocket Flow, a 100-line LLM framework. It crawls GitHub repositories and builds a knowledge base from the code. It analyzes entire codebases to identify core abstractions and how they interact, and transforms complex code into beginner-friendly tutorials with clear visualizations.

• Check out the YouTube Development Tutorial for more!

• Check out the Substack Post Tutorial for more!

  🔸 🎉 Reached Hacker News Front Page (April 2025) with >900 up‑votes: Discussion »

  🔸 🎊 Online Service Now Live! (May 2025) Try our new online version at https://code2tutorial.com/ – just paste a GitHub link, no installation needed!

🤯 All these tutorials are generated entirely by AI by crawling the GitHub repo!

• AutoGen Core - Build AI teams that talk, think, and solve problems together like coworkers!

• Browser Use - Let AI surf the web for you, clicking buttons and filling forms like a digital assistant!

• Celery - Supercharge your app with background tasks that run while you sleep!

• Click - Turn Python functions into slick command-line tools with just a decorator!

• Codex - Turn plain English into working code with this AI terminal wizard!

• Crawl4AI - Train your AI to extract exactly what matters from any website!

• CrewAI - Assemble a dream team of AI specialists to tackle impossible problems!

• DSPy - Build LLM apps like Lego blocks that optimize themselves!

• FastAPI - Create APIs at lightning speed with automatic docs that clients will love!

• Flask - Craft web apps with minimal code that scales from prototype to production!

• Google A2A - The universal language that lets AI agents collaborate across borders!

• LangGraph - Design AI agents as flowcharts where each step remembers what happened before!

• LevelDB - Store data at warp speed with Google's engine that powers blockchains!

• MCP Python SDK - Build powerful apps that communicate through an elegant protocol without sweating the details!

• NumPy Core - Master the engine behind data science that makes Python as fast as C!

• OpenManus - Build AI agents with digital brains that think, learn, and use tools just like humans do!

• PocketFlow - 100-line LLM framework. Let Agents build Agents!

• Pydantic Core - Validate data at rocket speed with just Python type hints!

• Requests - Talk to the internet in Python with code so simple it feels like cheating!

• SmolaAgents - Build tiny AI agents that punch way above their weight class!

• Showcase Your AI-Generated Tutorials in Discussions!

1. Clone this repository

   git clone https://github.com/The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge

2. Install dependencies:

   pip install -r requirements.txt
   npm install

   This project uses a Node.js sidecar for semantic code chunking through the code-chunk package, so a working Node.js/npm environment is required in addition to the Python dependencies. For OpenAI-compatible HTTP providers, you can set LLM_HTTP_TIMEOUT (seconds, default 120) to avoid indefinitely waiting on slow upstream responses. Abstraction discovery first asks the LLM to choose candidates from a compact chunk catalog (identify.compact_plan), then sends only selected evidence chunks for final refinement (identify.refine). If that compact path fails validation, the older batch extraction fallback can still be tuned with LLM_MAX_EXTRACTION_BATCHES (default 40) and LLM_EXTRACTION_CONCURRENCY (default 1), or the matching CLI flags --max-extraction-batches and --llm-extraction-concurrency. LLM call timing metrics are written as JSONL under logs/llm_metrics_YYYYMMDD.jsonl by default; set LLM_TELEMETRY_FILE to override the path or LLM_TELEMETRY=0 to disable it.

3. Set up LLM in utils/call_llm.py by providing credentials. To do so, you can put the values in a .env file. By default, you can use the AI Studio key with this client for Gemini Pro 2.5 by setting the GEMINI_API_KEY environment variable. If you want to use another LLM, you can set the LLM_PROVIDER environment variable (e.g. XAI), and then set the model, url, and API key (e.g. XAI_MODEL, XAI_URL,XAI_API_KEY). If using Ollama, the url is http://localhost:11434/ and the API key can be omitted. You can use your own models. We highly recommend the latest models with thinking capabilities (Claude 3.7 with thinking, O1). You can verify that it is correctly set up by running:

   python utils/call_llm.py

4. Generate a complete codebase tutorial by running the main script:

   # Analyze a GitHub repository
   python main.py --repo https://github.com/username/repo --include "*.py" "*.js" --exclude "tests/*" --max-size 50000
   
   # Or, analyze a local directory
   python main.py --dir /path/to/your/codebase --include "*.py" --exclude "*test*"
   
   # Generate a tutorial in Chinese by default
   python main.py --repo https://github.com/username/repo
   
   # Or, override the tutorial language
   python main.py --repo https://github.com/username/repo --language "English"

   • --repo or --dir - Specify either a GitHub repo URL or a local directory path (required, mutually exclusive)
   • -n, --name - Project name (optional, derived from URL/directory if omitted)
   • -t, --token - GitHub token (or set GITHUB_TOKEN environment variable)
   • -o, --output - Output directory (default: ./output)
   • -i, --include - Files to include (e.g., "*.py" "*.js")
   • -e, --exclude - Files to exclude (e.g., "tests/*" "docs/*")
   • -s, --max-size - Maximum file size in bytes (default: 100KB)
   • --language - Language for the generated tutorial (default: "Chinese")
   • --max-abstractions - Maximum number of abstractions to identify (default: 10)
   • --no-cache - Disable LLM response caching (default: caching enabled)

The application will crawl the repository, analyze the codebase structure, generate tutorial content in the specified language, and save the output in the specified directory (default: ./output).

• I built using Agentic Coding, the fastest development paradigm, where humans simply design and agents code.

• The secret weapon is Pocket Flow, a 100-line LLM framework that lets Agents (e.g., Cursor AI) build for you

• Check out the Step-by-step YouTube development tutorial: