Ever stared at a new codebase written by others feeling completely lost? This tutorial shows you how to build an AI agent that analyzes local codebases 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 local directories 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!
-
Clone this repository
git clone https://github.com/The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge
-
Install dependencies:
pip install -r requirements.txt
-
LLM mode is file-based by default in
utils/call_llm.py:- For each step, prompt/response files are generated under
workspace/llm/<project_name>/prompts/andworkspace/llm/<project_name>/responses/. - The process emits a machine-readable signal line:
[LLM_SIGNAL]{"type":"llm_manual_request","prompt_path":"...","response_path":"..."}
- An agent should read
prompt_path, write a response toresponse_path, and the runner automatically continues once the file is non-empty. - Consent is asked once per run (when enabled), then subsequent steps proceed automatically.
- Prompt/response files use stable step names (for example
identify_abstractions.txt,write_chapter_01.txt) so reruns can auto-skip steps when response files already exist. You can verify manual mode by running:
python utils/call_llm.py
- For each step, prompt/response files are generated under
-
Configure run settings in YAML:
# configure_args.yaml local_dir: /path/to/your/codebase project_name: my-project include_patterns: - "*.py" exclude_patterns: - "tests/*" output_dir: output language: english max_file_size: 100000 use_cache: true max_abstraction_num: 10 llm_require_consent: false llm_show_prompt: false log_dir: workspace/logs llm_cache_file: workspace/cache/llm_cache.json llm_manual_dir: workspace/llm llm_manual_poll_interval_s: 2.0 llm_manual_timeout_s: 0 llm_redact_logs: true
- Edit this YAML file directly before running.
-
Run the full pipeline:
python main.py
RunConfigloads and shows the effective YAML config, then asks for final approval before crawling starts.
-
Manual mode behavior:
- No terminal paste is required.
- The app writes prompt files and automatically waits/polls for matching response files.
LLM_SIGNALlines provide exact prompt/response paths for agent automation.- LLM cache is project-scoped under
workspace/cache/<project_name>/(derived fromllm_cache_filebase name). - Polling can be configured in YAML with
llm_manual_poll_interval_sandllm_manual_timeout_s.
-
Prompt for your terminal agent:
- See
PROMPT_INIT.md.
- See
The application reads project settings from YAML, crawls the configured local directory, analyzes the codebase structure, generates tutorial content, and saves output to the configured output directory.
🐳 Running with Docker
To run this project in a Docker container, manual mode is the default and no API key is required.
-
Build the Docker image
docker build -t pocketflow-app . -
Run the container
This project uses manual mode. Prompts are written to files, then you write model responses to matching response files.
Mount a local directory to
/app/outputinside the container to access the generated tutorials on your host machine.Example for analyzing a local directory:
docker run -it --rm \ -v "/path/to/your/local_codebase":/app/code_to_analyze \ -v "$(pwd)/workspace":/app/workspace \ -v "$(pwd)/output_tutorials":/app/output \ pocketflow-app
-
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:
