Download
PocketFlow Tutorial Codebase Knowledge is a project that demonstrates how to build an AI agent capable of analyzing arbitrary codebases and generating beginner-friendly tutorials that explain how they work, turning complex source code into clear educational content. The repository builds on a lightweight 100-line LLM framework and uses natural language models to inspect repository structures, identify core abstractions, map dependencies, and articulate the reasoning behind code design and interactions. By crawling code files, extracting higher-level patterns, and using large language models to narrate explanations, the system aims to help developers — especially those new to a codebase — understand unfamiliar projects without manual deep reading. It supports both GitHub URL crawling and local directory analysis, and can tailor output tutorials to different languages, making it accessible for international developers.
Features
- AI-driven codebase analysis and tutorial generation
- Supports GitHub repository crawling or local paths
- Inclusion/exclusion file patterns for customization
- Multi-language tutorial output
- Lightweight LLM framework underpinning analysis
- Scriptable output and configuration options
Project Samples
