Egonex-AI/Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

What it solves

It solves the problem of "reading code blind" when entering a large, unfamiliar codebase or knowledge base. Instead of manually tracing thousands of lines of code, it provides a visual, interactive way to understand how files, functions, classes, and business logic fit together.

How it works

The project uses a hybrid approach combining deterministic static analysis with semantic LLM analysis:

  • Tree-sitter is used for deterministic parsing to extract structural facts like imports, exports, and definitions.
  • A Multi-Agent Pipeline (consisting of specialized agents for scanning, file analysis, architecture, tours, and review) uses LLMs to generate plain-English summaries, identify architectural layers, and map business domains.
  • Knowledge Graph: The results are stored as a JSON graph, which can be visualized via an interactive web dashboard.
  • Incremental Updates: It tracks changes to files so that only modified code is re-analyzed in subsequent runs, saving tokens.

Who it’s for

  • Developers joining a new team or working in a massive monorepo who need to onboard quickly.
  • Project Managers who want to see how code maps to business processes without reading source code.
  • Maintainers who need to perform diff impact analysis to see how changes ripple through a system.
  • Knowledge Base Curators who want to turn wiki-style documentation into a navigable graph of ideas.

Highlights

  • Interactive Dashboard: A visual graph where nodes can be clicked and searched to see summaries and relationships.
  • Domain View: Maps code to real-world business processes, flows, and steps.
  • Guided Tours: Auto-generated architectural walkthroughs ordered by dependency.
  • Multi-Platform Support: Works as a plugin for Claude Code, Cursor, VS Code Copilot, Gemini CLI, and several other AI coding tools.
  • Diff Impact Analysis: Visualizes which parts of the system are affected by current changes before committing.

Related

  • Project
    CodeBoarding/CodeBoarding

    A tool that combines static analysis and LLM reasoning to generate visual architecture maps and documentation for codebases, helping developers and AI agents maintain system context.

  • Project
    Graphify-Labs/graphify

    A tool that maps codebases, docs, and media into a knowledge graph, allowing developers to query relationships and trace paths between concepts instead of grepping files.

  • Project
    FSoft-AI4Code/CodeWiki

    CodeWiki is an open‑source Python framework that uses LLMs (OpenAI, Anthropic, Azure, Bedrock, Atlas Cloud, or Claude/Codex subscription) to automatically generate comprehensive, architecture‑aware documentation—including markdown and Mermaid diagrams—for large, multi‑language codebases. It features hierarchical decomposition, recursive multi‑agent processing, configurable token limits, incremental updates, and GitHub‑Pages‑ready output.