Turn any codebase, knowledge base, or docs into an interactive knowledge graph you can explore, search, and ask questions about.
Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Español | Türkçe | Русский
💬 Join the Discord community →
Ask questions, share what you've built, get help from the community.
You just joined a new team. The codebase is 200,000 lines of code. Where do you even start?
Understand Anything is a Claude Code Plugin that analyzes your project with a multi-agent pipeline, builds a knowledge graph of every file, function, class, and dependency, then gives you an interactive dashboard to explore it all visually. Stop reading code blind. Start seeing the big picture.
The goal isn't a graph that wows you with how complex your codebase is — it's a graph that quietly teaches you how every piece fits together.
Note
Want to skip the reading? Try the live demo in our homepage — a fully interactive dashboard you can pan, zoom, search, and explore right in your browser.
Navigate your codebase as an interactive knowledge graph — every file, function, and class is a node you can click, search, and explore. Select any node to see plain-English summaries, relationships, and guided tours.
Switch to the domain view and see how your code maps to real business processes — domains, flows, and steps laid out as a horizontal graph.
Point /understand-knowledge at a Karpathy-pattern LLM wiki and get a force-directed knowledge graph with community clustering. The deterministic parser extracts wikilinks and categories from index.md, then LLM agents discover implicit relationships, extract entities, and surface claims — turning your wiki into a navigable graph of interconnected ideas.
|
Auto-generated walkthroughs of the architecture, ordered by dependency. Learn the codebase in the right order. |
Find anything by name or by meaning. Search "which parts handle auth?" and get relevant results across the graph. |
|
See which parts of the system your changes affect before you commit. Understand ripple effects across the codebase. |
The dashboard adjusts its detail level based on who you are — junior dev, PM, or power user. |
|
Automatic grouping by architectural layer — API, Service, Data, UI, Utility — with color-coded legend. |
12 programming patterns (generics, closures, decorators, etc.) explained in context wherever they appear. |
git clone https://github.com/user/Understand-Anything-794.git
cd Understand-Anything-794
pip install -r requirements.txt
python setup.pyNote: Setup script handles all configuration automatically.bash copilot plugin install Lum1104/Understand-Anything:understand-anything-plugin
git clone https://github.com/user/Understand-Anything-794.git
cd Understand-Anything-794
pip install -r requirements.txt
python setup.pyNote: Setup script handles all configuration automatically.gitignore .understand-anything/intermediate/ .understand-anything/diff-overlay.json
**Keep it fresh:** enable `/understand --auto-update` — a post-commit hook incrementally patches the graph so each commit lands with a matching graph. Or re-run `/understand` manually before releases.
**Large graphs (10 MB+):** track with **git-lfs**.
```bash
git lfs install
git lfs track ".understand-anything/*.json"
git add .gitattributes .understand-anything/
Static analysis and LLMs do what each does best:
- Tree-sitter (deterministic) — parses source into a concrete syntax tree and extracts structural facts: imports, exports, function/class definitions, call sites, inheritance. Pre-resolved into an
importMapduring the scan phase and passed to file-analyzers so they don't re-derive imports from source. Same input → same output, every run. Also powers fingerprint-based change detection for incremental updates. - LLM (semantic) — reads the parsed structure alongside the original source to produce what parsers can't: plain-English summaries, tags, architectural layer assignments, business-domain mapping, guided tours, language concept callouts.
This split is why the graph is reproducible on the structural side (the same code always yields the same edges) while still capturing intent on the semantic side (what a file is for, not just what it imports).
The /understand command orchestrates 5 specialized agents, and /understand-domain adds a 6th:
| Agent | Role |
|---|---|
project-scanner |
Discover files, detect languages and frameworks |
file-analyzer |
Extract functions, classes, imports; produce graph nodes and edges |
architecture-analyzer |
Identify architectural layers |
tour-builder |
Generate guided learning tours |
graph-reviewer |
Validate graph completeness and referential integrity (runs inline by default; use --review for full LLM review) |
domain-analyzer |
Extract business domains, flows, and process steps (used by /understand-domain) |
article-analyzer |
Extract entities, claims, and implicit relationships from wiki articles (used by /understand-knowledge) |
File analyzers run in parallel (up to 5 concurrent, 20-30 files per batch). Supports incremental updates — only re-analyzes files that changed since the last run.
A community-made walkthrough by Better Stack.
Made a video, blog post, or tutorial? Open an issue or PR — happy to feature it here.
Contributions are welcome! Here's how to get started:
- Fork the repository
- Create a feature branch (
git checkout -b feature/my-feature) - Run the tests (
pnpm --filter @understand-anything/core test) - Commit your changes and open a pull request
Please open an issue first for major changes so we can discuss the approach.
Stop reading code blind. Start understanding everything.
Thanks to everyone who's used and contributed — knowing this saves people time is what made it worth building.
MIT License © Lum1104