Egonex-AI /
Understand-Anything
Turns a codebase or wiki into an interactive graph you can search and ask questions about
- 87.7k stars
- 2.7k stars since 3 Oct
- TypeScript
- Updated today
- Beginner friendly
- Coding agents & dev tools
Joining a big codebase is slow because you don't know where to start. Understand Anything runs a multi-agent pipeline over your project and saves a knowledge graph as a JSON file. Each file, function, class and dependency becomes a node you can click, with a plain-English summary and its relationships.
You use it through slash commands inside your AI coding tool. /understand builds the graph, /understand-dashboard opens it in the browser, and commands like /understand-chat and /understand-explain let you ask questions about the code. Later runs only re-analyze changed files, so they use fewer tokens than the first run, which can be costly on large projects.
The graph is plain JSON, so you can commit it and teammates can open the dashboard without an LLM or API key. It started as a Claude Code plugin, and the README lists installers for Codex, Cursor, Copilot, Gemini CLI, OpenCode and others. It can also build a graph from a Karpathy-style LLM wiki.
What it does
Interactive structural graph
Every file, function and class is a node you can click and search. Selecting one shows a summary, its relationships and its code.
Guided tours and layers
It generates architecture walkthroughs ordered by dependency. Nodes are grouped into layers such as API, Service, Data, UI and Utility.
Search by name or meaning
Fuzzy and semantic search lets you ask which parts handle auth and get matching results across the graph.
Diff impact analysis
/understand-diff shows which parts of the system your current changes affect before you commit.
Business domain and wiki views
/understand-domain maps code to domains, flows and steps. /understand-knowledge builds a graph from an LLM wiki.
What you could build
- Map an unfamiliar codebase on your first week with a new team.
- Ask questions about how a feature such as a payment flow works.
- Check which parts of the system a change touches before committing.
- Generate an onboarding guide for new team members.
- Commit the graph so teammates can browse it without running the pipeline.
Get started
Install the plugin in Claude Code, then run /understand in your project to build the graph. Run /understand-dashboard to explore it. Other tools use the one-line install.sh script listed in the README.
/plugin marketplace add Egonex-AI/Understand-Anything/plugin install understand-anything/understandCommands are copied from the project's README. Read it on GitHub for the full setup.
More in Coding agents & dev tools
rea
MCP server that lets AI agents reverse engineer apps, binaries and websites locally
opencode
Open source AI coding agent for your terminal, with a beta desktop app
claude-code
Terminal coding assistant that reads your codebase and takes plain-English commands
codex
A coding agent from OpenAI that runs in your terminal on your own machine
pi
A minimal terminal coding agent you extend with skills, extensions and packages
orca
Desktop and mobile app for running many coding agents side by side
screenshot-to-code
Turns screenshots, mockups and screen recordings into front-end code with AI models
warp
Rust terminal that adds a built-in coding agent and runs other CLI agents
free-claude-code
Local proxy that lets Claude Code, Codex, Aider and others run on free or cheap models
CLI-Anything
Generates command-line wrappers so AI agents can drive desktop and web software