larkx indexes your codebase once and exposes a compact graph through MCP. Claude Code reads only the detail level it needs, often reducing token usage substantially, and focused tasks can save much more.
Without a structured index, Claude reads raw source files to understand your project. A 300-file TypeScript repo can cost ~480K tokens just to orient itself, before writing a single line of code. That adds up fast.
| Level | What you get | Typical cost | Best for |
|---|---|---|---|
| Level 1 | File paths | ~1–2K tokens | Navigation, find a file |
| Level 2 | Symbols | ~8–10K tokens | Find a function, list exports |
| Level 3 | Signatures | ~16K tokens | Understand an API surface |
| Level 4 | AI summaries | ~24K tokens | Deep understanding, refactoring |
| Without larkx | Raw source files | ~480K tokens | Everything, every time |
npm install -g larkxcd my-project && larkx initlarkx indexlarkx serveFull codebase map at any detail level. Claude picks Level 1–4 based on what the task needs.
Find any function, class, or export across the codebase in one call.
See what breaks if a function changes, call graph traversal, not guessing.
BFS from entry points to surface unreachable code before it ships.
Why does Claude Code use so many tokens?
Claude Code reads source files directly. On a larger project, reading the full codebase can consume hundreds of thousands of tokens in a session. larkx replaces that with a compact graph, and Claude can pick the detail level it needs instead of reading whole files.
How does larkx connect to Claude Code?
larkx runs as an MCP (Model Context Protocol) server. larkx init writes the .mcp.json config automatically and creates a CLAUDE.md so Claude knows which tools to call.
Will larkx break my existing Claude Code setup?
No. larkx adds to your setup - it does not replace any existing MCP servers or configuration. You can remove it any time by deleting .mcp.json.
Does larkx send my code anywhere?
No. larkx runs entirely on your machine. The index is stored locally in .larkx/. No telemetry, no cloud upload.
How long does indexing take?
Initial index: under 60 seconds for most projects. Re-indexing is near-instant because larkx only processes changed files using SHA-256 hashing.
Free and open source. Works with any project.