Free & open source

Larkx: A queryable graph of your codebase for AI agents.

larkx indexes any project into a compact graph that Claude Code, Cursor, GitHub Copilot, and any MCP-compatible AI client can read in seconds. Measured savings on the larkx repo: 49% fewer tokens on a high-level overview query verified by larkx bench, not estimated.

$ npm install -g larkx
49%
fewer AI tokens*
6
MCP tools
8
language families
8
frameworks
* Real number, measured by larkx bench on the larkx repo (101K → 52K tokens, $0.1565 → $0.0903). Run it on your own project for your number.
From zero to indexed in three commands
terminal
What's included

Nine focused features. No marketing fluff.

Tiered context

Four detail levels: paths, symbols, signatures, AI summaries. The AI picks the cheapest level per task.

Folder scoping

Restrict any query to a subtree. Token cost drops roughly in proportion to the folder size, often very large savings on focused tasks.

AI summaries

One-line summaries per file generated by your configured provider: Local Claude or the Anthropic API. Cached locally in .larkx/summaries.json.

MCP-native

Works with Claude Code, Cursor, Continue, Cline, and any Model Context Protocol client.

Reachability dead code

BFS from entry points. Auto-detects Next.js routes, NestJS modules, and more.

Incremental indexing

SHA-256 file hashing. Reindex is typically much faster after the first build.

Visual graph UI

Browser explorer with Module view and Graph view. Zoom, search, VS Code deep links.

Security defaults

Excludes .env, *.key, *.pem, credentials* by default. Never enters AI context.

Zero config

larkx init walks through AI summaries, MCP setup, agent files, and Claude Code hooks.

How many tokens does your project actually save?

larkx bench runs Claude with and without larkx and reports real token usage — not estimates.

See benchmark docs

Two commands. Five minutes.

Install, init, index, done. No accounts. No telemetry. Runs entirely on your machine.

Read the setup guide