Personal project 2026 published
Nomik: AI-Native Code Intelligence Powered by a Knowledge Graph
I built Nomik because AI coding assistants read your code but they don't understand it. Nomik scans any codebase and builds a persistent Neo4j knowledge graph, giving AI assistants the structural context to reason across functions, routes, DB writes, and imports not just text.
The problem. When you ask Cursor or Claude to refactor a function, it reads your files. It doesn’t understand your codebase. It guesses relationships, misses queue consumers, overlooks DB writes and confidently suggests changes that silently break things elsewhere. The root cause isn’t the model. It’s that AI reads files. It needs to understand graphs.
What I built. Nomik is an open-source CLI that scans any codebase once and builds a persistent knowledge graph in Neo4j every function, route, database operation, cron job, and import becomes a node or edge. Your AI queries that graph directly through 21 MCP tools instead of grepping raw files.
The result. Ask “what breaks if I rename processPayment?” and instead of a guess you get: 5 callers, 2 DB tables, 1 cron job — with exact file paths and line numbers. Ask “where is auth handled?” and get the full chain from route → middleware → session store.
Why it matters. On large TypeScript monorepos I kept hitting the same wall: the AI would confidently suggest refactors that broke things it didn’t know existed — a queue consumer calling the same function, a retry job hitting the same DB write. Context delivery was the bottleneck. A knowledge graph fixes that permanently.
Technical scope. Nomik supports 7 languages, extracts 37 node types, and exposes 33 CLI commands. It runs entirely locally — no code leaves your machine. It connects to Cursor, Windsurf, Claude Desktop, and Antigravity with a single command: nomik setup-cursor.
