Nomik is an AI-native code intelligence graph. It transforms your codebase into Neo4j and connects directly to AI agents via MCP.
# NOMIK — The Living Blueprint > **⭐⭐ If you find NOMIK useful, please consider giving it a star on GitHub! It helps the project grow! ⭐⭐** > **Follow the creator on X: [@willfreed01](https://x.com/willfreed01) | Website: [hamzabenjeddi.com](https://hamzabenjeddi.com/)** > **AI-native code intelligence graph. Scan once, query everything.** NOMIK builds a persistent **Knowledge Graph** of your entire codebase in Neo4j, then exposes it to AI assistants via **MCP** (Model Context Protocol). Instead of dumping files into a prompt, the AI queries a graph to retrieve exactly the relationships it needs — functions, classes, imports, call chains, DB operations, infrastructure, and more. ## Quick Start ```bash # Prerequisites: Node.js 20+, Docker npm install -g @nomik-ai/cli cd your-project/ nomik init # Config + Neo4j Docker + .env + project setup nomik scan . # Build the knowledge graph nomik setup-cursor # Connect to your IDE (or: setup-windsurf, setup-cursor) nomik watch . # (Optional) Live graph updates on save ``` Restart your IDE — the AI now has full graph-powered context. ## MCP Tools (21) Your AI assistant gets these tools automatically: | Tool | Purpose | Example | |---|---|---| | `nm_search` | Find symbols by name | "Find all auth functions" | | `nm_context` | Full context for a symbol | "Show everything about `GraphService`" | | `nm_impact` | Downstream impact analysis | "What breaks if I change `parseFile`?" | | `nm_db_impact` | DB table/column read/write analysis | "Who writes to users.email?" | | `nm_explain` | Symbol deep-dive (callers, callees, edges) | "Explain `createGraphService`" | | `nm_health` | Stats + health checks (17 node types) | "Any dead code or god files?" | | `nm_path` | Shortest path between two symbols | "How does `scanCommand` reach `neo4j`?" | | `nm_trace` | Full dependency chain | "Trace from A to B" | | `nm_changes` | Recently modified nodes
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.