Understand
Your Codebase
A local-first code intelligence engine that indexes your projects into a searchable knowledge graph — no cloud, no Postgres, no setup friction.
The Problem
AI agents shouldn't have to re-read everything
Every time an AI coding agent starts a conversation, it reads your source files from scratch — burning tokens, context, and time on the same code it already saw yesterday.
Wasted token budget
50–200K tokens per session spent re-parsing files your agent has already analyzed. That's your context window — and your budget — gone before real work begins.
No persistent understanding
Your agent's 'memory' resets every conversation. Without a durable code index, it can't build on past queries, track relationships, or produce consistently accurate results.
Cloud dependency risk
Most code intelligence tools send your source code to cloud APIs. That's a non-starter for proprietary codebases, regulated environments, or anyone who values data privacy.
Shallow indexing
Simple text search isn't enough. Understanding code requires AST-level parsing, symbol graphs, and cross-file relationship tracking — capabilities most tools don't localize.
Index Anything
Every language you use
Rich AST-level indexing for TypeScript and JavaScript. Symbol extraction for Python, Go, and Rust. Structure-aware chunking for config files and documentation.
See it in action
What it looks like
A 3D knowledge graph of your codebase. Symbols are nodes, relationships are edges. Pan, orbit, zoom — explore how your code fits together.
Architecture
How it works
Init & Index
Run `openez init` to register a workspace. The indexer parses your codebase into documents, chunks, graph nodes, and edges — stored locally in SQLite (WAL mode).
Query & Explore
Full-text search across all chunks, expanded through graph neighbor traversal. Visualize relationships in the 3D graph explorer or query via the CLI.
Connect & Automate
Expose your indexed runtime through MCP for AI agents, the CLI for scripts, or the web dashboard. All three point at the same SQLite store.
Capabilities
What you get
Semantic Indexing
TS/JS gets full AST-level indexing via ts-morph. Python, Go, Rust get top-level symbol extraction. Docs and config files get structure-aware chunking — all stored in local SQLite.
FTS + Graph Retrieval
Full-text search across all chunks, expanded through graph neighbor traversal. Optional embedding reranking — no vector database required for the default path.
Knowledge Graph
Every indexed symbol becomes a node. Every import, reference, and relationship becomes an edge. Explore the graph in 3D from the web dashboard.
Incremental & Watch
Index only what changed with incremental mode. Or run `openez watch` and let chokidar re-index files automatically on every save.
MCP Protocol
Expose any indexed workspace through the Model Context Protocol. AI agents (Claude, Codex, OpenCode) can query your codebase natively through MCP tools.
Editor Integrations
One command to wire up: `openez setup claude`, `openez setup codex`, or `openez setup opencode`. No manual JSON editing.
Quick Start
Ship faster, type less
Seven commands to manage your entire code intelligence workflow.
AI Integration
Plug into any AI agent
OpenEZ implements the Model Context Protocol — the standard for connecting AI coding agents to local tools. Add one entry to your MCP config and every Claude or Codex session gets instant codebase understanding.
~/.config/claude/mcp.json
Works with:
- Claude Desktop / CodeMCP-native, no plugins needed
- GitHub CodexConnect via openez setup codex
- OpenCode / CursorDrop-in MCP server config
Everywhere you need it
Three ways to connect
CLI
- pnpm openez init
- pnpm openez query
MCP Server
- openez serve --mcp
- Connect AI agents
- Claude, Codex, OpenCode
Web Dashboard
- Workspace management
- 3D graph explorer
- Settings & jobs