v1.7.1local-first RAG

Durable context for coding agents

Index code once. Let Codex, Claude, OpenCode, Windsurf, and Devin retrieve ranked code, graph context, and project memory from local SQLite.

npx @openez-graph/cli setup codex
MCP tools
0
Indexed formats
0
Agent setups
0
Local database
0

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.

Architecture

How it works

  1. 01

    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).

  2. 02

    Query & Explore

    Full-text search across indexed chunks, expanded through graph neighbor traversal. Inspect relationships in the graph explorer or retrieve focused context through MCP.

  3. 03

    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.

CLI
init, index, status, watch, serve, setup
local state
SQLite Runtime
registry + workspace DBs, FTS + graph + memory
shared by
MCP + Dashboard
agent tools, telemetry, graph inspection

See it in action

What it looks like

Inspect workspace state, measured MCP query telemetry, memories, documents, and symbol relationships from one local management UI.

openez — local dashboard
Loading graph…

Real graph sample from the openez repo

Capabilities

What you get

Semantic Indexing

TS/JS get full AST-level indexing via oxc-parser. Python, Go, Rust, Ruby, C++, C#, and Java get language-aware AST parsing with native acceleration where available. Docs and config files get structure-aware chunking — all stored in local SQLite.

Hybrid RAG Retrieval

Full-text search, exact symbol and file-name matching, and graph expansion along call and import edges, plus optional vector embeddings (bge-m3 / OpenAI) fused via Reciprocal Rank Fusion. No external vector DB required.

See the benchmark →

Knowledge Graph

Indexed symbols become nodes connected by imports, references, and other code relationships. Inspect the workspace graph from the local dashboard.

Automatic sync

The MCP runtime auto-registers and indexes a project, then keeps it current as files change. Manual incremental, watch, and full reindex commands remain available.

10 MCP tools

Give agents ranked retrieval, file outlines, graph context, git-diff impact, durable memory, and workspace controls through a focused MCP tool surface.

Five agent integrations

One setup command connects Codex, Claude Code, OpenCode, Windsurf, or Devin. OpenEZ writes the right config, so you do not have to.

Index Anything

Every language you use

Twenty formats, indexed at the depth each one supports.

Rich AST

Symbols and binding-resolved call edges via oxc-parser.

TypeScriptJavaScript

Language-aware AST

Tree-sitter symbols with native acceleration where available. Python, Go, Rust, and Ruby also fall back to regex.

PythonGoRustRubyC++C#Java

Scanned & chunked

Searchable through fallback chunking, without symbol extraction.

CoffeeScriptSlimCSSSCSSSASSLESSHaml

Structure-aware

Config and docs are chunked by their keys and sections.

YAMLJSONTOMLMarkdown

Quick Start

Install once. Pick your agent.

Setup writes the agent config, registers the current project, indexes it, and keeps the workspace synced while MCP is running.

  1. 1

    Install the CLI

    npm install -g @openez-graph/cli
  2. 2

    Connect your agent

    openez setup codex .
  3. 3

    Check the index

    openez status .

Give your agent durable context

Index once, query forever. Everything stays on your machine in local SQLite.

npx @openez-graph/cli setup codex