# Overview

Lakehouse native graph engine with git-style workflows

Omnigraph is a lakehouse native graph engine built for context assembly. It acts as the operational state and coordination layer for agents, with git-style versioning and branching, multimodal retrieval, and object storage native deployment on the [Lance](https://github.com/lance-format/lance) format.

## Quick install

```
curl -fsSL https://raw.githubusercontent.com/ModernRelay/omnigraph/main/scripts/install.sh | bash
```

Or with Homebrew:

```
brew tap ModernRelay/tap
brew install ModernRelay/tap/omnigraph
```

New here? Follow the [install guide](/content/docs/getting-started/install/index.html), or clone a [starter cookbook](https://github.com/ModernRelay/omnigraph-cookbooks) to get a working graph with seed data in one command.

## Explore the docs

[**Getting started** \ 
Install Omnigraph and run your first graph.](/content/docs/getting-started/install/index.html) [**Schema** \ 
Model your domain with typed .pg schemas, enforced on every write.](/content/docs/schema/index.html) [**Queries & data** \ 
Query, branch, commit, and diff. Version data like code.](/content/docs/queries-search/queries/index.html) [**Deploy & operate** \ 
Run it on your laptop, your own servers, or your cloud.](/content/docs/getting-started/deployment/index.html) [**Security** \ 
Cedar policy enforced in-engine, with full actor audit.](/content/docs/operations/policy/index.html) [**Reference** \ 
Every CLI flag, error code, and tunable.](/content/docs/cli/reference/index.html)

[Quickstart\ 
\ 
This walks the core loop end to end: define a schema, initialize a graph, load data, query it, and use a branch. It uses a local file-backed graph.](/content/docs/getting-started/quickstart/index.html)
