Object-storage native graph database with branching and typed ontology

★ 2,700⑂ 322👁 25⑃ 1,115● 298▤ 55
RustMITCreated 2026-04-10omnigraph.dev
Download: v0.15.0v0.15.0 ↓0.15.02026-11-09
+213
Daily
2,700
stars
322
forks
25
watchers
1,115
prs
298
issues
55
releases

README

Object-storage native graph database with branching and typed ontology.
  Unified retrieval engine (vector/BM25/graph) · Git-style workflows · Open data format (Lance)



  Quickstart  · 
  Docs  · 
  Cookbooks  · 
  CLI  · 
  Studio  · 
  llms.txt



  
  



  




Omnigraph is engineered for the new workload introduced by long-horizon agents: multiple agents sharing a typed world model to continuously retrieve and update context and coordinate work. Agents and UIs can become thin stateless consumers of durable state.

Omnigraph Cloud is in private preview: join the waitlist.

Join the Omnigraph Slack community to ask questions, share feedback, and follow development.

 Capabilities

| Capability | What it gives you |
|---|---|
| Typed ontology | Agents share one enforceable model of the domain. .pg schemas declare node and edge types, keys and constraints, and the engine enforces them on every write. |
| Multimodal retrieval | Agents assemble high-precision & recall context in one query: graph traversal + vector ANN + full-text + Reciprocal Rank Fusion in one runtime, with filtering. |
| Branching | Agents propose reviewable changes instead of writing to main: a branch per agent or task, three-way merge, time travel across the whole graph. |
| Declared as code | A cluster.yaml declares graphs, schemas, stored queries, embedding providers and policies. cluster plan previews, cluster apply converges, Terraform-style. |
| Security as code | Cedar policy enforced server-side on every mutation, per graph or server-wide; bearer auth, server-resolved actors, audit tracking. |
| Object-storage native, open format | Decoupled storage and compute. Store graphs on local disk or S3-compatible storage: RustFS / MinIO, AWS S3 / R2, or Azure preview. Graph data uses open, versioned Lance, including Blob values. |

 What you can build

| Use case | What it's for |
|---|---|
| Company brain | Org knowledge unified into one graph every agent can query |
| Agentic memory | Durable, versioned memory: a branch per agent or per task, merged on review |
| Context graph | Decision traces and codified tribal knowledge for retrieval |
| Dev graph | Issues & dependency model that coding agents read and write |
| R&D / ML data layer | Experiments and trials written into branches, versioned for training & eval |

 Install

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


This installs omnigraph (CLI) and omnigraph-server into ~/.local/bin from
published release binaries. Or with Homebrew:

bash
brew tap ModernRelay/tap
brew install ModernRelay/tap/omnigraph


 Studio

Omnigraph Studio is the desktop app for your graphs. Browse each type as
a table, follow relationships on a canvas, write queries with the compiler's
errors as you type, and review what a branch changes before you merge it. It is
a native Rust app on GPUI, the framework behind Zed, for macOS, Windows and

Top issues

Latest release

v0.15.0 v0.15.0 2026-11-09
Omnigraph 0.15 has five main highlights. Loading a large dataset into a new graph takes less than half the time it took in 0.14. Reads no longer wait for writes to commit. Most branch diffs and merges cost what changed, not how big the tables are or how long the history is. MCP agents get every graph operation, and your Cedar policy alone decides what each agent may run. S3 clusters close three ways in which two servers could write at once.

This release changes what MCP agents may call, how @card minimums and @unique are checked, managed organization commands, saved plans and a Rust error typ

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON