An agent reads the graph as context.
Agent asksGraph returns
Who knows X?5 people
What changed?12 commits
What's related?8 docs
The graph is how an agent understands the business.
$ curl -fsSL https://raw.githubusercontent.com/ModernRelay/omnigraph/main/scripts/install.sh | bash[Declarative]
Graph as code
Schema, context, policies, UI and infra are declarative files: versioned like code, enforced by the engine.
Context-as-code
Git-style branch, version, and merge for data. A set of linted, typed queries defines each lens on the graph, and branches keep concurrent batch writes safe.
How it reads
find_experts ranks people by vector similarity, full-text, and graph structure all at once, fusing them into a single ranked result. The whole lens is a file you lint, version, and review.
queries/team.gq
query find_experts($topic: String) {
match { $p: Person }
return { $p.name, $p.role }
order { rrf(nearest($p.embedding, $topic),
bm25($p.bio, $topic)) }
limit 5
}[Branches]
Git-style workflows
Many agents work the same graph at once, each on its own branch, merging into main only through review.
01
Branch
Claude Code and Hermes each fork main into their own branch.
cheap fork$ omnigraph branch create02
Write
Hermes adds new nodes and edges while Claude Code dedupes existing records. Isolated branches never collide.
schema + policy enforced$ omnigraph mutate03
Review
Each branch's diff is approved by a human or another agent before it lands.
human or agent$ omnigraph diff04
Merge
Both land on main in review order, three-way and attributed to their agent.
three-way · audited$ omnigraph branch mergeNo agent touches main directly. The schema rejects malformed writes at the branch, the policy decides who can merge, and the commit graph records every change and its author. Two agents, one graph, no collisions.
[Capabilities]
Key features
Hybrid retrieval
Vector, full-text, and graph traversal in one query, fused with rrf().
Typed schema
Writes are typed and checked, rejected at the branch before they land.
Atomic whole-graph commits
Readers see a consistent snapshot, never a partial write.
Three-way merge
Row-level merges with typed conflicts, not last-write-wins.
Time travel
Every version stays queryable; pin a query to any snapshot.
Approval-gated operations
Destructive changes need explicit approval before apply runs.
Object-storage native
Data, catalog, and state live in one S3-compatible bucket.
Actor audit
Every commit records its actor, resolved server-side.
Anti-probing security
Denied and nonexistent are indistinguishable from outside.
[Agent-native]
Graph optimized for agents
Your agents work with graph data the way engineers work with code: branched, typed, reviewed, merged, audited, and governed.
Everything that defines it is a file.
schema.pg
queries.gq
policy.yaml
notebook.yaml
cluster.yaml
Schema, queries, policy, dashboards, deployment. Versioned like code.
The discipline code already has.
BranchTypeReviewMergeAuditGovern
Everything you trust for code now governs knowledge.
Agents move at a different speed.
Teamquarterly
Agent fleetweekly
A team migrates a schema quarterly. A fleet wants to weekly.
Plan. Apply. Review.
PlanApplyReview
Declarative files with a plan/apply cycle: the only form an agent can write and a human can review.
[Infra]
Deploy on infrastructure you own
Not options to weigh, but guides and blueprints to follow: docs to run locally, guides for your own servers, and clone-and-go blueprints for the cloud.
Local
A folder on your machine. graphs/*.omni, zero infra.
Self-hosted
Your server plus any S3-compatible store.
AWS
S3, IAM and KMS inside your own account.
Railway
One service booting from one bucket.
[Cookbooks]
Start from a working graph
Cookbooks are runnable Omnigraph projects: schema, queries, seed data, and agent skills in one repo. Clone one, apply it, and inspect a real graph before you design your own.
01
Industry intel
Track AI and ML market signals through the SPIKE frame: signals, patterns, insights, and know-how.
02
Pharma intel
Monitor trials, filings, competitors, and market movement in a graph built for competitive intelligence.
03
Context graph
Model decisions, traces, actors, and artifacts so an organization becomes queryable by agents.
04
VC OS
Connect deal flow, theses, founders, portfolio signals, and follow-up work.
05
Biomed research
Track papers, claims, entities, and evidence across biotech and medical research.
06
Second brain
A personal operating graph for notes, people, commitments, routines, and recurring work.
[Stack]
Foundation
Built on a strong open-source foundation, aligned with the next-gen lakehouse graph.
The engine: typed, fast, memory-safe systems code.
Open columnar storage with versioning, so the graph remains readable files.
The in-memory standard for columnar data interchange.
Query execution for filtering, sorting, aggregation, and ranked retrieval.
Policy enforcement in the engine, applied before writes land.
[Spec]
At a glance
EngineRust
Version0.9.0
StorageS3 · RustFS · any S3-compatible bucket
FormatLance · open columnar
Retrievalgraph · vector · full-text · hybrid (RRF)
Branchinggit-style · three-way merge · time travel
PolicyCedar · enforced in-engine
ConfigTerraform-style · cluster + operator surfaces
ClientsCLI · TypeScript SDK · MCP
LicenseMIT · open source
Deploylocal · self-hosted · AWS · Railway
[Install]
Get started
curl -fsSL https://raw.githubusercontent.com/ModernRelay/omnigraph/main/scripts/install.sh | bash