Uvi vs Modern Relay
Modern Relay's Omnigraph is a git-style versioned graph DB primitive. Uvi ships the complete Reasoning Layer on top - Decision Graph, deep ETL, and a Forward Deployed Agent.
The thesis in one paragraph
Modern Relay's Omnigraph is an open-source, git-style versioned graph database - nodes, edges, branch, and merge as first-class semantics. It's the most architecturally aligned primitive in the market: a serious substrate a serious team could build a Reasoning Layer on top of. Uvi is the Reasoning Layer: Decision Graph with decisions as first-class nodes, deep ETL across code / tickets / PRs / Slack / internal services, native RBAC at retrieval, and a Forward Deployed Agent who ships it end-to-end in 2-4 weeks. Modern Relay gives you the building blocks. Uvi gives you the finished layer.
Side by side
Category
- Uvi
- Reasoning Layer (complete Decision Graph + ETL + agent surface)
- Modern Relay
- Open-source Omnigraph - a git-style versioned graph database primitive
Primary abstraction
- Uvi
- Decisions as first-class nodes - owners, triggers, blockers, evidence
- Modern Relay
- Nodes + edges with branch, merge, and version semantics
What you get out of the box
- Uvi
- A Decision Graph shipped end-to-end by a Forward Deployed Agent
- Modern Relay
- A graph DB you build your own schema and pipelines on top of
Enterprise ETL depth
- Uvi
- Live joins across code / tickets / PRs / Slack / internal services, encoded by Uvi
- Modern Relay
- You write the ingestion; the database stores whatever you land in it
Query interface for agents
- Uvi
- GraphQL + MCP - returns structured chains of decisions
- Modern Relay
- Graph query language - the agent (or you) interprets the traversal result
Permission model
- Uvi
- Native RBAC at retrieval, mirrored from source ACLs
- Modern Relay
- Application-level - you enforce it around the DB
Deployment
- Uvi
- On-prem or VPC, zero data egress, enterprise-grade
- Modern Relay
- Self-hosted (open-source) - operate it yourself
Primary buyer
- Uvi
- Enterprise R&D and Platform leaders wanting agents in production
- Modern Relay
- Infrastructure and platform engineering teams building custom graph products
Time to value
- Uvi
- 2-4 weeks to a production-grade Decision Graph via Forward Deployed Agent
- Modern Relay
- Weeks to months - you're building your own schema, ingestion, and query layer
Compose with each other?
- Uvi
- Yes - Modern Relay could theoretically be a storage layer, but Uvi is complete without it
- Modern Relay
- Yes - a team could build a Decision-Graph-like product on Omnigraph over months
| Uvi | Modern Relay | |
|---|---|---|
| Category | Reasoning Layer (complete Decision Graph + ETL + agent surface) | Open-source Omnigraph - a git-style versioned graph database primitive |
| Primary abstraction | Decisions as first-class nodes - owners, triggers, blockers, evidence | Nodes + edges with branch, merge, and version semantics |
| What you get out of the box | A Decision Graph shipped end-to-end by a Forward Deployed Agent | A graph DB you build your own schema and pipelines on top of |
| Enterprise ETL depth | Live joins across code / tickets / PRs / Slack / internal services, encoded by Uvi | You write the ingestion; the database stores whatever you land in it |
| Query interface for agents | GraphQL + MCP - returns structured chains of decisions | Graph query language - the agent (or you) interprets the traversal result |
| Permission model | Native RBAC at retrieval, mirrored from source ACLs | Application-level - you enforce it around the DB |
| Deployment | On-prem or VPC, zero data egress, enterprise-grade | Self-hosted (open-source) - operate it yourself |
| Primary buyer | Enterprise R&D and Platform leaders wanting agents in production | Infrastructure and platform engineering teams building custom graph products |
| Time to value | 2-4 weeks to a production-grade Decision Graph via Forward Deployed Agent | Weeks to months - you're building your own schema, ingestion, and query layer |
| Compose with each other? | Yes - Modern Relay could theoretically be a storage layer, but Uvi is complete without it | Yes - a team could build a Decision-Graph-like product on Omnigraph over months |
FAQ
Is Modern Relay a direct Uvi competitor?
Architecturally the closest of any competitor. Modern Relay's Omnigraph is a git-style versioned graph database - nodes, edges, branch, merge - designed as a shared graph substrate for AI agents. It's a well-designed primitive. But Modern Relay ships you the database; you build the schema, the ingestion, the joins, the query surface, and the deployment. Uvi ships the whole Reasoning Layer: Decision Graph, ETL depth, agent surface, and a Forward Deployed Agent who encodes it all in 2-4 weeks. Different level of the stack.
Isn't a versioned graph DB with branch/merge exactly what agents need?
It's a useful primitive, but by itself it's not what agents need. What agents need is a queryable model of your company's decisions, owners, triggers, and blockers - along with evidence pulled live from source systems - accessible via a stable schema they can rely on. A raw graph DB gives you the primitive to store all that; a Reasoning Layer gives you the model, the pipelines, the ACL enforcement, and the query surface already built. If you're a large infra team that wants to build your own Reasoning Layer, Modern Relay is an interesting substrate. If you want the answer in 2-4 weeks, that's Uvi's job.
What does the Forward Deployed Agent actually change?
It closes the gap between 'a graph DB is available' and 'my agents produce correct answers across five source systems.' A Uvi FDA - a specialist in ETL and data science - sits with your tech lead and encodes the joins your team knows but never wrote down: how a branch name links a ticket to a PR to a feature flag to an internal service that carries the live on/off state. The result is a Decision Graph tuned to your org's private definitions, not a generic schema. With Modern Relay, all of that is a build project on your side.
Could a team build Uvi on top of Modern Relay?
Theoretically, yes - given a large infra team, a data engineering team, an agent integration team, and 6-12 months. You'd be reimplementing the Decision Graph model, the ETL joins across code / tickets / PRs / Slack / internal services, source-ACL mirroring at retrieval, the GraphQL + MCP surface, and the Forward Deployed Agent engagement. That's what Uvi does as a product, staffed by Uvi. Buy vs. build applies here the way it applies to any infrastructure category.
When is Modern Relay the right choice?
When you're building infrastructure for a broader set of graph-based use cases, need branch/merge semantics as a first-class primitive, and want an open-source base you control end-to-end. Great for infra platform teams, custom knowledge graph products, and R&D on agent-native storage models. If your goal is shipping AI agents that reason across your enterprise stack, Uvi is the shorter path.
Can I run both?
In principle - Uvi doesn't preclude a graph DB substrate underneath. In practice, most enterprises deploying Uvi don't stand up a separate Omnigraph cluster; the Reasoning Layer ships with its own execution model. If you already run Modern Relay for other reasons, we're happy to talk about how they'd coexist.
A graph DB isn't a Reasoning Layer.
If you want to ship agents that reason across your enterprise stack in weeks - not build the layer yourself over months - talk to us.