The context graph for enterprise AI. Creators of @omnigraphdb, the Git-syle graph database built for a world where agents are first-class operators.
Joined October 2025
- Tweets3
- Following10
- Followers121
- Likes3
Sneak peek of what we've been up to in the past couple of weeks.
@kozlovski you're the 🐐, chatting with you is always a pleasure!
why agents need typed graphs to coordinate
/w Andrew and Ragnor from Modern Relay,
an agent substrate layer built on open-source infrastructure like Lance, Arrow, and DataFusion
Timestamps:
(0:00) Why build a graph database for agents?
(5:43) Why not Postgres or any other relational database?
(17:03) The composable "company brain" substrate for agents
(20:51) Need for agent guardrails (e.g type safety)
(27:00) Importance of Schemas
(33:48) NoSQL vs SQL
(42:46) Lance, DataFusion, and Arrow as the open stack
(51:00) What Modern Relay and OmniGraph are
(52:13) Branches: GitHub for agent-written data
(1:00:59) Slack Agents, the Dependency Graph and decoupling for parallelization
(1:12:32) Why Graphs are great + a 2-year prediction
(1:17:32) Centralization vs decentralization for long-horizon coordination problems
Today we're coming out of stealth at Modern Relay with $3M from @PointNineCap , @emergelab, @AminoCollective and @_CommonMagic alongside exceptional angels including Charlie Songhurst, Michael Boehler and Thomas Clozel.
We are building the context graph for AI-native orgs: the source of truth for company data, policies, decisions and the logic between them. Humans and agents share the same state in which they coordinate work, with changes branched, reviewed, and merged before they land. So knowledge actually compounds.
Omnigraph is the open source engine underneath: an agent-native graph database with git-style workflows, vector/fts search, and typed queries.
We believe intelligence is a solved problem. The next decade belongs to the companies that make their world models agent-accessible. And we're here to enable them.