Launching today
Omnigraph
Open source graph database for your AI agents
206 followers
Open source graph database for your AI agents
206 followers
Omnigraph is an open-source object-storage native graph database with branching and typed ontology. It allows AI agents safely collaborate on shared knowledge. Give agents one typed graph with Git-like branching, review, and merge for every write, so changes can be validated before becoming shared context. Run it on your own S3-compatible storage, with semantic, keyword, and hybrid search plus graph traversal in one query. No hosted memory API or proprietary storage required.
Free
Launch Team / Built With
AWS Startup AdvisorPersonalized AWS guidance that meets you where you’re already building
Promoted
git style branching and merge for every agent write makes so much sense. congrats Andrew
I used Omnigraph to build a second brain and it works like magic. Really great product!
@jonathan_reimer1 🔥
@odeth_negapatan1 thanks for support Odeth!
Yeah, time travel is such a cool concept for a knowledge graph - it's like asking "what did the world look like for us at that moment?" - and then you can see how it changed over time.
@odeth_negapatan1 Thank you, Odeth!
Congrats on the launch, @pronskiy. I like that it’s basically Git for agents. Good luck today!
@pronskiy @codingwisely Thank you, Vladimir!
Super excited to give this a try! As soon as I heard about it, I knew how useful it would be
Congrats on the launch! How do agents usually write to the graph: do they get the schema up front, or does Omnigraph infer the entities and relationships from what they store? I'm also curious how it handles conflicting facts from different agent runs.
@zain_sheikh Thanks, Zain!
Agents get the schema up front. It's a deliberate design choice and core part of Omnigraph. The schema is declarative, typed, and enforced on every write. You describe node and edge types once, and the agent reads the schema before it writes. This is how agents know the ontology. So they make fewer errors, and they also understand what the data means.
About conflicting facts. Each agent run can work on its own branch. If two runs changed the same node in different ways, the merge stops and nothing gets into main. You get a list of conflicts, and then you or another agent decide which version to keep.