Launched this week
Omnigraph
Open source graph database for your AI agents
611 followers
Open source graph database for your AI agents
611 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
Customer.ioAutomate Messaging Everywhere — Startups Get 12 Months Free
Promoted
Whats the first use case where it feels clearly better than just keeping everything in a normal database?
@russ_halilov define "normal database"😉
@russ_halilov Company brain comes first to my mind – one place where agents keep everything the company knows about people, customers, decisions, projects, prospects, etc.
You can build it on something conventional like Postgres of course. But soon you might hit many problems. Questions like “who talked to this customer and what did we promise them” turn into long chains of joins. And when several agents write at the same time, you have to build review and rollback yourself. In Omnigraph both come out of the box, because it is a graph and each agent writes to its own branch.
If you have one writer and simple tables, a relational database is fine.
By the way, I’m a happy Bluedot user 🔵 🫶 What do you guys currently use? And what are you biggest challenges?
Congrats on the launch, @ragnor and team! We’ve rebuilt our entire internal operating system on Omnigraph as the retrieval substrate our agents run on. The improvement in retrieval quality and speed we've seen across many use cases is insane. We’re still in the very early stages of what’s possible to build on top of Omnigraph, so we’re really excited to keep working with it 🚀
The Git-like branching for agent writes is the part that sold me — most agent memory tools let agents write freeform and just hope nothing conflicts, so having each run on its own branch with review and merge is a real answer to that mess. I'm curious about the typed ontology side though: when an agent runs into something that doesn't fit the schema, does it propose a schema change for review, or does it fail closed? That edge seems like where the design either stays clean or gets messy over time.
@jcbuilds Agent can propose schema change for sure - right in the .pg file for human or other agent to review.
All depends on governance.
branches make sense when multiple agents are proposing edits to the same shared graph
seeing which facts would be overwritten before merging would help catch conflicting updates
I used Omnigraph to build a second brain and it works like magic. Really great product!
@jonathan_reimer1 🔥
@jonathan_reimer1 thanks, Jonathan! Same here. I started with Markdown + Git and LLM-wiki approach, but the bigger it grew the harder it got to maintain. Omnigraph made it easier and a lot faster. What do you keep in yours?
git style branching and merge for every agent write makes so much sense. congrats Andrew
@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!