
Your Omnigraph graph can live in @Azure Blob Storage natively Designed by @RoyZalta from MIcrosoft. Thanks Roey 🙌 omnigraph.dev/docs/concepts/…

Versioned graph database on object storage. Git-style workflows and multimodal retrieval.

Your Omnigraph graph can live in @Azure Blob Storage natively Designed by @RoyZalta from MIcrosoft. Thanks Roey 🙌 omnigraph.dev/docs/concepts/…

Omnigraph took 🥉 Product of the Day on @ProductHunt Thank you to everyone who supported the launch!
Omnigraph is live on @ProductHunt 👋 It's an open source graph database where agents can safely collaborate. Each agent writes on its own branch, and the graph lives in your own S3 bucket. What would you build with it? producthunt.com/products/omn…

Collaboration infrastructure for the multi-agent future… v interesting, congrats on the PH launch, @ragnor & @omnigraphdb
Omnigraph is live on @ProductHunt 👋 It's an open source graph database where agents can safely collaborate. Each agent writes on its own branch, and the graph lives in your own S3 bucket. What would you build with it? producthunt.com/products/omn…

4. Omnigraph by @modernrelay An open-source (MIT) graph database for AI agents. Each agent writes on its own branch, you review and merge, and the data stays in your own S3 storage. producthunt.com/products/omn…

If several agents write to the same memory with no review, the shared context fills with junk. Omnigraph puts every write on a branch, so it gets validated before it merges into the shared graph. Think Git for agent knowledge. Open source, runs on your own S3. Live on PH producthunt.com/products/omn…

Neither. @omnigraphdb is basically like Git but for knowledge graph - so the agents work on separate branches. If conflict happens, the merge stops and nothing is replaced. Both versions stay on their branches with commit history, and a human or another agent decides which one to keep or how to merge.
When two agents write conflicting facts about the same node, does Omnigraph keep both with who wrote them, or does the later write replace the earlier one? That choice decides whether a human can later see the disagreement at all.

Good questions on our Product Hunt launch today! More questions and answers here, the team is in the comments all day: producthunt.com/products/omn…

Nice to see @modernrelay's Omnigraph featured on @ProductHunt today
Omnigraph is live on @ProductHunt 👋 It's an open source graph database where agents can safely collaborate. Each agent writes on its own branch, and the graph lives in your own S3 bucket. What would you build with it? producthunt.com/products/omn…

Company's Brain are coocking 🔥🔥
A new cookbook for Omnigraph: company brain Feed it meeting transcripts or other sources and it keeps track of what was claimed and what got decided (those can be quite different). Most importantly, where things contradict each other. All in one graph. github.com/ModernRelay/omnig…

We launched @omnigraphdb on @ProductHunt today It's an open source graph database where agents can safely collaborate. I've been working on it with the team since September. I'm in the comments all day, would love your feedback: producthunt.com/products/omn…

Omnigraph is live on @ProductHunt 👋 It's an open source graph database where agents can safely collaborate. Each agent writes on its own branch, and the graph lives in your own S3 bucket. What would you build with it? producthunt.com/products/omn…

Data quality was probably the biggest and most challenging domain in data two decades ago, and it is getting even harder these days with more autonomous systems and agents. The question becomes: how do we build and verify reliably? That's where graphs as code, with added types and checks, can ensure that agents won't store the wrong data in the wrong place. But how do we test? In the old days, we got a confirmed business number from the business users or domain experts. Or, the second most common, people created queries based on an OLTP relational database, which are verified numbers by the business that then need to be replicated by the DWH or analytics team. So, as a start, we could use that and feed it to the agents.

It’s been 6+ months since I wrote about our AI Command Center (writing.pointnine.com/p/ai-k…). We’re now on v3 and it’s become SOOOO much better. @qui_rins & I will write a longer post about it soon, but here's a super quick preview. A few of my favorite features: - Granola notes get filed in the right place automatically. If an internal meeting covers a portfolio company and a new deal, the portco update goes to its Slack channel and the deal goes to Zendesk. - We forward stuff to Albert (our new AI associate) and "he" does the right thing, e.g. summarizes, researches, files it in Zendesk,... - Albert is in our Slack and our G-Drive, we can tag him anywhere to ask for info or have him chime in. Our agents now sit on top of an ontology (github.com/modernrelay/omnig…), which makes retrieval MUCH better and MUCH faster (cc @modernrelay). Fully aware this isn’t cutting edge - no long-horizon agentic work, no software factory, no recursive self-improvement - but it’s just so fucking useful!

Agents that write to a shared knowledge store can corrupt it, and rolling back is painful. Omnigraph from @modernrelay is an open-source graph database on object storage with git-style branching and row-level three-way merge, so agents work on a branch. It fuses vector, full-text and graph search with rrf(), and runs on S3, R2, GCS or MinIO in open Lance format.

Omnigraph v0.14 - MCP on any self-hosted server: Claude Code or Codex connect without seeing the token - stage a write, publish or drop it - merge --dry-run shows conflicts - CSV import 5x faster: 47s → 8.6s on LDBC SF1 Breaking: see upgrade notes. github.com/ModernRelay/omnig…

My personal expertise graph runs on @omnigraphdb operated by @bot Tracks: Ideas Events Claims People Products Signals Companies Concepts Highlights Explanations Case studies Organizes them into Domains & Threads with full provenance: Span → Artifact → Source Has a thin custom UI↓