The frontier challenge in AI is no longer model capability.
It’s how agents share, verify, and build on each other’s knowledge.
That’s what @origin_trail is solving.
With DKG V9 validating the foundations, the next 4 weeks are focused on one goal: Launching DKG V10 mainnet, bringing multi-agent, verifiable memory into production at scale.
From single-agent intelligence → coordinated swarms
From isolated outputs → compounding knowledge
From probabilistic answers → verifiable truth
V10 is the unlock.
"Knowledge graphs improve the fidelity of AI."
— Dr. Bob Metcalfe, Turing laureate, Ethernet inventor, Internet pioneer, and our advisor.
It's why we built @origin_trail: shared, verifiable context that compounds value and token savings with every agent.
The nOS extends that context to AI agents your enterprise can trust.
Manufacturing is entering a new era. It's no longer just about data, but about turning it into trusted knowledge that enables smarter decisions and stronger collaboration.
Decentralized Knowledge Graph (DKG) connect data, people and processes through shared context across industrial ecosystems.
A full room in Ljubljana for @cursor_ai, where @BranaRakic gave a live look at Decentralized Knowledge Graph V10.
Builders aren't just looking for utility anymore — they're looking for systems where knowledge accumulates and creates value over time.
In hindsight it will be obvious that shared memory is key for reliable and viable AI
Frontier labs don't push it because it further destroys their moat
This is Metcalfe's law in action on cost reduction
Try @origin_trail and see for yourself👇
@EmanAbio@AnthropicAI@OpenAI@Google AI agents are already spending over 50% less on tokens and compounding value thanks to @origin_trail’s shared context graphs.
Knowledge is power. Knowledge shared is power multiplied.
"Systems of record store what happened. nOS explains why.”
@TraceLabsHQ just launched the new Network Operating System (nOS) for AI agents enterprises can actually trust.
Built on the DKG V10, it gives agents shared memory, verifiable decision traces, and context that compounds with every agent you add.
No more black-box decisions. Replay what your AI did, audit why it did it, and prove it to anyone.
The missing layer for enterprise AI is here.
Most AI agent demos fall apart the second you ask the boring question: prove it!
Which data did the agent use? Why did it grant that exception? Who'd catch it if it got the call wrong?
Usually there's no good answer.
The agent did its thing and moved on, and whatever reasoning it had is sitting in a log nobody reads, or nowhere at all. Fine for a demo. Much less fine when you're handing real decisions to these things at work.
So today we're shipping nOS, our Network Operating System for enterprise AI agents, built on the latest version of the @origin_trail Decentralized Knowledge Graph.
The idea is pretty simple. Agents stop working alone. They share one structured memory, and every decision an agent makes gets written down as a trace you can open later: what went in, what rule applied, what it was reasoning over. Those traces get signed and anchored on the DKG, so anyone can check them, you own them, and the next agent you deploy builds on them instead of starting cold.
Why bother doing it this way?
Because you can verify a decision without having to trust us. The proof stands on its own. Because the knowledge stacks up instead of evaporating, so your tenth agent is sharper and cheaper to run than your first. And because it's actually yours. The traces live in your graph, not locked inside someone's database. Run your own node and nothing leaves your walls.
We didn't get here overnight.
The DKG has been in production for years answering one stubborn question, how do you know a piece of data is true, for supply chains first and a lot of other places since.
AI agents just made that question everyone's problem at once.
Trusted by industry leaders, we're embarking on an exciting new chapter with @TraceLabsHQ.
Together, with a wider @origin_trail ecosystem!
AI agents won’t scale on isolated memory and black-box outputs.
@TraceLabsHQ's nOS is the answer - shared context graphs, verifiable decision traces, and infrastructure enterprises can actually trust.
Powered by @origin_trail.
Enterprises are where AI agents become both more valuable and more dangerous.
In consumer apps, a bad answer is annoying. In enterprise systems, a bad answer can affect customers, operations, compliance, supply chains, financial decisions, or mission-critical workflows.
So agents need more than access. They need governance, memory, provenance, security, and a way to collaborate around shared, trusted business context.
That is what the new nOS is all about.
@origin_trail DKG provides the shared, verifiable memory foundation for multi-agent collaboration. nOS takes that foundation and makes it enterprise-first: connecting into ERPs, CRMs, and other core systems, running on high-availability infrastructure, and adding the security layer enterprises require.
This is the right model for where AI is going. Not isolated agents pulling from fragmented tools, but multi-agent environments working from shared, verifiable context - with every decision traceable, every memory reusable, and every contribution anchored in the DKG.
Excited to bring the new nOS to existing and new enterprise customers, and help them build serious agentic systems on top of the DKG.
Every trace is enshrined in the OriginTrail DKG: cryptographically anchored, owned by your wallet, verifiable by anyone.
And it compounds — the 50th agent starts with everything agents 1–49 already learned.
Context shared is power multiplied
Get your enterprise AI game on track with the right AI agent collaboration framework - the new @TraceLabsHQ Network Operating System built on @origin_trail, and join the array of global enterprises already on board.
Check out the fresh nOS and get in touch
Today, we are proud to upgrade our 10 + years journey with a new identity and launching a brand new nOS — the Network Operating System for Verifiable Enterprise AI, powered by @origin_trail's new Decentralized Knowledge Graph.
Here's why we built it 🧵
"There may be some neuro-symbolic hybrid much better than we have right now that smoothly transitions between data in a corpus and abstract representations. The kinds of stuff you guys are doing are compatible with that."
— @GaryMarcus
⏱️10 highlights:
00:00 Intro: Gary Marcus & @BranaRakic at DKGCon
02:22 Why AI took a wrong turn
04:42 Deep learning vs. deep understanding
06:16 World models: a foundational idea
08:12 The building blocks of trustworthy AI
09:44 Neuro-symbolic AI & abstract relationships
13:04 Safety is an ecosystem - the airplane lesson
15:03 The real risk of AI agents today
18:36 Testing AI like we test new drugs
22:49 Where @OpenAI is headed
The signal is clear: the path forward runs through world models, abstraction, and an open, accountable ecosystem.
The future isn't more context. It's trustworthy shared context.
Without structure, provenance, permissions, and verification, shared memory becomes noise. With them, it becomes a network effect.
@garrytan With @origin_trail, any context is portable to any system or agent and shareable in a trusted fashion with whomever you want.
Knowledge is power, and knowledge shared is power multiplied.
Today on MCG: @DrevZiga | Co-Founder @origin_trail | $TRAC
OriginTrail is a shared database that lets companies and people store and verify information without giving it to the AI labs
Topics covered on stream include👇
01:53 - The decade-long evolution
04:25 - The thesis
09:20 - OriginTrail's edge
14:14 - 30,000 Chinese factory audits live in OriginTrail, used by US and Canadian importers through SCAN
17:53 - Use case expansion
21:24 - Symbolic AI + neural AI hybrid
25:14 - Business model
28:36 - Network revenue at ~20M $TRAC (~$9M USD) at the time of recording
32:30 - conviction based staking
33:30 - Bounty program
🇰🇷 CoinEasy just dropped Korea’s first onchain Knowledge Asset!
We didn’t just upload another JPEG, we permanently engraved our 𝗘𝗔𝗦𝗬𝗕𝗢𝗬 character onto the @origin_trail blockchain. It’s now a fully verifiable "Knowledge Asset," a major first for a Korean project on a global decentralized graph.
The Tech Specs:
• Stored as 75 data points on the OriginTrail DKG
• 100% public, verifiable + queryable
• Image locked forever on IPFS
(CID: bafkreihetyg5vewd4uiqsqxmv3glpmzsbasq4akq3pxv5jwrthtwufk5yy)
① Now: we engraved EASYBOY forever ✅
② Soon: your turn. Solve quizzes, learn, and your record lands onchain (EasyTree is coming)
③ Next: your learning and achievements become your own permanent, provable record. Once it's engraved, no one can erase it and anyone can verify it. Soon you'll be able to do this yourself.
Huge thanks to the @origin_trail team for making verifiable knowledge real.
🇰🇷 This is Korea, ongraph.
🇨🇭 Switzerland ranks among Europe’s safest rail systems. Keeping it that way depends on trusted data behind critical parts.
Swiss Federal Railways (@RailService) uses @origin_trail to trace critical rail components using trusted, interoperable data built on @gs1 standards.