Žiga Drev

Trust the source. Cofounded @origin_trail

[Žiga Drev @DrevZiga]

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!

[Trace Labs - Trusted Context for AI Agents @TraceLabsHQ]

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 🧵

[Tomaz L @TomazOT]

@ridark_eth personal second brains are useful, even more when available in "multiplayer mode".
@jakepel03 integrated @obsdmd with @origin_trail decentralized knowledge graph graph turning second brain into reusable memory for teams, agents, and organizations.
https://t.co/w8wfBEuIDu

[Žiga Drev @DrevZiga]

@RubenRohlstein @obsdmd @origin_trail @jakepel03 On the launchpad it appears

[Brana Rakic @BranaRakic]

DKG v10 release candidate 19 has landed on DKG testnet - and it's the FINAL DKG V10 release candidate.

Next stop: mainnet, tomorrow.

The next chapter of the @origin_trail Decentralized Knowledge Graph begins now, empowering agents to share context verifiably and with maximum on device privacy.

https://t.co/pgi5tEcN6r

[Žiga Drev @DrevZiga]

The new @obsdmd <> @origin_trail plugin looks and feels fantastic 👏 Great work @jakepel03

This effectively extends your “second brain” to a collective intelligence based knowledge sovereign context infrastructure you and your peers control🧠

[OriginTrail Developers @OriginTrailDev]

Intelligence is power. Intelligence shared is power multiplied⚡️

The 2nd winner of the Integrations Bounty, @jakepel03 just shipped an @obsdmd plugin that links your second brain to shared context graphs on @origin_trail in minutes.

Whether it's a personal research project or your company's knowledge base, you can now compound the value of your context across teams and organizations.

[Brana Rakic @BranaRakic]

DKG v10 release candidate 19 has landed on DKG testnet - and it's the FINAL DKG V10 release candidate.

Next stop: mainnet, tomorrow.

The next chapter of the @origin_trail Decentralized Knowledge Graph begins now, empowering agents to share context verifiably and with maximum on device privacy.

https://t.co/pgi5tEcN6r

[Jaka Pelko @jakepel03]

Excited to share that my Obsidian ↔ OriginTrail integration was selected as one of the winning projects in the Integrations Bounty. 🎉

Big thanks to @origin_trail for supporting builders exploring new ways to connect knowledge, AI, and decentralized infrastructure.

🧵 1/6

[Jurij Skornik @JureSkornik]

Congrats to @jakepel03 for an awesome DKG plugin in @obsdmd, giving Obsidian users and their agents the power to collaborate and build on shared notes and context graphs in a verifiable way!

[Žiga Drev @DrevZiga]

@OriginTrailDev @jakepel03 @obsdmd @origin_trail I wrote about this kind of integration before. I love how @jakepel03 brought it to a much more refined integration 🔥

[Žiga Drev @DrevZiga]

https://t.co/XgfEoGo4ss

[OriginTrail Developers @OriginTrailDev]

Intelligence is power. Intelligence shared is power multiplied⚡️

The 2nd winner of the Integrations Bounty, @jakepel03 just shipped an @obsdmd plugin that links your second brain to shared context graphs on @origin_trail in minutes.

Whether it's a personal research project or your company's knowledge base, you can now compound the value of your context across teams and organizations.

[BRX @otnoderunner]

Thank you @OriginTrailDev!

Glad to protect @telegram communities using https://t.co/2Amu7cnWGU

Powered by DKG V10 ethereum:0xaa7a9ca87d3694b5755f213b5d04094b8d0f0a6f

[Apex Fusion @ApexFusion]

Vector is the Apex Fusion L2 where AI agents do real work, and prove it.

We aimed a fleet of agents at one of the hardest archives on earth: 385,000 Serbian WWI casualties in handwritten Cyrillic, rebuilt into a verifiable knowledge graph on the @origin_trail DKG.

20,960 assets, every fact provable. See Vector at work 👇
https://t.co/z6LRp9f2Kk

[Žiga Drev @DrevZiga]

@BranaRakic Lfg 🔥

[Brana Rakic @BranaRakic]

DKG v10 pre-mainnet bug bounty - update

Tracers, thank you. Your contributions to the bug bounty have been outstanding, and the inputs you've surfaced are making v10 meaningfully stronger.

The $TRAC honeypot bounty has concluded - and no TRAC was extracted from the honeypot. This meets the pre-mainnet security gate we set for the release.

We've received a lot of valuable reports and are finishing processing and addressing them as we speak - we expect to respond to every open ticket within the next 24 hours.

With the gate met, we're proceeding with the v10 mainnet release.

Shoutout to @dmitry_charts and all anon white hats who have participated! Thank you for helping us build a network worthy of the trust placed in it

[Žiga Drev @DrevZiga]

@perplexity_ai Or you keep your context graph on your device, and gain compounding effects by promoting it with @origin_trail to shared context graphs. 100% ownership retained, value and savings compounded in the networks.

Sovereign context infrastructure.

https://t.co/kmSAnlMb8h

[Brana Rakic @BranaRakic]

https://t.co/UT4yNDrvlJ

[umanitek @umanitek]

Guardian Product Walkthrough https://t.co/PiUYPPlKY9

[Žiga Drev @DrevZiga]

@otnoderunner @OriginTrailDev @openclaw @telegram @origin_trail Keep up the great work and trace ON!

[OriginTrail Developers @OriginTrailDev]

🏆1st winner of the DKG v10 Integrations Bounty: TRACaBot by @otnoderunner

@openclaw Telegram agent that writes scam reports to DKG Shared Memory. One community flags a bad actor → every community is protected.

Exactly the collaborative, agent-native knowledge v10 is built for

[OriginTrail @origin_trail]

Run a command in your favourite agent or a coding tool and you’re good to go!

@cursor_ai, @claudeai (Code & Desktop), Codex by @OpenAI, @windsurf, VSCode + @github Copilot Chat, @cline, @NousResearch and @OpenClaw.

Begin here:

https://t.co/pKdVn2ex6q

[OriginTrail @origin_trail]

Congrats to @cursor_ai on the $60B @SpaceX acquisition, earning a coding tool's way into, literally, a space company🚀

Timely: our CTO @BranaRakic demoed the @origin_trail V10 integration at the Cursor meetup — a shared context graph agents reuse instead of rebuild. Where coding savings and value compound.

[Jurij Skornik @JureSkornik]

One of the exciting things introduced by @origin_trail DKG V10 is the new, conviction-based staking, allowing stakers to increase their rewards by locking TRAC for different periods of time - the longer the lock, the higher the reward multiplier📈

Check out how it works 👇