OriginTrail

13.6K posts

OriginTrail banner
OriginTrail

OriginTrail

@origin_trail

Trust the Source.

Decentralized Katılım Mayıs 2014
1.4K Takip Edilen91.2K Takipçiler
Sabitlenmiş Tweet
OriginTrail
OriginTrail@origin_trail·
🆕Imagine hundreds of agents working in parallel, handing off to one another and building on each other's work. Every finding becomes a cryptographically anchored Knowledge Asset: verifiable, permanent, owned by the publisher, and queryable by any agent on the network. Enter Decentralized Knowledge Graph v9, already powering AI agent swarms to be: → up to 60% faster → up to 40% cheaper than markdown handoffs. The advantage compounds as the swarm grows. Build something exciting—or simply run a hello-world OriginTrail multiplayer game to try it!
Brana Rakic@BranaRakic

x.com/i/article/1892…

English
14
49
133
12.8K
OriginTrail
OriginTrail@origin_trail·
38% of users accidentally shared fake news. Imagine AI agents doing the same at scale. For agents to verify what’s real and work together, they need shared, verifiable memory, powered by @origin_trail. 🕸️
English
6
21
53
832
@aaronjmars
@aaronjmars@aaronjmars·
crazy cook, DKG V9 + MiroShark 👀
Žiga Drev@DrevZiga

The AI future of 1B+ Europeans and Americans simulated — less than an hour of human effort. 🦈Powered by DKG V9 + MiroShark. Significant time and resources saving, as this is achieved with agents coordinating, sharing memory, and compounding insight on @origin_trail. OpenClaw agent executed seamlessly — helped by excellent CN → EN translation. Huge shoutout to @aaronjmars — MiroShark is exactly the kind of engine that will thrive on DKG V10 mainnet, alongside the next wave of agentic systems.

English
5
15
43
2.9K
OriginTrail
OriginTrail@origin_trail·
AI agents will not scale on isolated memory. 🕸️ They need shared verifiable memory that works across tools, teams, and workflows. So before agents act, the knowledge they rely on can be traced and checked. @BranaRakic on why scaling AI means scaling trust.
English
6
23
64
3.4K
OriginTrail retweetledi
Žiga Drev
Žiga Drev@DrevZiga·
The AI future of 1B+ Europeans and Americans simulated — less than an hour of human effort. 🦈Powered by DKG V9 + MiroShark. Significant time and resources saving, as this is achieved with agents coordinating, sharing memory, and compounding insight on @origin_trail. OpenClaw agent executed seamlessly — helped by excellent CN → EN translation. Huge shoutout to @aaronjmars — MiroShark is exactly the kind of engine that will thrive on DKG V10 mainnet, alongside the next wave of agentic systems.
@aaronjmars@aaronjmars

> Built a sanitized version of MiroFish called MiroShark Everything translated to English, improved simulation flow, recommended models, can be run locally + work w/ any OpenAI-compatible API key If you want to experiment w/ this wonderful framework, I recommend using it 👇

English
3
29
80
8.8K
OriginTrail
OriginTrail@origin_trail·
We’re moving from isolated AI agents to coordinated intelligence networks. The bottleneck is no longer capability — it’s shared, verifiable memory. That’s what @origin_trail is solving. With DKG V9 proving the architecture, he focus now shifts to V10 mainnet. OpenClaw, NemoClaw, Hermes… Agents that once operated alone now become nodes in a shared memory system — publishing, verifying, and building on each other’s knowledge in real time. This is the shift: From intelligence → coordination From outputs → compounding knowledge From probability → verifiable context The V10 is the unlock.
OriginTrail Developers@OriginTrailDev

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.

English
8
28
89
2.6K
OriginTrail retweetledi
Žiga Drev
Žiga Drev@DrevZiga·
Fast tracking to v10 @origin_trail users both enterprise and indie developers are reporting the time to implement have gone down from 10 hours to less than 10 minutes, already with the DKG v9 testnet with collocation of nodes and AI agents. Best time to get on track is now!
OriginTrail Developers@OriginTrailDev

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.

English
5
26
60
2.4K
OriginTrail retweetledi
Brana Rakic
Brana Rakic@BranaRakic·
The real bottleneck in AI isn't smarter models. It's that every agent starts from zero. No memory of what was tried. No knowledge of what others discovered. No way to verify what's true. @origin_trail DKG V10 changes this. Agents share signed knowledge graphs - not chat logs, not vector dumps -actual verifiable, queryable knowledge that compounds across sessions, across teams, across organizations. We're already running it: agent-human teams coordinating DKG V10 development through the DKG context graphs. Decisions, code structure, dev planning - all in the graph, all queryable by any agent. The Decentralized Knowledge Graph is the connective tissue AI has been missing.
OriginTrail Developers@OriginTrailDev

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.

English
3
28
70
2.3K
OriginTrail retweetledi
OriginTrail Developers
OriginTrail Developers@OriginTrailDev·
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.
OriginTrail Developers tweet media
English
3
38
83
13.5K
OriginTrail
OriginTrail@origin_trail·
AI agents are entering the era of experience. As they learn from the world, the memory they rely on needs to be verifiable and grounded in trusted sources. Hear from @BranaRakic, @origin_trail co-founder & CTO 🎯
English
8
27
80
5.2K
OriginTrail retweetledi
Brana Rakic
Brana Rakic@BranaRakic·
.@karpathy just described @origin_trail without saying it. Agents collaborating across the internet on the same research problem, running thousands of parallel experiments where each commit builds on the last. The unsolved piece is how collaborating agents who don't trust each other share & verify the knowledge they've learned. That's what context graphs on the new DKG do. An auto-research swarm sets up a context graph with a defined set of verifier agents and an M-of-N signature threshold. Untrusted agents run experiments and submit results as Knowledge Assets. For those results to land in the shared context graph, M of the N trusted verifiers must cryptographically co-sign the batch on-chain, attesting that the claimed metrics actually reproduce. The result is a growing, queryable knowledge graph of verified experimental results that any agent in the swarm can query to decide what to try next, built on a trust layer where untrusted contributors do the heavy lifting and trusted verifiers keep the graph honest.
Brana Rakic@BranaRakic

x.com/i/article/1892…

English
6
43
111
6.8K
OriginTrail
OriginTrail@origin_trail·
Europe’s cultural heritage and construction sector faces the same problem: fragmented, hard-to-verify building data. 🇪🇺-funded @BUILDCHAIN_HE project tackles this with Digital Building Logbook, powered by @origin_trail – turning fragmented building data into a verifiable, interoperable resource across the full lifecycle.
English
15
24
74
2.2K
OriginTrail
OriginTrail@origin_trail·
Making sure any takeoff is done safely 🛫 DMaaST, an EU-funded initiative, is advancing trusted AI for robotics & aerospace with @origin_trail, enabling rapid, reliable responses to unforeseen events through seamless integration of vast and diverse data sources.
English
0
26
82
4.5K
OriginTrail
OriginTrail@origin_trail·
All major AI models are missing the same thing: A shared memory. OpenAI. Google. Claude. → isolated intelligence → no compounding → constant resets 🦞V9 DKG unlocks collective intelligence. Thousands of agents, one memory layer. Years of work → done in hours.
Brana Rakic@BranaRakic

x.com/i/article/1892…

English
6
29
71
2.7K
OriginTrail
OriginTrail@origin_trail·
@OxPharmaGenesis Discover how @origin_trail and @OxPharmaGenesis are advancing trustworthy AI and DeSci. ⤵️ x.com/origin_trail/s…
OriginTrail@origin_trail

💊@OxPharmaGenesis, trusted by 8 of the world’s top 10 pharma leaders and 50+ global healthcare organizations, is joining forces with @origin_trail to advance trustworthy AI and pioneer DeSci! Together, we’re building collaborative, AI-ready clinical knowledge ecosystems to fuel the next generation of agentic science.

English
0
10
32
1.1K
OriginTrail
OriginTrail@origin_trail·
How can medical AI agents become more trustworthy? 🔍 Hear from Dr. Kim Wager of @OxPharmaGenesis as he showcases a live demo of agentic medical AI grounded in verifiable data provenance, powered by the @origin_trail Decentralized Knowledge Graph (DKG).
English
9
23
71
1.5K

Keşfet

@aaronjmars @BranaRakic @karpathy @BUILDCHAIN_HE @OxPharmaGenesis @elonmusk @BarackObama @taylorswift13