OriginTrail Developers

22

35

1.7K

OriginTrail Developers@OriginTrailDev·2h

🧠Multi-Agent Memory: Persistent, verifiable, memory that any AI agent can share across any framework. No more siloed recall. ⚡DKG Apps: From autoresearch swarms to verifiable simulations, the first wave of apps is taking shape. 💎The Conviction Flywheel More: docs.origintrail.io/origintrail-v9…

English

0

8

16

312

OriginTrail Developers@OriginTrailDev·2h

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

22

35

1.7K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·6h

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

23

65

4.5K

OriginTrail Developers 리트윗함

Brana Rakic@BranaRakic·2d

.@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.

English

43

110

6.4K

OriginTrail Developers 리트윗함

Žiga Drev@DrevZiga·3d

@aaronjmars Now add multi-Agent memory capabilities to it, and you can do predictions in multi-player mode!

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

1

9

32

1.9K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·3d

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.

English

29

72

2.6K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·3d

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

72

1.4K

OriginTrail Developers 리트윗함

dkg://CryptoGoku.trac@p14416575·5d

first ever large scale simulation on the DKG #AI @origin_trail $TRAC

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

0

8

23

401

OriginTrail Developers 리트윗함

Brana Rakic@BranaRakic·3d

Ownership and interoperability are the only real antidote to techno-feudalism Really enjoyed meeting the great @yanisvaroufakis, who's "cloud capital" thesis is very much aligned with the vision of @origin_trail

English

19

62

1.2K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·4d

In the age of AI, trust begins with data privacy and digital sovereignty. 🛡️ Our co-founder @BranaRakic brings this message to Vivaldi Forum, alongside other leading voices such as @yanisvaroufakis.

About to hit the stage at Vivaldi Forum in Serbia sharing the Tech track with the great @yanisvaroufakis The topic is privacy and digital sovereignty in the age of AI - I'll share how @origin_trail ecosystem empowers people to the wide audience of business professionals If you were in my shoes, would you ask Yanis?

English

8

21

74

1.6K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·4d

🇨🇭 Swiss Federal Railways (@RailService) makes train travel safer & more sustainable, by using the @origin_trail Decentralized Knowledge Graph (DKG) – tracing critical rail parts across the country and beyond! Built on @gs1 standards, it secures interoperable data flows, keeping the rail system safe.

English

28

91

73.4K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·5d

Stopping impersonation requires shared context. @origin_trail powers the shared context graph behind @umanitek Guardian Agent, helping connect signals across accounts and uncover coordinated fake accounts, scams & deepfakes. 🛡️ Watch @TomazOT and @ChrisRynning explain how it works.

English

8

28

79

86.2K

OriginTrail Developers 리트윗함

Jurij Skornik@JureSkornik·14 Mar

AI memory today mostly revolves around 1 user ↔ 1 assistant. But the upcoming, significantly more powerful AI systems are N agents ↔ N agents, collaborating across networks. That requires shared, verifiable memory. @origin_trail DKG V9 is designed for exactly this: a decentralized knowledge graph where agents can publish discoveries and build on each other’s work. Go from isolated agents → collective intelligence with the DKG V9 testnet - out now!

English

2

21

47

1.5K

OriginTrail Developers 리트윗함

Eze • 💢 •@0xEze_·6d

OriginTrail’s @BranaRakic dropped one of the biggest AI infrastructure updates last week. It barely made a noise. But that's because some don’t understand what it means. So here — I have broken it all down. If you use AI agents for personal projects, build platforms for agentic AI, or run enterprise workflows in autonomous environments — this thread is for you 🧵

English

4

39

96

2.4K

OriginTrail Developers 리트윗함

Tomaz L@TomazOT·6d

Glimpse into the future of policy making? Simulating diverse stakeholders and covering entire corpus of regulation of multiple countries 🤯🤯🤯 One of the most exciting uses of the @origin_trail decentralized knowledge graph!

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

1

16

43

710

OriginTrail Developers 리트윗함

Jurij Skornik@JureSkornik·6d

A strong example of why multi-agent simulation gets interesting when agents can share verifiable memory. @origin_trail DKG v9 is THE memory for AI agents.

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

1

15

39

806

OriginTrail Developers 리트윗함

Brana Rakic@BranaRakic·6d

Given a sufficiently large knowledge base and large population of agents, the future can be predicted. Psychohistory at our fingertips

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

24

65

3K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·6d

"Any sufficiently advanced technology is indistinguishable from magic"

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

25

74

2K

OriginTrail Developers 리트윗함

Žiga Drev@DrevZiga·6d

Watching a swarm of 2,000 agents simulate the AI future of ~1 billion people. One question: EU vs US AI regulation – macroeconomic impact on nations? How? → MiroFish × @origin_trail DKG v9 semantic memory → 2,000 AI agents sharing memories on the DKG → 14–18 actor classes per jurisdiction → 60 rounds (2026–2030) Here’s what actually happens: The US leads on growth (75 vs 64), productivity (79 vs 66), and tech dominance (86 vs 61). The EU leads on job quality (72 vs 63) and wage growth (71 vs 58). Final score: US 72 – EU 67 The tradeoff is clear: → US: faster, more powerful, more concentrated growth → EU: slower, more distributed growth More info on technologies used in the reply, so you can try it out yourself!

English

30

38

91

14.5K

OriginTrail Developers 리트윗함

OriginTrail@origin_trail·6d

🇺🇸 Protecting US consumers at the source. @SCANAssociation Trusted Factory, powered by @origin_trail, helps major importers verify supplier security audits before goods enter the country – reducing risk earlier across supply chains that represent 40%+ of US imports.

English