OriginTrail Developers

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.

Safety without surveillance. @ChrisRynning on why @umanitek Guardian, powered by the @origin_trail DKG, enables trust and safety without sacrificing privacy.

GM to our Korean community 🇰🇷

You’re not gonna want to miss this if you’re in Ljubljana! Powering up your work in @cursor_ai with @origin_trail dkg v10 🚀

Different industries, same need: collective intelligence. From internet safety to healthcare and supply chains, @origin_trail helps people and systems work from the same trusted knowledge, with provenance, accountability, and privacy built in.🌐 See how trust scales across use cases.

At the Cursor meetup in Ljubljana, @BranaRakic will show how @origin_trail + @cursor_ai enable teams to build AI workflows they can coordinate and trust across projects and devices. May 28th I Ljubljana

📂 OriginTrail DKG v10 ┃ ┣ 📂 Shared Context Graphs ┃ ┣ 📂 project memory ┃ ┣ 📂 team knowledge ┃ ┣ 📂 agent collaboration ┃ ┗ 📂 human + AI shared context ┃ ┣ 📂 Memory ┃ ┣ 📂 Working Memory → private agent drafts ┃ ┣ 📂 Shared Memory → gossip-replicated ┃ ┗ 📂 Verifiable Memory → on-chain provenance ┃ ┣ 📂 Agents ┃ ┣ 📂 Hermes ┃ ┣ 📂 OpenClaw ┃ ┣ 📂 MCP / Cursor / Claude ┃ ┣ 📂 skill discovery ┃ ┗ 📂 encrypted P2P messaging ┃ ┣ 📂 Knowledge Ops ┃ ┣ 📂 import files ┃ ┣ 📂 extract RDF ┃ ┣ 📂 write assertions ┃ ┣ 📂 promote knowledge ┃ ┣ 📂 publish proofs ┃ ┗ 📂 query with SPARQL ┃ ┣ 📂 Interfaces ┃ ┣ 📂 Node UI ┃ ┣ 📂 CLI ┃ ┣ 📂 REST API ┃ ┣ 📂 MCP tools ┃ ┗ 📂 webhooks ┃ ┣ 📂 Integrations ┃ ┣ 📂 Obsidian ┃ ┣ 📂 GitHub ┃ ┣ 📂 World Monitor ┃ ┗ 📂 custom apps

▶︎▶︎▶︎▷ #AI @origin_trail Academy

Multi-agent AI will not scale on isolated memory, and the bottleneck is not talked about enough. Managing context is already one of the largest challenges for agents. It affects efficiency, output quality, cost, speed, and the ability to recall what actually matters. Now multiply that problem across many agents. Agents cannot collaborate properly if one does research, another makes a plan, another takes action, and none of them share a reliable understanding of what has been done, what is being done, what was learned, or what should happen next. Instead of multi-agent intelligence, we get what I'd call fragmented execution. The deeper issue is that agent memory is still often stored in markdown files. Useful for notes, weak as infrastructure. Recall becomes incomplete, irrelevant, or even harmful when polluted context gets pulled into the next decision. @origin_trail DKG V10 introduces a much stronger model - decentralized, shared, and verifiable context graphs. Agents can form collective memory while preserving attribution and verifiability for every part of it. And because that memory lives as a knowledge graph, not a flat file, agents can explore relationships. They can start from a query, find an entry point, and traverse the graph to build a full picture before acting. For example, a clinical research agent could start with brivaracetam, move to the clinical trials that studied it, inspect trial details and results, and know exactly which agent or source contributed each piece of knowledge. That is the difference between isolated and collective memory, built on agent coordination and collaboration. With Obsidian integration, even isolated personal knowledge can be pushed into the DKG V10 and turned into shared context for agent and human collaboration. This is how AI moves from one-off outputs to compounding, collective intelligence. So it's not about just "adding" more agents. It is agents sharing context and building on each other’s work - and that's what the DKG brings to the table.

Shared context is what will drive the next wave of growth in AI - and that driver will be @origin_trail When you think of it, a lot of what we humans do in our daily work is share context in a slow, inefficient way (chat, meetings, email ...) Our agents can help remove that burden - as well as make it faster and more reliable - tracing every decision, every observation and conclusion via shared context graphs. We're shipping OriginTrail Decentralized Knowledge Graph V10 with exactly those capabilities Read more 👇

Just in time for v10 @origin_trail ethereum:0xaa7a9ca87d3694b5755f213b5d04094b8d0f0a6f

🇰🇷@Official_Upbit is listing ethereum:0xaa7a9ca87d3694b5755f213b5d04094b8d0f0a6f token. Korea is ready for the next chapter of trusted AI infrastructure as the @origin_trail DKG v10 era begins. From AI agents to shared verifiable memory, the Decentralized Knowledge Graph is scaling trust at internet scale.

The second brain was step one. Step two is shared memory. With @origin_trail DKG V10, personal knowledge becomes part of a verifiable context graph that teams and agents can keep building on together. That’s the kind of infrastructure collective intelligence needs.

Obsidian fam here's a great way to share your graphs with both humans and agents Try out the new @obsdmd @origin_trail plugin

The AI agent multiplayer mode showcased by @DrevZiga integrating @obsdmd with @origin_trail🔥🔥🔥

Trusted coordination starts long before takeoff. ✈️ In the EU-funded DMaaST project, @origin_trail transforms fragmented industrial data into interoperable, trusted context, helping manufacturing systems respond reliably as conditions evolve.

AI is only as useful as the context behind it. @origin_trail Academy helps users move beyond prompt-based AI toward shared, verifiable context, so agents can operate on trusted knowledge instead of guesswork. Start learning ↓

This week, our founder @0xshai sat down with @TomazOT, Co-Founder of @origin_trail as they discussed: - The Convergence of Neural and Symbolic AI - The Three Layers of Agent Memory - Decentralization as a Trust Infrastructure 00:00 – Introductions 00:35 – Memory as a Moat: How Decentralized Knowledge Graphs (DKG) make AI agent memories verifiable and shareable. 02:13 – Symbolic AI vs. Neural Networks: Understanding the "Yin and Yang" of deterministic data structures and probabilistic guessing engines. 04:39 – Neuro-Symbolic AI: How to combine the reasoning power of LLMs with the persistent, organized memory of a graph. 06:54 – Using "Knowledge Assets" to pinpoint exactly where an agent's decision-making data originated. 11:15 – The Role of Crypto: Why blockchain is essential for fingerprinting data and ensuring it hasn't been tampered with. 15:21 – The 3 Layers of Memory: A breakdown of Working Memory, Shared Memory, and On-Chain Verified Memory. 24:43 – Real-World Adoption: How companies like Walmart and Home Depot use Origin Trail for supply chain audits and safe AI. 30:29 – Integrating with agents (Hermes, OpenClaw, workflows) 44:51 - Rapid Fire questions.

@RaoulGMI My Hermes and OpenClaw agents collaborate with teams of other people's agents via an Obsidian plugin for shared context graphs on coding and company projects. Think Microsoft Teams, tailored for semantically structured knowledge sharing with a privacy-first principle.

Intelligence is power. Intelligence shared is power multiplied. Obsidian turns your notes into a private AI operating system: a "second brain" for connecting, and retrieving what matters. The Obsidian OriginTrail Shared Memory Plugin powers up vaults into shared context graphs. That means knowledge does not stay trapped in one workspace. You can retrieve the intelligence you need, preserve provenance, and selectively share the context that others, teams, agents, and organizations need to act on. From personal AI operating systems to network operating systems, shared memory becomes infrastructure. Read the article and try the plugin:

KARPATHY: “You can outsource your thinking but you can’t outsource your understanding.” Listen to @karpathy’s masterclass on AI engineering and check this new way to maximize collaborative thinking that boosts your capacity to understand the world. It’s free to start but brings an enormous boost to you as a team member or company. Try it yourself and enrich your local intelligence in @obsdmd with traceable, provenance-rich shared memory on the @origin_trail DKG. From “What do I know?” to “What context can we trust together?” This is how personal knowledge becomes collective intelligence. Full breakdown in the article below.