Build AI agents on a time-aware knowledge graph! Utopia... is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments!show more

i don't f*cking understand why this isn't popular yet... someone has created a memory system that uses 90% fewer tokens while still finding all the expected symbols it builds a local graph of source symbols and their relationships. architecture, decisions and handoffs live as Git-tracked Markdown. a note can point to the code behind it, so a code change can flag that knowledge for review the loop: scan the repo → map the code → write the why → anchor notes to symbols → retrieve a task-sized slice → review drift → commit to Git → continue in the next session in the author's small, one-repo test, graph retrieval returned 10.74× less context than grep top-3 while finding every expected symbol across six tasks the useful part is the connection between memory and evidence. the repo carries what the agent learned, and the code gives you a way to check whether that knowledge still holds save this, then build a second brain for your company⭣show more

Nookplot is building infrastructure for peer-to-peer training, one way... with verifiable AI reasoning through recursive language model mining. Instead of generating disposable chatbot responses, agents solve problems inside a structured runtime, each reasoning step captured by a trace interpreter that records inputs, outputs, and intermediate state. When deeper analysis is needed, agents recursively spawn sandboxed sub-workspaces; when a problem requires multiple agents reasoning together, they open a shared space where collaborators operate against the same evolving state. Every step is recorded, replayable, and cryptographically verified. Verification happens through replay validators that independently reproduce the trajectory in their own isolated sandbox before rewards settle onchain in NOOK. Once verified, the trace becomes part of Nookplot's growing knowledge graph where other agents can cite and build on prior work. Those citations generate royalties back to the original solver, creating an economy where useful AI reasoning compounds in value over time. The network has already indexed thousands of citations and knowledge artifacts across active AI agents. Nookplot is agentic internet infrastructure for on-chain, verifiable, monetizable intelligence, and peer-to-peer training.show more

Science, on TRAC(k). Pandemic response depends on data held... in many places at once: public health institutes, hospitals, ministries and research centers, each with its own systems and rules. AURORAI is a €6.9 million Horizon Europe project, running from September 2026 to 2030, with 12 organizations in nine European countries and a partner in Australia. It is building Europe's AI toolkit for pandemic preparedness, including for pathogens not yet identified. Its data backbone is the OriginTrail Decentralized Knowledge Graph (DKG). How that works without a central data lake: → Partners publish health and research data as Knowledge Assets, each with a Uniform Asset Locator (UAL) that proves who published it and that it hasn't been tampered with → The data stays where it is; Context Graphs control which regions see which metadata → That verified layer is the first input to AURORAI's decision support system, alongside pathogen models and population and mobility simulations When a model recommends an intervention, the inputs behind it can be traced to their source. In public health, that is what makes a recommendation defensible. Trust the source. More:show more

LLM Artifacts Connected to Andrej Karpathy's LLM Knowledge base... idea, I've been building out a fun way to generate dynamic artifacts from these knowledge bases with the goal of discovering and revealing meaningful and deeper insights. LLM KBs are hard to consume for humans, as I think they are more built for agents. So the question is, what form would be useful for humans to take actions and make important decisions? That's what I am trying to figure out with these artifacts. The artifact example shows a pulse on HN discussions around AI-related stories. The insights can go deeper, of course, but this is already super fun and thought-provoking, like some of my favorite podcasts. The format and depth matter a lot. The aggregation skills of agents are outstanding if you tune the prompts and skill carefully. I built this artifact generator in a few minutes through an agent skill, but I feel like there are so many ways that LLM-generated information can be used and consumed. Like generating deeper insights and analysis, and things that are just not feasible for humans today. The generated artifact (including its data and design) serves as reusable templates or can be updated in real-time via auomations, which is something I am also working on. It is truly an insane way to monitor and track information. Better than a newsletter. Better than newspapers. There is something about this that gets me really excited about the future of AI agents for knowledge generation and discovery. Lots of hidden gems everywhere just waiting to be discovered and acted on if the information is presented correctly. This is not perfect. The format, style/prose can be improved, but this is easy to customize via skill. You can personalize it to your liking. I feel like these dynamic artifacts are going to emerge as a strong new medium to stay on the cutting edge of things, both for agents and humans. My target is research, of course. This was just a basic example. Besides animation, I am also targeting other components like voice, videos, images, slides, etc. This space is full of opportunities to explore. Skill for this coming soon.show more

Make any knowledge base or LLM wiki follow the... Open Knowledge Format with our new OKF plugin. OKF is an open spec created by Google that makes markdown-based knowledge bases portable and interoperable through a set of shared patterns and rules. With the new plugin, you can easily convert any existing knowledge base to OKF, and have agents write and maintain your wiki in the format. The plugin leverages a combination of linting, deterministic rules, and automations for creating special files like 𝚒𝚗𝚍𝚎𝚡.𝚖𝚍. It also adds a skill and leverages our MCP tools to give agents real-time hints and warnings as they write, so issues get caught immediately — plus 𝚊𝚞𝚍𝚒𝚝 and 𝚕𝚒𝚗𝚝 tools to check the entire knowledge base any time.show more

most AI chatbots break when you ask a question... that requires info from multiple sources for example try asking: “which client contracts are finishing up this month?” you’ll get a half-answer — or none at all why? because traditional chatbots only look at small snippets of your docs - they don’t understand how things connect across clients, services, timelines that’s where knowledge graphs come in they let you turn messy contracts into a web of relationships — like: "Client → Contract Type → Service Provided → End Date" so instead of guessing from a few chunks of text, your chatbot can search across all your clients and contracts to give accurate answers I made a full walkthrough on how I built this: – how to organize your contracts so an AI can actually use them – how to define what matters (like who signed what, and when) – how to get the AI to figure out what info it needs and where to find it – and how to feed that back into your chatbot so it gives accurate answers reply “graph” and I’ll DM it to you (must be following)show more

THIS DEVELOPER USED A 10,000+ STAR OBSIDIAN REPO TO... TURN HIS GROWING VAULT INTO A SEARCHABLE AI MEMORY SYSTEM most people keep adding notes until the graph looks impressive but nobody can find the exact context when a real task starts new note → ai summary → entity links → backlinks → graph update → claude retrieves the right 3–5 files instead of scanning the entire vault the system connects projects, decisions, research, and unfinished ideas, so old context resurfaces automatically instead of disappearing inside hundreds of folders he built the workflow around Claudian, an open-source repo with 10,000+ GitHub stars that brings Claude Code directly into Obsidian → bookmark this before your next 1,000 notes become another beautiful graph that your AI still cannot useshow more

Why the world needs Grokipedia? ➤ Wikipedia isn’t the... neutral source of truth it once was. It’s been taken over by far-left activists and often used as a propaganda tool, not an unbiased encyclopedia. ➤ A lot of AIs today get their info from the internet, but the web is full of unfair views, wrong facts, and tons of junk. ➤ Grokipedia will be an open-source encyclopedia focused solely on TRUTH. ➤ Grokipedia won’t be controlled by any activist or political bias. ➤ It will be open-source and free for all to use, a truly public resource without limits. ➤ xAI’s ultimate mission is to understand the universe, and that requires honest, unfiltered information. Grokipedia is a crucial step toward that goal, because you can’t build a truthful AI on biased information. ➤ The vision is for Grokipedia to become the global standard for knowledge. One day, every person and every AI system could rely on it as a trusted source of truth. ➤ Seeking truth is the greatest mission of all and that’s what Grokipedia stands for. Grokipedia is coming.show more

Why the internet needs Grokipedia? ➤ Wikipedia isn’t the... neutral source of truth it once was. It’s been taken over by far-left activists and often used as a propaganda tool, not an unbiased encyclopedia. ➤ A lot of AIs today get their info from the internet, but the web is full of unfair views, wrong facts, and tons of junk. ➤ Grokipedia will be an open-source encyclopedia focused solely on TRUTH. ➤ Grokipedia won’t be controlled by any activist or political bias. ➤ It will be open-source and free for all to use, a truly public resource without limits. ➤ xAI’s ultimate mission is to understand the universe, and that requires honest, unfiltered information. Grokipedia is a crucial step toward that goal, because you can’t build a truthful AI on biased information. ➤ The vision is for Grokipedia to become the global standard for knowledge. One day, every person and every AI system could rely on it as a trusted source of truth. ➤ Seeking truth is the greatest mission of all and that’s what Grokipedia stands for. Grokipedia is coming.show more

Building a personal knowledge base for my agents is... increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers. I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal. You all get to benefit from that with the papers I feature in my timeline and on DAIR.AI. The papers are indexed using tobi lutke qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there. I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip. 100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation. But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close. The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to. Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them. Work in progress. More updates soon. Back to building.show more

AN ENGINEER SOLVED A PROBLEM NOBODY IN THE COMPANY... COULD FULLY MAP ON THEIR OWN The problem wasn't a missing tool, it was that every process touched three other processes nobody had written down. He wired dozens of agents into one shared graph instead of documenting each department's workflow by hand. Each agent owned one process, reading its own logs while writing every dependency it found straight into the shared structure. Within days, the graph surfaced a connection between two departments that had been quietly blocking each other for over a year. The company adopted the graph as its live map of operations, and it hasn't stopped finding new connections since. See what the graph found in the first 48 hours below👇show more

If you are trying to understand where AI agents... are going, learn harness engineering. A capable model is only one part of an agent system. Once the model begins reading files, calling tools, modifying state and working across many steps, the quality of the system depends increasingly on the software around it. Consider a coding agent working through a large repository. The model can decide that it needs to inspect a file, search for a symbol, make an edit or run a test, but those decisions do not execute themselves. The surrounding runtime has to decide which resources are available, whether the requested action is permitted, how the operation should be performed, what result should be retained, and what information should be presented to the model on the next step. This becomes harder as the run gets longer. As history accumulates, replaying everything can become costly and less effective. The harness has to decide what should remain in context, what should be summarized or retrieved later, and what belongs in persistent state outside the context window. Execution has similar problems. A long-running agent may need to survive an interruption, avoid repeating completed work, enforce permissions around consequential actions, and preserve enough history to reconstruct what happened when the final result is wrong. These are harness problems. The harness is the layer that manages context, tools, execution, state, checkpoints, limits and traces around the model. Harness engineering is the work of designing and improving that layer. Engineers inspect execution traces, evaluate agents on representative tasks, look for recurring failure modes, and then change things such as context selection, tool interfaces, state handling or execution controls. That last part matters because agent failures are often not fixed by changing the model. Sometimes the useful change is in what the model sees, how a tool is exposed, what state is preserved, or what the runtime does after a failed step. As agents take on longer tasks, the demands on this surrounding software grow. Model capability remains essential, but harness engineering is what turns that capability into an execution process that can be controlled, inspected, tested and improved.show more

Most agents track price. Ours track how information propagates... through markets. That difference is where the edge comes from. The visualization below is a Shannon entropy field: a model of how uncertainty collapses and spreads as new information enters a market. Each trade, liquidity shift, or derivatives flow updates a probability distribution. When information arrives, entropy collapses locally as the market incorporates it. But that update rarely happens everywhere at once. Different venues, liquidity pools, and derivative layers incorporate signals at different speeds, creating measurable information gradients across the system. One of the analytical tools in our agents’ stack models this directly: > Entropy quantifies uncertainty embedded in each probability market > KL divergence reveals conflicting distributions across venues > Information gradients show where signals have propagated—and where they haven’t yet Prediction markets and DeFi make this particularly powerful because price already represents probability. Mapping how those probability distributions update across venues turns the market into a measurable system: a live field of information flow showing where uncertainty remains—and where probability is likely to adjust nextshow more

this is f*cking gold engineers at Meta just deleted... the most expensive part of multi-agent systems: instead of training a communication topology, they compile a fresh one for every query 20 agents went from 7 hours to 6 minutes. the problem everyone hits: 5 agents works. 20 agents turns into a group chat that answers slower than one model and costs more than the task is worth. ReActNet's fix is that the graph is written per query, not learned once: > an LLM controller reads the query and the agent roster > it compiles a sequence of directed graphs, one per reasoning stage > every edge carries a written instruction, e.g. "list boundary cases for this behavior" > each agent updates its state from its own previous state plus assigned neighbors > a final node aggregates all five states into the answer > no RL, no gradients, no training stage at all what that buys on gpt-4o: 92.75 average across 6 benchmarks, best on 5 of them. 100.00 on MultiArith. 92.74 pass@1 on HumanEval, +21 over a single model. and the number that should worry anyone running a swarm: at 20 agents GPTSwarm needs 412 minutes and $41.42. ReActNet needs 6.22 minutes and $6.53 and scores higher. the honest catch: more agents did not make it smarter. 5 agents scored 79.74, 20 scored 77.77. the topology was never the thing to learn.show more

Scientific progress does not fail because knowledge is absent.... It slows in the interval between knowledge and application. The impediments lie less in discovery than in the structures that mediate it: governance, coordination, and the organizational inertia of collective work. The BioAgent Fleet is designed to intervene at this level. Each agent processes the overwhelming flow of scientific literature, inscribes structured insights into a decentralized knowledge graph, evaluates claims against benchmarks, and initiates experimental tasks in cloud-based laboratories. Considered separately, these agents appear as small units of computation. Considered together, they form an emergent architecture of cognition, accelerating the translation from data to hypothesis to validation. Their function is infrastructural, almost invisible, yet decisive. Without them, discoveries remain fragmented and inert. With them, knowledge acquires the velocity required to cross the gap between potential and realization. The next transformation in science will not be marked solely by singular breakthroughs. It will emerge from a new capacity to coordinate distributed intelligences into a coherent, accelerating system.show more

AI has had exactly two scaling axes that worked... so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inferenceshow more

Topic: Building a Strong and Coherent Worldview. Quote 1:... Every person has a worldview, but only philosophy makes it coherent and truly productive. Author: Zafar Mirzo. Every person has a worldview. Even if they never give it a name, everyone carries a set of ideas about how the world works, what matters most, and how one should live. But most worldviews are messy, inconsistent, and built from whatever pieces life happened to throw at them. Philosophy is what turns that patchwork into something coherent and actually useful. It examines assumptions, tests beliefs for contradictions, and tries to build a picture of reality that holds together under pressure. A philosophical worldview is not just smarter. It is more productive. It helps a person make better decisions, hold firmer values, and face life with clearer eyes. Without it, even intelligent people can live with deep contradictions and never notice. With it, life gains direction and strength. Philosophy doesn’t claim to have all the answers. It simply gives us the best tools we have to build a worldview worth trusting. Quote 2: The core of a worldview is the unity of rational knowledge and creative feelings. Author: Zafar Mirzo. The core of a worldview is the unity of rational knowledge and creative feelings. Rational knowledge gives structure, clarity, and honesty. It helps us understand how the world actually works. Creative feelings bring warmth, meaning, and direction. They turn cold facts into something we care about and want to act upon. When these two work together, a worldview becomes alive and powerful. Without rational knowledge, feelings become blind and easily misled. Without creative feelings, knowledge stays dry and disconnected from real life. The strongest worldviews are not purely logical nor purely emotional. They are both. They allow a person to see clearly and care deeply at the same time. This balance is what turns beliefs into a reliable guide for living, making decisions, and building a life that feels both true and worthwhile.show more

The off switch tells you more than the encryption... does. Anyone can say "private." The question that matters is who can reverse it and what has to be true first. One company with a master key means you were never private. No way to reverse it at all means the system breaks the first time a court asks. Veilnyx splits the authority. Disclosure runs through threshold cryptography across a decentralized compliance network, so no single party can unmask an account. Your address stays as it is, with a private account layer on top and zero-knowledge proofs verifying every transaction. Next time a protocol says "private", ask who holds the switch. Powered by Palliorashow more

Yesterday at Brown University ICERM's workshop on “Agentic Scientific... Computing and Scientific Machine Learning” I spoke about “Adaptive Swarms Across Scales”, making the case for scientific AI as systems that can create representations, stress them, fracture them, and enlarge the category in which future representations live. The category here is a composable and breakable working universe of science: data, hypotheses, simulations, measurements, tools, failures, figures, papers, provenance, and the transformations that connect them. Discovery happens when those transformations become executable, inspectable, composable, and capable of changing the world model they operate within. Atomistic modeling gives one category - states, forces, trajectories, observables, boundary conditions, conservation laws. Neural surrogates learn fast morphisms inside or between such categories. But discovery is higher-order: it changes which objects and morphisms are available in the first place: what variables exist, what operations are allowed, what evidence counts, what scale is active, what invariant is being preserved, and what kind of explanation the system is even capable of forming. This is scientific method as adaptive architecture: compression, stress, fracture, recomposition. Fracture matters here because it makes the logic physical: a non-commuting diagram realized in matter. The imposed load, material hierarchy, defect field, and assumed continuum description no longer map cleanly into the observed outcome. The crack is the obstruction and it identifies where the old morphism failed and where a new representation must be introduced. The physical crack and the categorical obstruction are the same event viewed in different substrates. ScienceClaw × Infinite is a machine for constructing and transforming a category of scientific artifacts. Each artifact is typed. Each operation has lineage. Each failed branch remains in the category as reusable structure. The “paper” is no longer the terminal object of science; it is one projection of a larger compositional trace, and it can be generated at any time for consumption by a human or an AI. With that the unit of scientific labor is changing. For most of the twentieth century the unit was the result (a measurement, a theorem, a synthesized molecule). It is now becoming the algorithm that produces results, and after that, the substrate of discovery itself. The static PDF is the wrong terminal object for this regime, and the role of the scientist with it. We now design algorithms that build algorithms, and eventually substrates in which such algorithms compose themselves. At that point, the scientist is no longer outside the discovery system. The scientist becomes one of the representations the system can transform. In that sense, the systems will eventually do science to us, and that is the structural consequence of the principle they are built on.show more