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

THIS IS F*CKING DANGEROUS ex-SpaceXAI employee leaked a second-brain... template for Grok Bot. 99% of Grok Bot users don’t know this setup exists your documents, voice notes, research, and past decisions become connected memory. ask why you rejected an idea six months ago, and it retrieves the reasoning and sources. less repeated work, fewer wasted tokens, and answers grounded in what you already know 20 GitHub repos to recreate the setup: 01 Basic Memory → keep knowledge in readable Markdown files that an AI can search and update through MCP. your notes stay accessible outside the chat 02 Cognee → turn documents and conversations into persistent knowledge graphs, connecting decisions to the discussions and evidence behind them 03 MemOS → add a memory layer that stores, retrieves, and manages information across tasks, with feedback for correcting what the system remembers 04 Mem0 → retain useful preferences, facts, and interaction history so connected workflows can retrieve relevant memories in later sessions 05 Graphiti → track relationships and how facts change over time, preserving the difference between what was true before and what is true now 06 LightRAG → combine graph relationships and vector retrieval to find connected information across documents, with support for incremental updates 07 PageIndex → build a navigable tree of a long document so retrieval can find relevant sections with traceable page references 08 Karakeep → collect links, notes, images, and PDFs in a searchable library, with optional automatic tagging and summarization 09 Linkwarden → preserve useful web pages as archived copies, keeping the source available even when the original link disappears 10 Paperless-ngx → turn scanned documents and paperwork into an organized, searchable archive that can feed your knowledge workflow 11 Unstructured → break documents into structured elements so your ingestion pipeline can separate useful content before indexing it 12 MinerU → extract readable content from complex PDFs, scans, tables, and office documents, with references back to document locations 13 whisper.cpp → transcribe recordings locally so spoken ideas and meeting discussions can become searchable text in your archive 14 pgvector → store embeddings alongside your structured data in Postgres, then retrieve related passages with metadata and filters 15 sqlite-vec → add vector search to a lightweight SQLite database for a local memory store without a separate database server 16 Meilisearch → combine keyword and semantic search so your archive can find both an exact project name and a related idea 17 Neo4j → store explicit connections between people, projects, sources, and decisions, then query how those pieces relate 18 watchfiles → detect changed files and trigger updates in your indexing scripts, keeping the archive current without repeatedly processing everything 19 Syncthing → synchronize your knowledge files between computers so the notes you capture and the files your workflow reads stay aligned 20 restic → create encrypted backups and recover previous snapshots when a bad edit or accidental deletion damages your knowledge collection start with one project and one memory backend. connect it to Grok Bot through supported MCP tools, APIs, or local scripts, then add the capture and retrieval pieces you need test it with a question you already know the answer to: “why did we reject this approach?” a useful second brain should bring back the original reasoning, its evidence, and any later decision that replaced it that’s when an old conversation becomes something you can build on months later save this. the work you’ve already done should keep paying you back the article below shows how to reuse that knowledge without loading your entire archive into every Grok Bot conversation ↓show more

Finally! A RAG over code solution that actually works... (open-source). Naive chunking used in RAG isn't suited for code. This is because codebases have long-range dependencies, cross-file references, etc., that independent text chunks just can't capture. Graph-Code is a graph-driven RAG system that solves this. It analyzes the Python codebase and builds knowledge graphs to enable natural language querying. Key features: - Deep code parsing to extract classes, functions, and relationships. - Uses Memgraph to store the codebase as a graph. - Parses pyproject to understand external dependencies. - Retrieves actual source code snippets for found functions. Find the repo in the replies!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

You can break down every memory implementation into two... axes - time: what changed, and when - connections: what links to what supermemory's graph keeps both on atomic facts, the latest fact wins, the old one stays as history, and you never draw an edgeshow 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

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

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

You can now view Knowledge Base retrieval chunks directly... in the Test LLM feature🌐 Get full visibility into how your Knowledge Base is being used. Instantly verify whether queries retrieve the right information — and fine-tune as needed.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

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

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

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

Imagine thousands of AI agents not trapped in one... platform, but connected across a living network. Each agent can: — help with tasks — exchange signals — collaborate in rooms — access knowledge — coordinate actions — improve over time This is not a chatbot. This is an agent mesh. A decentralized layer where intelligence can work together — across people, devices, and environments. DRIVE369 is building that layer. #agent #ai #depin #web3 #p2p #mesh #agi #drive369show 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

late to the party but built a UI layer... on top of the wiki my OpenClaw🦞 agent writes and maintains, based on exactly what Andrej Karpathy describes here. obsidian vault underneath, react frontend on top: search, an interactive knowledge graph, topic browsing, article pages with tables of contents + neighborhood mini-graph and many more.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

Today SciPhi is open-sourcing Triplex, a SOTA LLM for... knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.show more