Facts - Moozonian Search

synaptale.com• Jul 26, 2026• 1 min read

Show HN: What 180k words look like as a temporal knowledge graph (Oz series)The graph is free to explore and requires no registration.SynapTale builds a model of a story as a temporal graph made up of nodes (entities) and edges (their actions and relationships). The graph is not a visualization of the wiki. The wiki, timelines, relationship histories, and analytics are projections of the graph.The current demo contains 232 entities, 1,852 edges, and a snapshot of the story’s state at every chapter. By chapter 100, it still remembers a promise made in chapter 8 and turns the story into a set of source-verifiable facts.The most interesting things can be found in the graph itself and in the Analytics tab. A few things I found:1. The character with the highest kill count is the Tin Woodman—the same character who cries over a beetle he accidentally crushed. Dorothy comes second, with three killing events. 2. Dorothy never deceives anyone during the first 100 chapters of the series. 3. The Scarecrow’s debt to the stork has remained active for 92 chapters, starting i

github.com• Jul 21, 2026• 1 min read

Show HN: Inflexa – open-source Intelligence for BiologyHey HN!Inflexa is an OSS-first TUI for agentic-AI reproducible biological analysis with provenance tracked on every step. It's a better designed Claude Science (bar the GUI for now).Before this, we spent years building a cloud multi-omics analysis platform, working alongside research teams in pharma, biotech, and academia.Our vision is as follows: - OSS first - Data privacy, and security are of utmost importance - Agents are untrusted actorsAgentic products do not solve a core architectural and design problem: provenance.How do you build up the body of evidence to support your claims from hundreds of chat messages, scattered artifacts (scripts, intermediary data files, random research files)?We are one of the first in the biotech space to propose using an established specification for provenance, which its extremely fitting for the world of agentic AI: [W3C PROV](https://www.w3.org/TR/prov-overview/).Our provenance is deterministic and driven programmatically. Our architecture imposes

github.com• Jul 19, 2026• 1 min read

Show HN: Phosphor – a CRT TV video player for your MacI built Phosphor. Phosphor is a CRT TV on your Mac. It can take almost any video file and play it as if it’s being shown on a real CRT.It tries to emulate a CRT all the way down to the electron beam and the individual red, green, and blue phosphors. It simulates the beam scanning across the screen, 240p and 480i raster modes, phosphor persistence, glow, bloom, convergence, composite-video artifacts, and curved glass.It’s built natively using Swift and Metal and is hyper optimized for Apple Silicon, so it runs like butter. Video frames stay on the GPU, and the expensive CRT reconstruction only runs when a new video frame arrives.You can choose between aperture grille, slot mask, and shadow mask phosphors. You can also switch between RGB, S-Video, NTSC, and PAL signals, along with consumer TV, Trinitron, and studio-monitor profiles.Parts of the renderer are based on CRT-Guest-Advanced HD, which I adapted to native Metal and expanded with beam timing, individual phosphor masks, HDR output

pastehex.dev• Jul 16, 2026• 1 min read

Show HN: I've built tldraw for HTML and Markdown pages (with encryption)Hello, HN!This is a small app I've built to satisfy three pains/wishes I've had for a while and I think there might be people out there who can benefit from it as well.1. I want to pop up a new tab, start writing my thoughts and, maybe, share them over the internet. As fast as I can and with as little friction possible. tldraw totally does this for drawing stuff in a whiteboard but for text, Obsidian is a local tool that requires installing and Notion is too involved. I want a simple link that just works the moment you navigate to the page.2. Sometimes I wanted to share code or other text artifacts with customers over Discord, but the platform caps messages to a certain length before it forces you to submit a .txt. Pastebin kinda fills this gap but it's an old site and it doesn't handle BIG pastes very well also it doesn't double as your own document vault (plus I don't care about all their "public pastes" thing).3. This is a recent one. Now, due to AI tools, everyone is sharing Markdo

bing.com• Jul 16, 2026• 1 min read

Can anti-inflammatory diets cure arthritis? Orthopaedic surgeon Dr Akhilesh Rathi separates fact from online mythsCan cutting out certain foods cure arthritis? Dr Rathi explains the facts behind anti-inflammatory diets and what really helps joint health.

namestrace.com• Jul 12, 2026• 1 min read

Show HN: How old is someone named Gertrude? SSA data says 80Hi, I build a website about everything related to names. I focused on two core ideas, verified data sources and a clean UI. The reason I made this website is, pretty much everyone has a name, and at some point, most ppl looks it up. And I want to be the website with definitive information on it which is reliable.I recently came up with a new feature (as suggested by the title of this post and idea came from FiveThirtyEight form a 2014 article, however I don’t think their tool exists anymore), where you can type your name and it will then tell you a bunch of interesting facts for example the typical age of people with this name, how many of them are alive etc.All the data comes from open-source data, and aggregated. I would love to put some fun facts here about certain names, but I think its best if you explore for yourself fun facts about your own names. The biggest weakness I feel about this website, is due to my infrastructure to keep it running form free I’m limited on how many page

news.ycombinator.com• Jul 11, 2026• 1 min read

Bitemporal provenance in agent memory: What did we believe, when, and whyCozoDB, a transactional relational-graph-vector database with embedded Datalog in Rust, went dormant in December 2024. We hard-forked it as MnesticDB (not official CozoDB), under an MPL-2.0 license, to continue Ziyang Hu and the Cozo Project Authors' vision of building a "Hippocampus for AI", or agentic memory.But agentic memory isn't a pile of current facts with a log of past decisions. It has to track change over time, and be auditable. We've recently shipped several features that make this possible.First, we added a distinction between valid time (when a fact is true about the world) and transaction time (when the database came to believe it). This allows time travel, the ability to audit the memory at any point and see what knowledge any past decision was based on. Every write draws its transaction time from a crash-safe monotone commit clock, an atomic high-water mark persisted inside the same transaction that commits the data, so the clock can never advance without the write land

github.com• Jul 11, 2026• 1 min read

Show HN: A deterministic I Ching engine, cross-validated against another implI built a deterministic engine for I Ching (六爻 / Liu Yao) hexagram casting and open-sourced the core (Apache-2.0). I want to be upfront that the interesting part here is not the divination — it's a testing problem, and I'd like feedback on how I handled it.The engine takes a moment in time plus a coin toss and mechanically derives a fully annotated chart: the hexagram, its palace, the stem-branch (najia) assignments, the "six relatives," moving lines, void days, and the line-strength skeleton. It does not interpret anything — it only emits hard, mechanical facts.The problem that made this interesting: the rules are ~3000 years old, written in classical Chinese, and different schools contradict each other. There is no official answer key, and human experts disagree and are sometimes wrong. So the tests I'd naturally write just encode the same assumptions my code does — if I misread a rule, the code and its test are wrong together and both stay green. The self-validation paradox.My way o

github.com• Jul 10, 2026• 1 min read

Show HN: An MCP server that lets AI agents request disability insurance quotesHi HN. I own an online insurance agency, a painfully old-school industry. I am not a developer. I vibe-coded it all in Claude Code, then reviewed and tested before anything shipped. Which is part of the story I guess, that a small firm with curious and reasonably capable people can now operate agent infrastructure that would have required a contractor two years ago.I'm trying this because a growing share of our prospects start by asking their AI of choice what coverage to buy and who to get it from. Assistants can read my site, so like everyone else I'm trying to get recommendations via content. But the next natural step is agents actually taking actions on sites rather than just reading them, so I created seven tools, six read-only (a verified-facts knowledge base, carrier comparison, specialty and education guides, benefit-cap math, rider definitions) and one action, "quote request," which writes a lead straight into our CRM through the same Salesforce web-to-lead path that our web f

evenkeel.c6e.me• Jul 9, 2026• 1 min read

Show HN: EvenKeel – a free financial planning chatbotEvenKeel is an LLM-powered chatbot that helps with budgeting, financial planning, retirement savings, tax optimization, etc.It is a harness around Gemini 3 Flash Preview that provides a library of skills for things like: evaluating a house purchase, insurance planning, portfolio asset allocation, etc. as well as tools for doing financial math and Monte-Carlo simulations.You can upload files as well as chat, and as you go, it updates a "Financial Picture" with relevant facts about your situation, so you can see what data has been collected, track goals, etc. this picture along with recent chat interactions is fed into the model each turn so the most important details are always in context.Your data can be exported or account deleted from the Settings page at any time, or you can interact anonymously until LLM spending gets too hot.Hope you find it helpful!

github.com• Jul 7, 2026• 1 min read

Show HN: Bike4Mind – open-core AI workbench; any model, agents, RAG, self-hostHi HN, I am Erik Bethke, game dev that has been making online games for 30+ years (Starfleet Command, GoPets, FarmVille, Mafia Wars).For the last 3 years I have been building Bike4Mind and now I have to put my big boy pants on and 'go to market'. Ugh, it would be so much more cozy to fire up a few more agents and fix a few more bugs, polish some more UX - or hey how about a new feature that does Q, R or S?What is Bike4Mind? I started Bike4Mind to be the home of a bunch of AI augmented game development tools, and over time have just kept adding features. It is a full cognitive workbench we have all of the features - notebooks, files, data lakes & RAG, agents (different forms), generate share-able artifacts in react or python. We have secure websockets to connect to our CLI - B4M CLI, so it is truly batteries included - and runs any model - OpenAI, Anthropic, Gemini, xAI, Bedrock. Switch models during a conversation, fork a notebook, run 4 different models on the same prompt, loads of im

armoredmeatball.substack.com• Jul 7, 2026• 1 min read

Show HN: Building My Own Public HTML Library for Async LearningI like creating HTML artifacts from my AI agents to facilitate async learning. The problem is that I find many simple flows are more cumbersome than they should be. Artifacts should be fast to navigate to, easy to organize, quick to share and for others to open and read.I built html-hub.com/browse as a public HTML for async learning, and write about some of my learnings in the blog post. Some features encompassed include: agent transcripts, artifact citations, and auto-sorting an artifact into a directory

news.ycombinator.com• Jun 29, 2026• 1 min read

Ask HN: Have the founders of Palentir and Anduril ever read Tolkien?The Lord of the Rings famously includes very strong thematic critiques of industrialization and technological encroachment into everyday life.[0] Tolkien portrays the titular relics, as well as many of the other magical artifacts in Middle Earth like the palentiri, as tools of evil, destruction, and environmental devastation. Tolkien cited his upbringing in the rapidly industrializing English Midlands and his experiences in World War I as major influences, and used the typical Arthurian framing of good versus evil to contrast natural, agrarian life with the soulless, mechanical efficiency of industrialization.So my question is--have the founders of Palentir[1] and Anduril[2] ever actually read JRR Tolkien, and if so, did they comprehend its text? Assuming they do understand the symbolism behind their company names, are they just trolling us; Or are they simply engaging in a gimmicky, cynical effort to commoditize our nostalgia as a branding exercise for manufacturers of the literal too

news.ycombinator.com• Jun 28, 2026• 1 min read

Ask HN: Local CJK/Latin entity extraction without shipping a model?I am building a local-first Mac writing app, and I am stuck on the story-memory layer.The problem: given a long fiction manuscript, I need to extract characters, aliases, relationships, locations, timeline facts, and unresolved plot facts. It has to work reasonably well across CJK and Latin-script text. For example, Chinese/Japanese/Korean names do not tokenize like English names, aliases may be implicit, and the same character can appear under several surface forms across chapters.I do not want to ship a huge local model just to do this. The app should work locally on normal Macs, and the extraction/indexing layer needs to be fast enough to run repeatedly as the manuscript changes.What I am trying to figure out:- practical local NER/entity-linking options for CJK + Latin text - whether a hybrid rule-based + embeddings approach is realistic - how to store weak candidate facts before they are confirmed - how to link extracted facts back to exact manuscript evidence - how to avoid one ba

motion.so• Jun 22, 2026• 1 min read

Show HN: Frontier AI for Motion DesignHey HN, meet Motion — a frontier agent for motion design.Here’s how it works:1. Give Motion a prompt — include any context like product links, X threads, YouTube videos, personal assets, and design MD. Motion will reference styles, incorporate research, and storyboard scenes.2. Motion creates the video — it can orchestrate entire explainers, launch videos, logo animations, convert articles to video, or even add motion design to your existing videos.3. Edit everything — after generation, edit everything directly: resize, drag and drop, modify elements. Or just chat with Motion to iterate. No need to re-generate entire scenes or deal with hallucinated artifacts.We made Motion's launch video using Motion, check it out here: https://x.com/_adishj/status/2062203755718930550?s=20Would love to have the community try Motion and give us any and all feedback — we'd love to hear it!

tot.page• Jun 15, 2026• 1 min read

Show HN: tot.page – git-backed publishing for HTML and Markdowntot.page is a simple service that produces a share link for any html or raw markdown from your terminal. Nothing new there except it's backed by git with CDN-like delivery (using cloudflare artifacts [1]). tot file.html → raw public living URL, and: → immutable hash snapshot URL → no account needed (treat links like excalidraw)The docs on the home page are being served by tot.This is a small thing powering a bigger one: https://tot.page/0CW7xV96XMxnalrzwRl4eQRated E for Everyone:https://github.com/plannotator/tot[1] https://www.cloudflare.com/products/artifacts/

news.ycombinator.com• Jun 13, 2026• 1 min read

Show HN: I am running 3 coding agents non-stop over the last 3 days. Here is how1. Headless modeHeadless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run.2. Ask humanThe traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu...3. Tasks queueBeads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can create tasks, define dependencies between tasks, and have status, priorities, hierarchy. Beads helps prevent multiple tasks from being claimed by > 1 worker.4. Worker artifactsWe want to be able to monitor how a worker is doing, at what stage it is, and resume it after a restart. For every task we can create a dedicated folder using the beads task id and put into it what we need. I put there: - plan and status md - knowledge md - events.jsonl - s

bing.com• Jun 10, 2026• 1 min read

How cultural backgrounds shape financial forecastsThere's a funny thing about facts. Two people can look at the same ones but interpret them very differently, depending on their styles of thinking. On Wall Street, analysts with short-term or ...

github.com• Jun 6, 2026• 1 min read

Show HN: Ccgs – Collaborative Claude Code sessions, stored in Git branchesMy team uses Claude Code daily, and the sessions have become some of the most useful artifacts we produce. But they're trapped in ~/.claude/projects/ on whichever laptop they happened on. There's no good way to hand a colleague "the session where I untangled the migration" so they can claude --resume it and keep going from where I left off. Enter ccgs: Share Claude Code sessions through an orphan branch (@ccgs/) in your existing repo's remote- Session files carry the author's absolute paths. On pull, ccgs rewrites the working dir back to your path so resume actually works — surgically editing only the structural cwd field, not a blind find-and-replace that would happily corrupt the transcript.- Everything goes through git plumbing (hash-object/commit-tree/update-ref) against a throwaway index. It never touches your working tree, index, or current branch, and it's fine with a dirty tree. It will not git checkout something behind your back.To try it without installing: `npx claude-git-se