news.ycombinator.com
Show HN: AFS – filesystem-native memory layer for AI agentshttps://news.ycombinator.com/item?id=47062802I've been building multi-agent AI pipelines and kept running into the same structural problem: agents are stateless by default. Every session restart discards everything they learned. In multi-agent systems it compounds — Agent-1 learns something Agent-2 will never know. I started calling it "agent amnesia." AFS is my attempt to fix this. The central architectural decision is unusual: your filesystem IS the memory layer. There's no separate database process to run, no cloud service to authenticate against. AFS stores memories as JSON files in a `.afs/` directory, with SQLite FTS5 for full-text search, HNSW indices for vector similarity, and msgpack-encoded graph edges for relationships. *Three-tier memory lifecycle (automatic)* Memories auto-migrate without explicit management: - Working memory (< 24h): raw observations, fast access, no compression- Episodic memory: full history with provenance, searchable - Semantic memory: auto-consolidated knowledge (scheduler synthesizes patterns fFeb 18, 2026 4:31 PM
esa.int
Revealed: 10 new insights in climate sciencehttps://www.esa.int/Applications/Observing_the_Earth/FutureEO/Space_for_our_climate/Revealed_10_new_insights_in_climate_scienceEach year, the world’s leading climate scientists evaluate the most critical evidence on how our planet is changing. Their assessments draw heavily on data from Earth-observing satellites – and the latest report delivers a stark warning: the planet’s energy balance is drifting further out of alignment, ocean warming is now accelerating, and the land’s capacity to absorb carbon is declining, along with other troubling trends.Feb 18, 2026 1:00 PM
news.ycombinator.com
Show HN: Fixing AI's Core Flaws, A protocol cuts LLM token waste by 40–70%https://news.ycombinator.com/item?id=47045604WLM (Wujie Language Model), a protocol stack + world engine that rethinks AI from token prediction to structural intelligence. I built this to fix the problems we all deal with daily: hallucination, drift, uncontrollable behavior, black-box reasoning, unstructured knowledge, and chaotic world/agent generation.The Pain We Can’t Keep IgnoringCurrent LLMs/agents are token predictors, not intelligences. They suffer from:• Hallucination: No grounded structure → guesses instead of knowing.• Persona drift: Personality is prompt-hacked, not structural.• Uncontrollable behavior: Sampling, not deterministic structure.• Black-box reasoning: No traceable reasoning path.• Knowledge soup: Embeddings/vectors, no formal structure.• Fragile world models: Prediction, not interpretable structure.• Random generation: No consistent causal/world rules.We’ve patched these with RAG, fine-tuning, prompts, RLHF — but they’re band-aids on a foundational flaw: AI lacks structure.How WLM Solves ItWLM is a 7-layer Feb 17, 2026 10:01 AM
bing.com
EC-Council Expands AI Certification Portfolio to Strengthen U.S. AI Workforce Readiness and Securityhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a89847c502f4d98af6246f8a51fd74c&url=https%3A%2F%2Fwww.tennessean.com%2Fpress-release%2Fstory%2F143749%2Fec-council-expands-ai-certification-portfolio-to-strengthen-u-s-ai-workforce-readiness-and-security%2F&c=2913691642603927758&mkt=en-usTAMPA, FL, INDIA, February 11, 2026 /EINPresswire.com/ — EC-Council, creator of the world-renowned Certified Ethical Hacker (CEH) credential and a global leader in ...Feb 16, 2026 10:10 AM
bing.com
How to make Background Transparent in Paint 3Dhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a86530b20fc4c7dbb4c2179bcb830a6&url=https%3a%2f%2fwww.thewindowsclub.com%2fremove-background-image-with-paint-3d-in-windows-10&c=2815641755163138857&mkt=en-usBefore we go ahead with the editing, there is a fundamental idea that you should know. Paint 3D uses an algorithm and bit of user input to figure out what should be removed. The less distraction or ...Feb 14, 2026 10:57 PM
bing.com
How to make Background Transparent in Paint 3Dhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a865314d89742b194b9decba8a2d3f5&url=https%3a%2f%2fwww.thewindowsclub.com%2fremove-background-image-with-paint-3d-in-windows-10&c=2815641755163138857&mkt=en-usBefore we go ahead with the editing, there is a fundamental idea that you should know. Paint 3D uses an algorithm and bit of user input to figure out what should be removed. The less distraction or ...Feb 14, 2026 10:57 PM
bing.com
How to make Background Transparent in Paint 3Dhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a8652f6c05647099082cf82e4d568e9&url=https%3a%2f%2fwww.thewindowsclub.com%2fremove-background-image-with-paint-3d-in-windows-10&c=2815641755163138857&mkt=en-usBefore we go ahead with the editing, there is a fundamental idea that you should know. Paint 3D uses an algorithm and bit of user input to figure out what should be removed. The less distraction or ...Feb 14, 2026 10:57 PM
bing.com
How to make Background Transparent in Paint 3Dhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a86531be742407198f8280597e2c1a1&url=https%3a%2f%2fwww.thewindowsclub.com%2fremove-background-image-with-paint-3d-in-windows-10&c=2815641755163138857&mkt=en-usBefore we go ahead with the editing, there is a fundamental idea that you should know. Paint 3D uses an algorithm and bit of user input to figure out what should be removed. The less distraction or ...Feb 14, 2026 10:57 PM
bing.com
How to make Background Transparent in Paint 3Dhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a86532205dd4f69a060a47729eefa61&url=https%3a%2f%2fwww.thewindowsclub.com%2fremove-background-image-with-paint-3d-in-windows-10&c=2815641755163138857&mkt=en-usBefore we go ahead with the editing, there is a fundamental idea that you should know. Paint 3D uses an algorithm and bit of user input to figure out what should be removed. The less distraction or ...Feb 14, 2026 10:57 PM
flipcloc.com
Show HN: An aesthetic customizable online flip clock and my first ever apphttps://flipcloc.com/I know there are many flip clocks out there, but flip clocks are truly wonderful and my version FlipCloc is smooth, optimized, detailed, and fully customizable to match your workflow / aesthetics / mood.Often, flip clocks online feel half baked: choppy animations, bad flipping animations, lazy flap separations, sometimes not even distinct top and bottom flaps, zero customization, and so on. After playing with time related concepts in various projects, I wanted to build an app of my own and made this using WebGL and React. This is my first ever app and I’m quite proud of this beta version.Try the full experience for free in any browser. No ads, just a beautiful clock you can run in a tab, window, or PiP while working or studying. (One-time purchase unlocks saving custom themes, settings, and presets and is usable on the web, app, or screensaver.) You can start by trying out some of the different preset styles and then customizing it to your preferences.Key features:• Show/hide seconds, Feb 12, 2026 12:52 PM
klava.space
Show HN: Privacy-first iOS Keyboard with above-key predictionshttps://www.klava.space/Hey y'all, building Klava – an iOS keyboard inspired by BlackBerry, Windows Phone and other iconic aesthetics. It's pretty cool, I love it.It started because I missed BlackBerry keyboard's above-key predictions dearly. That is, suggestions are displayed above individual keys as you type, and you can flick them up to input words. Then came the realisation that I am violently nostalgic for the design languages of the past, when phones were fun – and have been looking for something like that on iOS for ages. Lastly, I realised that everything should be highly customisable and privacy-first because that's nice for me and for everyone.v1.2 now out with 25+ languages supported. Any Qs on the peculiarities (there are a ton) of building a custom iOS keyboard – feel free to shoot, and any thoughts & feedback.Feb 11, 2026 6:11 PM
news.ycombinator.com
Show HN: GHOSTYPE – AI voice input that learns your writing stylehttps://news.ycombinator.com/item?id=46971643Hello HN,I’m the creator of GHOSTYPE.I built this because I wanted a voice input workflow that didn't feel like talking to a chatbot. I wanted something that felt like a "neural extension" of my keyboard.It’s a macOS-native app that sits between your voice and your active window. Here is what it actually does:The Core Input Workflow:Push-to-Talk & Smart Send: Hold a global shortcut to speak. It detects the active app to determine the correct send method (e.g., Cmd+Enter for Slack vs Enter for Discord).Inline Editing: You can format while speaking. Need a line break, a specific spelling, or a bulleted list? You just say it, and it handles the formatting inside the sentence before outputting."Call Ghost": Post-processing commands (translate, polish, expand) are available immediately after speaking, before the text is typed out.The Experimental Stuff (WIP):1. Ghost Twin (Style Transfer): I call this a "Virtual Personality Engine" (a bit pretentious, I know). It analyzes your local writingFeb 11, 2026 6:35 AM
bing.com
EC-Council Expands AI Certification Portfolio to Support Singapore's AI Workforce Readiness and Trusted AI Adoptionhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a89847c502f4d98af6246f8a51fd74c&url=https%3A%2F%2Fwww.marketwatch.com%2Fpress-release%2Fec-council-expands-ai-certification-portfolio-to-support-singapore-s-ai-workforce-readiness-and-trusted-ai-adoption-cacb128f&c=16712925327618455131&mkt=en-usThe MarketWatch News Department was not involved in the creation of this content. SINGAPORE, Feb. 10, 2026 (GLOBE NEWSWIRE) -- EC-Council, creator of the world-renowned Certified Ethical Hacker (CEH) ...Feb 10, 2026 10:30 AM
dwrite.me
Show HN: Dwrite.me A minimalist writing space that blocks copypaste to fight AIhttps://dwrite.meLately, the internet has started to feel loud, yet incredibly empty. Every time I browse Google, Medium, or news portals, I run into articles that feel "too perfect." The structure is flawless, the grammar is impeccable, but there is absolutely no soul in them.We all know why. It’s AI.As a developer, I love technology. But as a human, I’ve started to crave writing that has "scars"—writing that has emotion, rhythm, and is actually born from someone’s messy brain, not a polished prompt.That’s why I built dwrite.me.An Internet That’s Too Fast My frustration is simple: We live in an age where everything is expected to be instant. Need a 2,000-word article? One click. Need an opinion? Ask a chatbot.But here’s the problem: If everyone is using AI to write, why should we bother reading each other at all? We aren't exchanging thoughts anymore; we are just swapping machine-processed data. Our way of thinking is becoming lazy. We no longer value the "friction" of struggling to find the right worFeb 9, 2026 5:03 AM
esa.int
The curious case of why methane spiked around Covidhttps://www.esa.int/Applications/Observing_the_Earth/FutureEO/Space_for_our_climate/The_curious_case_of_why_methane_spiked_around_CovidWith fewer cars on the road, planes in the air and factories running, the skies seemed cleaner during the Covid-19 pandemic. However, while there was a decline in pollutants such as nitrogen dioxide, scientists were surprised to see that methane surged in the early 2020s and then dropped – and now they know why.Feb 6, 2026 7:30 AM
spacedaily.com
Rock microbes reveal hidden groundwater carbon enginehttps://www.spacedaily.com/reports/Rock_microbes_reveal_hidden_groundwater_carbon_engine_999.htmlBerlin, Germany (SPX) Feb 03, 2026 Deep underground, microbial communities living on rock surfaces are emerging as powerful but largely overlooked drivers of groundwater chemistry and carbon storage. A team from the Cluster of Excellence Balance of the Microverse at Friedrich Schiller University Jena has now shown that these attached microbes follow fundamentally different strategies from free-floating cells in groundwater, withFeb 4, 2026 3:53 PM
news.ycombinator.com
Even as a fast dev, I wasn't fast enough for my ideas. Then came Vibe Codinghttps://news.ycombinator.com/item?id=46877447The Speed Trap of Modern DevI’ve always been a fast developer. I know my stack, I know my shortcuts. But there was still a painful latency between my mental architecture and the screen. My ideas always outpaced my output. No matter how fast I typed, the "Implementation Friction" was a tax on my creativity.The 10x Shift: Moving at the Speed of ThoughtVibe Coding didn't just make me "better" — it removed the mechanical bottleneck. I’m no longer translating thoughts into code; I’m describing the vibe of the system and watching it manifest.The Result: I’m building things alone that previously required a dedicated team or a month-long sprint.The High: The dopamine hit isn't just about "it works." It’s the rush of zero latency. It's the feeling of your brain being directly plugged into the compiler.The "Dark Side" of Hyper-FlowBut here’s the rub: When you remove the friction, you remove the "sanity check."The Addiction: The feedback loop is so fast that it becomes a slot machine. Each promptFeb 3, 2026 9:19 PM
asktotle.com
Show HN: I turned my PDFs into audiobooks I can have conversations withhttps://asktotle.comHey HN,TLDR: Upload any document, get an audiobook with synced highlighting you can pause and talk to.I'm a self-taught dev (admittedly mediocre), currently between jobs and my brain is absolutely fried from social media. I can't read anymore. My eyes glaze over after two paragraphs.So I went down a rabbit hole looking for scientifically proven ways to actually focus while reading:- Encoding info visually AND aurally reduces mind wandering by up to 40% - Retrieval practice (asking questions) beats passive re-reading every time - Background music matched to content keeps you in flowCouldn't find anything that did all this. So I built it myself:- Synced text highlighting while you listen - Talk with your book; pause and ask "wait what does that mean?" and it knows exactly where you are (won't spoil what's ahead) - Adaptive background music that matches the mood of each pageI've removed all slop. No flashy features, no gamification etc. etc. Just reading on steroids for fried brains, likeFeb 2, 2026 11:49 AM
nono.sh
Show HN: Nono – Kernel-enforced sandboxing for AI agentshttps://nono.shHey HNLuke here.I built nono and got it out quick then I expected, in response to the openclaw carnage, but its use is beyond openclaw.The problem: AI agents execute code on your machine. Prompt injections, hallucinations, or compromised tools can read ~/.ssh, exfiltrate credentials, or worse. Application-level sandboxes can be bypassed by the code they're sandboxing.I have been around security for a long old time now (i started something called sigstore a few years back) and have seen this pattern so many times before.The solution pitch: nono uses OS-level isolation that userspace can't escape:Linux: Landlock LSM (kernel 5.13+) macOS: Seatbelt (sandbox_init) After sandbox + exec(), there's no syscall to expand permissions. The kernel says no.What it does:nono run --read ./src --allow ./output -- cargo build nono run --profile claude-code -- claude nono run --allow . --net-block -- npm install nono run --secrets api_key -- ./my-agentFilesystem: read/write/allow per directory or file NeFeb 1, 2026 9:35 PM
github.com
Show HN: Self-hosted RAG with MCP support for OpenClawhttps://github.com/2dogsandanerd/ClawRagI've been using OpenClaw to control my home server via WhatsApp, but it couldn't access my documents. Instead of uploading my private contracts to OpenAI, I built ClawRAG – a self-hosted RAG engine that connects to OpenClaw via MCP (Model Context Protocol). Now I can ask "What did the contract say about liability?" and get cited answers, not hallucinations.Most RAG systems are either too complex for a solo dev's home setup or they rely on cloud-hosted vector stores. I needed something that runs in a single Docker container, understands messy PDFs (tables!), and integrates natively as a "tool" for agents rather than just another REST endpoint.## Technical Deep Dive### Why MCP instead of REST? I chose the Model Context Protocol (MCP) because it provides structured schemas that LLMs understand natively. The MCP server exposes `query_knowledge` as a tool, allowing the agent to decide exactly when to pull from the knowledge base vs. when to use its built-in memory. It prevents "tool-drift" Feb 1, 2026 4:45 PM
