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
bing.com
Beyond 75: The Five Most Iconic Topps Cards Not to Make the Listhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a88d17e66214f3ea26ce25f7f707a74&url=https%3A%2F%2Fwww.si.com%2Fcollectibles%2Fbeyond-75-the-five-most-iconic-topps-cards-not-to-make-the-list&c=14291171381266197594&mkt=en-usAs part of the run-up to its 2026 Series 1 release, Topps released its list of the 75 most iconic Topps cards of all time. The list, selected by experts ranging from executives to historians to ...Feb 18, 2026 6:43 AM
news.google.com
11 Easy Dinner Recipes That Start With a Box of Jiffy Corn Muffin Mixhttps://news.google.com/rss/articles/CBMic0FVX3lxTE12MjgxRmdPeG8wWUwyYXhqMWUyNVdyVmZQR09TdW04LUx6UXVoa1ZPZEd1WU5FNDdrQ2pfSmh1Rzg1azBwczh5bnJxdm9vUGFBbF9MbGlsbHpGT1JuaGx0UFlJSkJlVU1KbENhZGtRRHU2Y1k?oc=511 Easy Dinner Recipes That Start With a Box of Jiffy Corn Muffin Mix AllrecipesFeb 17, 2026 8:00 AM
coolwulfAI.com
Show HN: CoolWulf AI – A personal AI assistant built in Go, optimized for macOShttp://coolwulfAI.comHey HN,I've been building CoolWulf AI (https://coolwulfai.com), a self-hosted personal AI assistant. After seeing OpenClaw blow up, I wanted to share what I've been working on — a different approach to the same problem.*Why I built this:*I tried OpenClaw and found the Node.js/TypeScript stack heavy for what's essentially a local agent. pnpm, Node 22+, React — lots of moving parts. I wanted something that's a single binary, zero runtime dependencies, and feels native on macOS. So I built it in Go.*How it's different from OpenClaw:*- *Single binary, no runtime needed.* Download, set your API key, run. No Node.js, no pnpm, no build step. One ~100 MB binary. - *Built in Go.* Fast startup, low memory footprint, compiles to a native executable. No garbage collector pauses from a JS runtime sitting in the background. - *macOS-native integrations.* Deep AppleScript-based control of Apple Notes, Reminders, Calendar, Terminal.app, and WeChat desktop. These aren't browser hacks — they use the natFeb 17, 2026 5:32 AM
mindweave.space
Show HN: Mindweave – AI-powered personal knowledge hub with semantic searchhttps://www.mindweave.space/Hi HN,I built Mindweave to solve a problem I kept running into — I'd save bookmarks, notes, and links across different apps, then never find them again when I actually needed them.Mindweave lets you capture notes, links, and files in one place. The interesting part is what happens after: - Semantic search — find content by meaning, not just keywords. "That article about improving deep work" finds it even if those words don't appear in the content. Powered by pgvector cosine similarity on Gemini embeddings. - AI auto-tagging — Gemini generates tags on save, so you don't have to organize anything manually. - Knowledge Q&A — ask questions about your saved content using RAG. Retrieves relevant pieces, feeds them as context to Gemini, returns a grounded answer. Stack: Next.js 15 (App Router, Server Actions), PostgreSQL 16 + pgvector, Google Gemini (text-embedding-004, 768d), Drizzle ORM, Auth.js v5, Tailwind/shadcn. Deployed on Cloud Run. A few things I found interesting while building thisFeb 16, 2026 5:20 AM
news.google.com
This minimalist Scottish tech start-up is ready to furnish your homehttps://news.google.com/rss/articles/CBMieEFVX3lxTE5hei1vbFlsUzJBbDRuQUZ6NmkxdjVUMVVIV2JkaWRadG9taWpuMVdYNUpFaU5fR3RYbWk2eDU0S3MtZWQ2NzFSUXViam1raEpZalVFSWhJR01PUGV4UUVoeDJ2QWVQYlN6RHpuVjFpSmdVb0JUWElQbw?oc=5This minimalist Scottish tech start-up is ready to furnish your home wallpaper.comFeb 15, 2026 8:00 AM
spacedaily.com
Strange 'inside-out' planetary system baffles astronomershttps://www.spacedaily.com/reports/Strange_inside-out_planetary_system_baffles_astronomers_999.htmlParis, France (AFP) Feb 12, 2026 Surprised astronomers said Thursday they have discovered a star with planets in a bizarre order that defies scientific expectations - and suggests these faraway worlds formed in a manner never seen before. In our Solar System, the four planets closest to the Sun are small and rocky, while the four farther out are gas giants. Scientists had thought this planetary order - rocky first, thFeb 13, 2026 12:49 PM
spacenews.com
Space companies bet on Golden Dome as questions persist over scope and fundinghttps://spacenews.com/space-companies-bet-on-golden-dome-as-questions-persist-over-scope-and-funding/At SmallSat Symposium, executives cite enduring missile threat as rationale for continued investment The post Space companies bet on Golden Dome as questions persist over scope and funding appeared first on SpaceNews.Feb 11, 2026 9:35 PM
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
spacedaily.com
Gilat books multimillion order for Sidewinder inflight ESA terminalshttps://www.spacedaily.com/reports/Gilat_books_multimillion_order_for_Sidewinder_inflight_ESA_terminals_999.htmlLondon, UK (SPX) Feb 08, 2026 Gilat Satellite Networks has secured a multimillion order from a major global avionics company for its Sidewinder electronically steered antenna inflight connectivity terminals designed by Gilat Stellar Blu, with deliveries scheduled over the next six months. The new contract underscores growing momentum for the Sidewinder ESA platform as airlines and service providers look to deploy advanFeb 8, 2026 1:59 AM
news.google.com
Here's what went down at the Winter Olympics opening ceremonyhttps://news.google.com/rss/articles/CBMitwFBVV95cUxNSHpER0RKdHo5enpENENPREJUZ1g3SEM4MWg5bVVyZzVoT3VQaXBrOXlpeHJGS0Z0UW5uRjRCbVlqNFlPaVRnTTl2UTJCMWltSnJhMDNia21KN0pvNm9wUmFvUU1mMnJRby0tbGxWVjBtSk51eFBaZmFjcWFCU0dzTFU4Q0d0ZWVxemtaa0cwU2ZPb00xZkZSalF5bWJiYWlLV1Bzc0U4UWpwRGlTOHVnMzB5eWR6N1U?oc=5Here's what went down at the Winter Olympics opening ceremony wallpaper.comFeb 7, 2026 8:00 AM
github.com
Show HN: I built a RAG engine to search Singaporean lawshttps://github.com/adityaprasad-sudo/Explore-SingaporeI built a "Triple Failover" RAG for Singapore Laws, then rewrote the logic based on your feedback.Hi everyone!I’m a student developer. Recently, I created Explore Singapore, a RAG-based search engine that scrapes about 20,000 pages of Singaporean government acts and laws.I recently posted the MVP and received some tough but essential feedback about hallucinations and query depth. I took that feedback, focused on improvements, and just released Version 2.Here is how I upgraded the system from a basic RAG to a production-grade one.The Design & UI I aimed to avoid a dull government website.Design: Heavily inspired by Apple’s minimalist style.Tech: Custom frontend interacting with a Python backend.The V2 Engineering OverhaulThe community challenged me on three main points. Here’s how I addressed them:1. The "Personality" Fix Issue: I use a "Triple Failover" system with three models as backup. When the main model failed, the backups sounded entirely different.The Solution: I added Dynamic SFeb 7, 2026 3:58 AM
nasa.gov
Evaluation of Adhesive and Solvent Alternatives for PolymericBonding Applicationshttps://www.nasa.gov/centers-and-facilities/nesc/evaluation-of-adhesive-and-solvent-alternatives-for-polymericbonding-applications/The NASA Engineering and Safety Center (NESC) conducted a technical assessment to evaluate alternatives to dichloromethane, traditionally used for bonding transparent polymeric materials. This effort was initiated in response to potential regulatory restrictions under the EPA Toxic Substances Control Act (TSCA), which could impact critical bonding processes used in spaceflight hardware and experimental systems. Download […]Feb 4, 2026 6:09 PM
spacedaily.com
ESA adjusts Cluster orbits for rare twin reentry campaignhttps://www.spacedaily.com/reports/ESA_adjusts_Cluster_orbits_for_rare_twin_reentry_campaign_999.htmlParis, France (SPX) Feb 04, 2026 When satellites fall back to Earth, most of their structure burns up in the atmosphere, but engineers still lack detailed data on how real spacecraft actually break apart during reentry and which components survive the plunge. To close this gap, the European Space Agency has retargeted the final orbits of its remaining two Cluster satellites so that both can be observed from an aircraft during tFeb 4, 2026 1:04 PM
news.ycombinator.com
Show HN: OpenSymbolicAI – Agents with typed variables, not just context stuffinghttps://news.ycombinator.com/item?id=46876687Hi HN,We've spent the last year building AI agents and kept hitting the same wall: prompt engineering doesn't feel like software engineering. It feels like guessing.We built OpenSymbolicAI to turn agent development into actual programming. It is an open-source framework (MIT) that lets you build agents using typed primitives, explicit decompositions, and unit tests.THE MAIN PROBLEM: CONTEXT WINDOW ABUSEMost agent frameworks (like ReAct) force you to dump tool outputs back into the LLM's context window to decide the next step.Agent searches DB.Agent gets back 50kb of JSON.You paste that 50kb back into the prompt just to ask "What do I do next?"This is slow, expensive, and confuses the model.THE SOLUTION: DATA AS VARIABLESIn OpenSymbolicAI, the LLM generates a plan (code) that manipulates variables. The actual heavy data (search results, PDF contents, API payloads) is stored in the Python/runtime variables and is never passed through the LLM context until a specific primitive actually neFeb 3, 2026 8:19 PM
spacedaily.com
NASA books fifth Axiom private astronaut flight to space stationhttps://www.spacedaily.com/reports/NASA_books_fifth_Axiom_private_astronaut_flight_to_space_station_999.htmlLos Angeles CA (SPX) Feb 02, 2026 NASA has ordered a fifth private astronaut mission to the International Space Station from Axiom Space, targeting a launch no earlier than January 2027 from the agency's Kennedy Space Center in Florida. The flight, designated Axiom Mission 5, continues the series of commercially sponsored crewed missions to the orbital laboratory under NASA's commercial space strategy. NASA Administrator JFeb 3, 2026 4:52 AM
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
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
bing.com
Apple reaches 2.5 billion active devices after record-breaking quarterhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e552c1b045248f3e8f2c2f50ec7c&url=https%3a%2f%2fappleinsider.com%2farticles%2f26%2f01%2f29%2fapple-reaches-25-billion-active-devices-after-record-breaking-quarter&c=15747634837524631994&mkt=en-usThe active install base of Apple users has increased by 150 million users since 2025 and has reached over 2.5 billion active users as of January 2026. Apple's first-quarter earnings are ...Jan 29, 2026 2:32 PM
bing.com
Apple reaches 2.5 billion active devices after record-breaking quarterhttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85c8561e7d4f26bb7e1511115750cc&url=https%3a%2f%2fappleinsider.com%2farticles%2f26%2f01%2f29%2fapple-reaches-25-billion-active-devices-after-record-breaking-quarter&c=15747634837524631994&mkt=en-usThe active install base of Apple users has increased by 150 million users since 2025 and has reached over 2.5 billion active users as of January 2026. Apple's first-quarter earnings are ...Jan 29, 2026 2:32 PM
