spacenews.com
FireSat adds orbit-visualization software to help firefighters plan around satellite passeshttps://spacenews.com/firesat-adds-orbit-visualization-software-to-help-firefighters-plan-around-satellite-passes/ExoAnalytic tool aims to show when fire-monitoring satellites can actually see the ground The post FireSat adds orbit-visualization software to help firefighters plan around satellite passes appeared first on SpaceNews.Feb 4, 2026 3:50 PM
news.ycombinator.com
Ask HN: Where does modern geometry survive contact with SGD?https://news.ycombinator.com/item?id=46882060Over the past year I worked through Frankel’s “The Geometry of Physics” cover to cover, not to relearn physics, but to rebuild a modern geometric toolbox as it is actually used there: manifolds, differential forms, connections and curvature, Lie groups and algebras, fiber bundles, gauge structure, and variational principles.The motivation was practical rather than theoretical:Which of these geometric structures, if any, actually survive discretization, noise, and SGD-style training in modern machine learning?In physics, global and coordinate-free formulations were not aesthetic choices; they were forced when local reasoning stopped working. A recurring structural pattern was:structure -> symmetry -> invariance -> dynamics -> observablesIn modern ML we increasingly see analogous issues:* parameter symmetries and large quotient spaces * non-Euclidean data (graphs, meshes, manifolds) * highly structured hypothesis classes * training dynamics that are not well-described by flat Euclidean oFeb 4, 2026 6:07 AM
news.ycombinator.com
Show HN: WarpParse – Rust ETL engine 1.5–8x faster than Vectorhttps://news.ycombinator.com/item?id=46880903Hey HN, We’ve been working on WarpParse, an open-source (Apache 2.0) ETL engine built in Rust, and we’re excited to share it with you today. We built it because we found that existing tools often struggled with resource efficiency or configuration complexity when handling massive log volumes. WarpParse aims to solve this with: Performance: 1.5x to 8x higher throughput than Vector in our benchmarks. Efficiency: Uses ~1/3 the CPU and ~37% of the memory of Vector under similar loads. DSLs: We created WPL (Warp Parse Language) for strong-typed parsing and OML (Object Modeling Language) for declarative data enrichment with native SQL integration. We’ve also built a visual editor (WpEditor) to make rule-writing less of a headache. We’d love to hear your thoughts on the architecture, the DSL approach, or any feedback you have after checking out the repo. GitHub: https://github.com/wp-labs Editor: https://editor.warpparse.ai As a fledgling open-source project, we deeply recognize the power of Feb 4, 2026 2:59 AM
ansicolor.com
Show HN: AnsiColor, resilient ANSI color codes for your TUIhttps://ansicolor.comHi HN. AnsiColor constructs resilient ANSI color codes for your TUI, cli app or prompt. Colors that will work regardless of the user's terminal theme.I built this after experiencing the hilarious illegibility of Codex CLI when running with Solarized Dark. If a zillion dollar company can't get it right, we need better tools.It comes with these themes: Andromeda Ayu Dark/Light Bearded Dark/Light Catppuccin Frappe Catppuccin Latte Catppuccin Macchiato Catppuccin Mocha Dracula GitHub Dark Gruvbox Monokai Dark/Light Nord One Dark/Light Palenight Panda Solarized Dark/Light Synthwave 84 Tailwind Tokyo Night Dark/LightFeb 3, 2026 11:33 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
news.ycombinator.com
Show HN: Folion – Local-first Windows file search with a semantic RAG layerhttps://news.ycombinator.com/item?id=46872030Hi HN,I’m a solo dev, and after a first push amongst some close friends, I’m finally sharing Folion (https://www.folionapp.com).I built this because I struggle with what I call digital hoarding. My folders are full of files like final_v2_edit.docx and draft_2024_backup.pdf. Tools like Everything are great if I remember the filename, but I usually only remember the concept of what was inside.The Tech & Privacy: Folion indexes your folders locally using a vector store on your machine. I’ve added a RAG-based search engine that operates locally and an LLM layer via AWS Bedrock so you can chat with your files. Your index and embeddings never leave your device; only the specific snippets retrieved for a query are sent to the LLM for response generation.Quick 30-second trailer: https://www.youtube.com/watch?v=94puRu4GMKg (Full 14-min demo on the website).Being Realistic About Limitations: Since this is a solo project, I want to be upfront about what it is and isn't:It’s a Precision Tool: For Feb 3, 2026 3:17 PM
vibelo.ai
Show HN: Using sound symbolism and multi-agent AI to generate brand nameshttps://vibelo.aiI built an AI naming tool that applies psycholinguistic research to brand name generation. The interesting part isn't that it uses AI — it's how the agents are structured and what they're optimized for.The core problem: if you ask any LLM to name a business, you get the same [Adjective][Noun] compounds. NovaTech. BrightPath. SwiftFlow. They're linguistically dead — no phonetic texture, no semantic depth, high cognitive fluency but zero distinctiveness.The pipeline has six stages:1. A discovery agent analyzes the business and produces a strategic brief. Critically, it also generates a "tangential category" (something completely unrelated, like "a luxury candle brand" for a SaaS tool) and a "disguised context" (an adjacent industry).2. Three creative agents run in parallel, each with a different framing of the same brief. One works honestly from the brief. One is told it's naming the disguised context. One is told it's naming the tangential category. The disguised and tangential agents cFeb 3, 2026 1:59 PM
spacedaily.com
OpenClaw's AI agent does everything, even social mediahttps://www.spacedaily.com/reports/OpenClaws_AI_agent_does_everything_even_social_media_999.htmlWashington, United States (AFP) Feb 2, 2026 Meet OpenClaw: the AI assistant that promised to be your dream intern, terrified cybersecurity experts, and now thrives on chatbot-only social media - all in just a few weeks. The perfect assistant? At the heart of the tech world's latest come-out-of-nowhere fascination is an AI tool built by Austrian researcher Peter Steinberger in November to help organize his digital life. AfterFeb 3, 2026 6:28 AM
news.ycombinator.com
Ask HN: What's your competitive intelligence workflow as a small team?https://news.ycombinator.com/item?id=46865447I've been researching how founders track competitors and the tooling landscape is interesting. Enterprise teams use Klue/Crayon ($20K+/yr), mid-market uses Competitors.app ($15-20/competitor/mo), and everyone else seems to use... Google Alerts and hoping for the best?Curious what actually works for small teams:- Do you actively monitor competitors, or just check in occasionally? - What signals matter most? (pricing changes, feature launches, hiring, funding?) - Is the raw data useful, or do you need someone to interpret "competitor X changed their pricing page" into "here's what this means for you"?I keep hearing founders say they got blindsided on sales calls by competitors they didn't know existed. Wondering if this is a real pain point or just something people complain about but don't actually prioritize.Feb 3, 2026 2:07 AM
news.ycombinator.com
Ask HN: A proposal for interviewing "AI-Augmented" Engineershttps://news.ycombinator.com/item?id=46865130Hi HN,I’m currently rethinking our hiring process. Like many of you, I feel that traditional algorithmic tests (LeetCode style) are becoming less relevant now that LLMs can solve them instantly. Furthermore, prohibiting AI during interviews feels counter-productive; I want to hire engineers who know how to use these tools effectively to multiply their output.I am designing a new evaluation framework based on real-world open-source work, and I would love the community’s feedback on whether this sounds fair, effective, or if I’m missing something critical.The Core Philosophy: We shouldn't test if a candidate can write syntax better than an AI. We should test if they can guide, debug, and improve upon an AI's output to handle the "last mile" of complex engineering.The Proposed Process:1. Task Selection (Real World Context) Instead of synthetic puzzles, we select open issues or discussions from public GitHub repositories that share a tech stack with our product. Scope: 2–4 hours. Types: ImFeb 3, 2026 1:35 AM
toolvault.co
Show HN: Mortgage Payment Calculator (fast, no signup)https://toolvault.co/tools/mortgage-payment-calculatorI built a mortgage payment calculator for people who just want clean, fast numbers without the lead-gen friction.https://toolvault.co/tools/mortgage-payment-calculatorIt started because every time I tried to run mortgage scenarios, I hit one of these problems:Forms that demand email/phone before showing resultsSlow, ad-heavy pages that feel like landing funnels, not toolsCalculators that only show principal + interest, ignoring real monthly costsWhat this tool does:Calculates full monthly housing cost: principal, interest, property tax, insurance, PMI, and HOA feesShows an amortization-style breakdown so you can see how payments shift from interest to principal over timeLets you quickly tweak: home price, down payment, interest rate, loan term, and extra monthly costsWorks well on mobile and desktop, no account or email requiredA few design decisions I made:No popups, no dark patterns, no “talk to a lender” wallReasonable ad density only (I do monetize it, but tried hard not to make itFeb 2, 2026 7:06 PM
drift.1mb.dev
Show HN: Drift FM – Ambient Mood Radio (Go, SQLite, Vanilla JavaScript)https://drift.1mb.devBuilt an ambient mood radio. Pick one of 6 moods (focus, calm, late night, energize, groove, storm) and it plays continuously.Tech: Go backend serving static files + API from single binary, SQLite for metadata, vanilla JS frontend with no build tools. PWA with offline support.Content pipeline is automated: audio processing, normalization, Cloudflare R2 sync.Running on a $4 VPS, 8MB memory usage. No framework, no React, no webpack.drift.1mb.devFeb 2, 2026 6:35 PM
mentionable.io
Show HN: Mentionable – Track if ChatGPT recommend your brandhttps://mentionable.ioHey HN,I built Mentionable because I kept wondering: when someone asks ChatGPT "what's the best tool for X?", does it mention my product? I had no idea, and manually testing prompts across 5 different LLMs was tedious.The problem: AI assistants are becoming a major discovery channel. People ask ChatGPT, Claude, or Perplexity for recommendations instead of Googling. If you're not showing up in those responses, you're invisible to a growing segment of potential customers.What Mentionable does:1. You enter your URL 2. We analyze your site and auto-generate prompts (things like "best CRM for freelancers" or "affordable invoicing software") 3. We query ChatGPT, Claude, Perplexity, Gemini, and Grok regularly to check if they recommend you 4. You get a simple dashboard showing where you're mentioned, where you're not, and how it changes over timeNo complex dashboards with 50 metrics. Just: "Are you being recommended? Yes/no. Here's what changed."Why I built this: Existing tools in this space Feb 2, 2026 8:35 AM
news.ycombinator.com
Auto-compaction felt fine. The invoice didn'thttps://news.ycombinator.com/item?id=46851021I let Claude Code context accumulate and burned $2,000+ in tokens — without noticing any quality dropI made a costly mistake with Claude Code: I let context accumulate across long sessions and relied on auto-compaction. What surprised me is that the output quality stayed good. I was happy with the results. There was no obvious “something is wrong” signal. The only thing that went wrong was the bill.What happened - I kept iterating in the same long-lived context. - Auto-compaction kicked in when needed. - Sonnet was used by default most of the time. - From a UX perspective, everything felt fine.Why this is dangerous - There’s no clear quality degradation to warn you. - Token usage grows invisibly in the background. - Auto-compaction itself consumes a lot of tokens. - You only realize something is wrong when you look at the invoice.Root causes - Long-lived context feels convenient, so you don’t reset it. - Tooling doesn’t surface cost as a first-class signal. - The mental model (“LLMs caFeb 2, 2026 12:42 AM
solidtheapp.info
Show HN: Solid. Gamifying focused work without a gamer aesthetichttps://solidtheapp.info/Hi HN, I’m building Solid, a work-focused productivity app that uses gamification psychology without game-like visuals, points, or avatars.The idea came from using tools like Habitica and focus apps, but feeling disconnected from the “gamer” aesthetic. Solid is designed for professionals who want motivation, clarity, and consistency, without distractions.Right now this is an early landing page to validate interest. I’d love feedback on the concept, positioning, or whether this is something you’d actually use.Thanks for taking a look.Feb 2, 2026 12:41 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
github.com
Show HN: A P2P file transfer CLI that approaches scp/rsync speeds without setuphttps://github.com/samsungplay/ThrufluxHi HN,Over the past months, I built thruflux to make moving large sets of files between arbitrary machines simpler and faster, without requiring SSH, servers, or port forwarding.It’s a cross-platform CLI written in Go that uses direct peer-to-peer transfers over QUIC, with automatic NAT traversal and relay fallback when needed. A single sender can serve multiple receivers concurrently, and directory transfers are handled natively (no zipping).I recently benchmarked it against scp, rsync, croc, and magic-wormhole to understand the tradeoffs more clearly. While it doesn’t always beat built-in infrastructure tools like scp/rsync in ideal conditions, it gets surprisingly close while solving a harder problem (zero-setup P2P), and transfer speeds shows much lower variance than single-stream TCP tools. Moreover, thruflux consistently outperformed comparable P2P CLI tools, particularly for multi-file transfers.The project is open source and still evolving — happy to hear feedback, especially fJan 31, 2026 8:03 PM
github.com
Show HN: Destructive_command_guard (Dcg)https://github.com/Dicklesworthstone/destructive_command_guardThis is a free, open-source, highly-optimized rust program that runs using pre-tool hooks in Claude Code (CC) and checks the tool call that CC was about to make to see if it’s potentially destructive; that is, could delete data, lose work, drop tables, etc.Get it from the GitHub link and install with the convenient one-liner.A tool like dcg has several competing goals that make it a careful balancing act and tough engineering problem:1. Since it runs for every single tool call, it must be FAST. Hence why it is written in Rust and an extreme amount of focus has been placed on making it as fast as possible.2. It must avoid annoying false positives that waste your time, add friction, and re-introduce you as the bottleneck unnecessarily. I run dozens of agents at once and don’t want them wasting time waiting for me unless it’s needed. Usually, the messages from dcg are enough to get the agent to be more thoughtful about what it’s doing.3. It’s not enough to just use a simple rulebook whereJan 31, 2026 11:35 AM
github.com
Show HN: EditorWatch – Detect AI cheating by analyzing how students write codehttps://github.com/Vic-Nas/EditorWatchHi HN,I built EditorWatch to help CS instructors detect AI-generated code in programming assignments.Current plagiarism detectors only look at the final code. Students copying from ChatGPT slip through easily. EditorWatch is different - it monitors HOW code is written, not just what's written.A VS Code extension tracks coding patterns: - Sudden code appearance (paste bursts) - Lack of natural trial-and-error - Robotic typing patterns - Perfect-first-time codeIt generates an authenticity score (0-10) with visualizations for each submission.Privacy-conscious design: - No video/screenshots, only metadata (timestamps, character counts) - Only tracks specified file types (.py, .js, etc.) - Students must explicitly opt-in - Data deleted after grading - 100% open sourceFree for education, paid for commercial use. Deploys easily on Railway or your own server.I know it's not foolproof - determined students can bypass it. But it raises the bar significantly and works as one tool alongside code rJan 31, 2026 8:14 AM
