4,220 results for Tool

news.ycombinator.com
Ask HN: Do you also "hoard" notes/links but struggle to turn them into actions?https://news.ycombinator.com/item?id=46826277Hi HN — I’m exploring an idea and would love your feedback.I’m a builder and user of Obsidian, validating a concept called Concerns. Today it’s only a landing page + short survey (no product yet) to test whether this pain is real.The core idea (2–3 bullets):- Many of us capture tons of useful info (notes/links/docs), but it rarely becomes shipped work.- Instead of better “organization” (tags/folders), I’m exploring an “action engine” that: 1.detects what you’re actively targetting/working on (“active projects”) 2.surfaces relevant saved material at the right moment 3.proposes a concrete next action (ideally pushed into your existing task tool) My own “second brain” became a graveyard of good intentions: the organizing tax was higher than the value I got back. I’m trying to validate whether the real bottleneck is execution, not capture.Before writing code, I’m trying to pin down two things:- Project context signals (repo/PRs? issues? tasks? calendar? a “project doc”?)- How to close the
Jan 30, 2026 4:22 PM
deterministic-stream-demo1.pages.dev
Show HN: A small reference demo for separating UI stalls from network delayshttps://deterministic-stream-demo1.pages.dev/I built a small reference demo that streams data in the browser, intentionally stalls the UI, and exports a structured trace you can compare across runs.This isn’t a benchmark or a product. I mostly built it to sanity-check my own understanding of a common problem: is this slowdown coming from the network or from the UI thread?What the demo does:Uses real SSE streaming (no simulated network behavior)Relies on real browser throttling (DevTools → Network → 3G)Intentionally blocks the main thread to create real UI stallsExports a plain JSON trace with strict event orderingHow to try it:Open the siteSet DevTools → Network → 3GClick Run All (Standard Test)Download the traceRun it again and compareWhat surprised me is that with the same test and seed, the structure of the trace stays the same, even though timing shifts. That made it much easier (for me) to reason about what actually happened without squinting at timelines.The page is instrumented with a small deterministic event kernel so th
Jan 30, 2026 5:14 AM
metal.graphics
Show HN: MetalGraph – Visual node editor for SwiftUI Metal shadershttps://www.metal.graphics/appHi HN,I just released MetalGraph, a visual node-based editor for building Metal shaders for SwiftUI.The motivation: the feedback loop when iterating on SwiftUI + Metal can be pretty rough. I wanted something closer to a node editor workflow where you can tweak values, rewire the graph, and immediately see the result. It became a great tool for learning metal for myself.What it does: - Node graph editor (50+ nodes) with a real-time preview - 30+ built-in examples (color effects, layer effects like glass/chromatic aberration, distortions, touch-driven effects) - Exports production-ready code: Metal Shading Language + SwiftUI-ready .colorEffect / .layerEffect variants - Supports reusable custom nodes + simple for-loops for iterative computations - Optional AI assistant (Claude / OpenAI) for shader questions and help building graphsIf you are thinking about learning Metal shaders for SwiftUI or have any experience, I’d love feedback! The app is free to download (you can't add/remove nodes
Jan 30, 2026 3:21 AM
relnotes.app
Show HN: Relnotes.app – Turn GitHub PRs into your Friday's report automaticallyhttps://relnotes.app/Hi HN,I’m the solo builder behind relnotes.app. I built this because I realized I was spending far too much time every Friday manually formatting technical changelogs into "human-readable" emails for stakeholders and clients.As a dev, it felt like the least productive part of my week.The Workflow:You connect your GitHub repo.When a Pull Request is closed, the app generates a release update.It formats these updates into a branded, professional email template.It sends/schedules them for your stakeholders automatically.I launched this on Product Hunt last week and it was a total ghost town (1 upvote!), so I’m trying to figure out if I’m solving a problem people don't actually care about, or if I’m just bad at explaining the value.I’d love your feedback on:The "Stakeholder" Angle: Does your team actually send manual status emails, or do you just give them access to Jira/GitHub and hope for the best?Technical friction: Would you trust an automated tool to draft these, or is manual oversight
Jan 29, 2026 6:15 AM
spacedaily.com
AI digital twins aim to protect astronaut mobility on deep space missionshttps://www.spacedaily.com/reports/AI_digital_twins_aim_to_protect_astronaut_mobility_on_deep_space_missions_999.htmlLos Angeles CA (SPX) Jan 29, 2026 West Virginia University researchers are developing artificial intelligence tools to help astronauts maintain movement control and overall physical health during long missions in microgravity environments such as space stations, the Moon and future voyages to Mars. Their work centers on building personalized computer models that capture how each astronaut moves and how their muscles are activate
Jan 29, 2026 4:43 AM
news.ycombinator.com
Ask HN: Need for AI usage disclosure system?https://news.ycombinator.com/item?id=46798133With the influx of AI-generated code in open source repos, would there be any need/interest in creating a standard to disclose AI usage?Something like a markdown document in the project root (like LICENSE or CONTRIBUTING) that explains:- what level of AI was used (None, Assisted, Fully Generated) - which components used UI (core logic, test, etc.) - what A.I tools were used - who reviewed it (human vs. AI reviewed & tested) - contribution guidelines with AI (may be stepping on the toes of CONTRIBUTION)I'm sure some repos have this already and each can implement it in their own way. But could a standard that defines a structure to disclose this be helpful?From the perspective of someone quite inexperienced in open source contribution, not sure if this would be of any help (and to who).Interested to hear your thoughts on this.
Jan 28, 2026 5:06 PM
autograph.video
Show HN: Autograph.video for Anyone Interested in Motiongraphicshttps://www.autograph.video/Hi everyone, after months and months of designing and animating. My brother and I built this Animation tool that helps anyone remix their favourite motion designs bits in minutes. Let us know what you think www.autograph.videoGetting started:https://youtu.be/05aNmIM37xc?si=RhJrqEdyvl-UCYu5
Jan 28, 2026 12:36 PM
glitchward.com
Show HN: GlitchWard – Active defense and CIS hardening for neglected SMB servershttps://glitchward.comHey HN,I’m Lubos, a solo founder based in Slovakia. I’m building GlitchWard because I got tired of seeing SMBs and agencies running "naked" servers.Most small teams ignore server security not because they don't care, but because enterprise tools (Wiz, Datadog Security) are too expensive, and manual hardening (fail2ban, OS updates) eventually gets forgotten.I wanted a tool that creates a "self-defending" server, capable of stopping attacks even when I'm asleep.CURRENT STATUS: We officially launched yesterday. During our beta, we onboarded 20+ clients and the beacon is currently protecting 100+ servers. You can also check out our demo video and launch details on Product Hunt: https://www.producthunt.com/products/glitchwardWe are currently supporting only Linux based operating systems (Debian, Ubuntu, RHEL...)WHAT IT DOES: You install a lightweight beacon agent (Rust binary), and it provides:Active Defense: It doesn't just watch; it acts. We recently caught and killed a reverse shell atta
Jan 28, 2026 11:04 AM
news.ycombinator.com
Ask HN: Do you verify AI-generated content before publishing?https://news.ycombinator.com/item?id=46791462I'm researching content repurposing tools and trying to understand a workflow gap:When you use AI to turn podcasts/interviews/webinars into social posts, do you verify accuracy before publishing?Context: Tools like Castmagic and Descript are 85-95% accurate. That 5-15% error rate means AI sometimes: - Misquotes speakers - Paraphrases in ways that change meaning - Attributes quotes to wrong person (multi-speaker issue)I've found two camps:Camp A: "I carefully verify everything" - Re-read transcripts or scrub audio - Takes 20-30 minutes per post - Zero tolerance for publishing errorsCamp B: "I trust AI and publish" - "Good enough" for social media - Errors are rare enough to accept - Speed > perfectionMy questions: 1. Which camp are you in? 2. If Camp A: what's your verification workflow? 3. Has anyone been burned by publishing inaccurate AI content? 4. Would "click any quote to hear exact audio timestamp" be valuable?Building a tool that links every generated claim to source evidence. T
Jan 28, 2026 5:33 AM
news.ycombinator.com
Show HN: We are building Git for datahttps://news.ycombinator.com/item?id=46785065Today you can easily adopt AI coding tools because you have git for branching and rolling back if AI writes bad code. We haven't seen this same capability for data and decided to build it ourselves.Nile is a new kind of data lake, purpose built for using with AI. It can act as your data engineer or data analyst creating new tables and rolling back bad changes in seconds. We support real versions for data, schema, and ETL.We'd love your feedback on any part of what we are building - https://getnile.ai/What do you think?
Jan 27, 2026 7:25 PM
gitbybit.com
Show HN: GitByBit — Git course integrated into VSCode and Cursorhttps://gitbybit.comHi folks! My name is Alexander Shvets. People know me best as an admirer of raccoons and the creator of Refactoring.GuruToday I'd like to show you the project I've been working on for the past two years: https://gitbybit.comIt's a Git course that runs inside your code editor (VS Code, Cursor, and friends), so you learn Git by using it in real dev environment. It's well-designed and illustrated.## Who is it for?The course will be most helpful for three groups of people:- Developers who “use Git” but mostly as a black box. You know a few commands, but you want to actually understand what you’re doing.- Builders returning to code (PMs, designers, ex-devs) who now use AI tools for prototypes and internal tools, and need their Git muscles back.- Hobby coders and beginners who want a practical, confidence-building path from zero to “I can work with Git.”## What makes it different?I designed GitByBit as a modern way to learn Git (if we can still say so about a project that doesn't use AI). It
Jan 27, 2026 1:10 PM
github.com
Show HN: ReelStudio – open-source Instagram Reel transcription with Whisperhttps://github.com/stym06/reelstudioHey HN, I built an open source tool to transcribe Instagram Reels using OpenAI's Whisper model. GitHub: https://github.com/stym06/reelstudio How it works: - Paste a Reel URL → Worker downloads via yt-dlp → Whisper transcribes → Get shareable transcript page Tech stack: - Next.js 14 frontend - Go worker (polls PostgreSQL for jobs) - faster-whisper for transcription - No login required The architecture is simple: the frontend creates a task in PostgreSQL, a Go worker polls for pending tasks, downloads the video, runs Whisper, and saves the transcript. The frontend polls until complete and redirects to the transcript page. I built this because I wanted to repurpose Reel content into blog posts and needed accurate transcripts with timestamps. Existing tools either required accounts, had watermarks, or were expensive. Self-hosting is straightforward - just need PostgreSQL, the Next.js server, and the Go worker with Python/Whisper installed. Would love feedback on the architecture or any fea
Jan 26, 2026 8:35 PM
news.ycombinator.com
Show HN: Klaus – a Claude Code native delegating agentic harnesshttps://news.ycombinator.com/item?id=46760506Good afternoon everyone, spent like 2 weeks straight doom-scrolling Anthropic docs, Arxiv rabbit holes, and Claude blog posts till my eyes bled. Instead of shipping yet another wrapper that "reinvents" the wheel, I just vibe engineered this thing to max out Claude Code's native features. Klaus Baudelaire (https://github.com/blas0/klaus-baudelaire) basically: Routes agents (in parallel/sequence) with through keyword based scoring + prompt length (no fancy external router needed).Instead of trying to make agentic delegation deterministic by setting keyword variables as a "YOU MUST INVOKE X-AGENT IF THE USER SAYS DELEGATE", keywords = a score, a certain score = a specific system prompt that is injected into the session post UserPromptSubmit. You can read how this works more on the repo: (https://github.com/blas0/klaus-baudelaire)Delegates built-in agents + some redefined ones (broad general roles + hyper-specific tool callers) Some agents were built from/around Claude's exposed system pro
Jan 26, 2026 1:02 AM
studio.mfelix.org
Show HN: Alien Abducto-rama: a FUN browser game I made with my kidshttps://studio.mfelix.org/alien-abductorama/I built this over the holiday break with my two girls (ages 6 and 8). You pilot a UFO and beam up humans, cows, cats, dogs, and sheep for points. They drew all the art while I talked to Claude Code to scaffold the game logic.The magic moment was watching my kids use voice dictation to talk directly to Claude Code. My 8-year-old asked for a "purpler" tractor beam and watched it change in real time. She wasn’t coding, but she _was_ driving: describing what she wanted, testing the result, and iterating fast. It was really cool to watch... later on she asked me what javascript was and we dug into the source.Since then we've added a UFO Shopping Mall between waves (spend UFO bucks on power-ups), bombs, laser turrets, a dodge roll called "warp juke," and a top 100 leaderboard. There's also in-game feedback where you can submit and upvote feature requests. Building all these little features has been a great excuse to put in reps with AI coding tools and try out new stuff like Gastown.You'll n
Jan 24, 2026 3:45 PM
cloudclerk.ai
Show HN: CloudClerk. We struggled with BigQuery finops, so we decided to fighthttps://www.cloudclerk.ai/Hello HN, Lucas here.I’ve been working with BigQuery for ~5 years, mostly in large (petabyte-scale) environments. Over time we ended up spending a lot of money and engineering effort just trying to understand where costs were coming from, why and how to optimize them.At some point we decided to stop, leverage all our past experience and spend a full cycle building tooling focused on cost visibility and optimization. The main goal was to regain ownership of cost data and make it possible to understand our cost structure in under a minute, while aligning the views of engineering and FinOps at the project level. To complement these, and given the recent rise of AI, we also built agents that review usage patterns and selected KPIs to surface issues and suggest concrete optimizations (always through an encoding layer for privacy).This ended up working well for us: we reduced monthly BigQuery spend by ~43% and made cost considerations part of normal engineering workflows instead of a separat
Jan 23, 2026 4:22 PM
noriskillsets.dev
Show HN: A registry for curated, high quality Claude skills and skillsetshttps://noriskillsets.dev/Hi Hacker News!I’m Ritam, working with the small but mighty team at Nori. We’ve been obsessed in recent months with how to take tools like Claude Code from “I’ll experiment around with this” to “This is the most useful and necessary thing I use every day”. When I first sat down with our team to check out what they’d built, I found my skepticism about agentic coding melting away—they’d built useful, high quality, handwritten skills, instructions that functioned as “skillsets” to tie skills together for consistent and replicable results, and tooling to manage loading the right context for the right task into the agent.In recent weeks, the conversation around skills has reached a fever pitch, as have lists and sites full of skills scraped from all over the internet. Much like the actual gold rush, the current state of those collections requires a lot of time and sifting to find small, real chunks of 24k skills hidden amongst the muck (or to use a more relevant word, slop). So at Nori, we
Jan 22, 2026 5:00 PM
news.ycombinator.com
Show HN: I'm tired of my LLM bullshitting. So I fixed ithttps://news.ycombinator.com/item?id=46721773As a handsome local AI enjoyer™ you’ve probably noticed one of the big flaws with LLMs:It lies. Confidently. ALL THE TIME.I’m autistic and extremely allergic to vibes-based tooling, so … I built a thing. Maybe it’s useful to you too.The thing: llama-conductorllama-conductor is a router that sits between your frontend (eg: OWUI) & backend (llama.cpp + llama-swap). Local-first but it should talk to anything OpenAI-compatible if you point it there (note: experimental so YMMV).LC is a glass-box that makes the stack behave like a deterministic system, instead of a drunk telling a story about the fish that got away.TL;DR: “In God we trust. All others must bring data.”Three examples:1. KB mechanics (markdown, JSON, checksums)You keep “knowledge” as dumb folders on disk. Drop docs (.txt, .md, .pdf`) in them. Then:>>attach - attaches a KB folder>>summ new - generates SUMM_.md files with SHA-256 provenance baked in + moves the original to a sub-folderNow, when you ask something like:> “yo, what
Jan 22, 2026 4:50 PM
github.com
Show HN: BrowserOS -- browser agents with GPT-OSS, local llmshttps://github.com/browseros-ai/BrowserOSHi HN – we're the founders of BrowserOS.com (YC S24), and we're building an open-source agentic web browser. We're a fork of Chromium and our goal is to let non-developers create and run useful agents locally on their browser.--- When we launched a month ago, we thought we had the right approach: a "one-shot" agent where you give it a high-level task like "order toothpaste from Amazon," and it would figure out the plan and execute it.But we quickly ran into a problem that we've been struggling with ever since: the user experience was completely hit-or-miss. Sometimes agent worked like magic, but other times the agent would get stuck, generate a wrong plan, or just wander off course. It wasn't reliable enough for anyone to trust it.This forced us to go back to the drawing board and question the UX. We spent the last few weeks experimenting with three different ways a user could build an agent:A) Drag-and-drop workflows: Similar to tools like n8n. This approach creates very reliable agen
Jan 22, 2026 4:30 PM
bing.com
The 10 best national and super regional banks of 2026http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8ab386395d48f7b549dcd36ea780f2&url=https%3A%2F%2Ffinance.yahoo.com%2Fpersonal-finance%2Fbanking%2Farticle%2Fbest-national-banks-210657984.html&c=3034099466170899556&mkt=en-usWhether you're looking for robust digital tools, a wide ATM network, or a one-stop shop for all your financial needs, a national or "super regional" bank may be the right fit for you. We evaluated the ...
Jan 22, 2026 12:34 PM
bing.com
The 10 best national and super regional banks of 2026http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a89035712444dd99db46bcb6366f3e7&url=https%3A%2F%2Ffinance.yahoo.com%2Fpersonal-finance%2Fbanking%2Farticle%2Fbest-national-banks-210657984.html&c=3034099466170899556&mkt=en-usWhether you're looking for robust digital tools, a wide ATM network, or a one-stop shop for all your financial needs, a national or "super regional" bank may be the right fit for you. We evaluated the ...
Jan 22, 2026 12:34 PM