Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
If not, why not?That way, people can choose whether they want to install various software betas based on how much SSD wear they are willing to accept.And since this data would be made public and available in one place, software developers would be more careful about excessive logging in their betas.
Hacker News1mo agoToolAI
Hi HN, we are Marcos and Harrison, cofounders of Palmier (https://palmier.io). We are building Palmier Pro, an open source macOS video editor, with built-in AI generation and a local MCP server that connects to your agent. Here are a few demos:- Making some AI transitions: https://www.youtube.com/watch?v=hbM_-eR1GX4- Multicam editing with Codex: https://www.youtube.com/watch?v=SjS2q2LT1q8- Cutting long form clips into shorts: https://www.youtube.com/watch?v=PR66eN2ouuQWe built Palmier Pro as an internal tool when we were making AI launch videos for other startups. The main problem it solved in the beginning was the back-and-forth between AI generation platform and video editor. The iteration loop was awkward: AI videos → download → import to editor → edit → realize we need to change the AI video → repeat. So we built a minimal video editor where we could let Claude generate AI videos inside the editor.As we gave more and more tools to the agent, we wanted to push to see what else agents can do in the video editing space. So today, your Claude/Codex can:- Manage projects inside Palmier Pro- Import media from a public URL or filesystem to the project, and organize them in folders- Search media (by embedding footages using SigLIP2 running locally)- Edit the timeline (tracks/clips/keyframes operations)- Generate images, videos, sound effects, captions, music- Export videosThere are two ways for LLMs to interact with the editor: by connecting to the local MCP server, or using the in-app chat. Both use the same tools and APIs exposed by the video editor.We have seen people using MCP server to connect to their own workflow to automate massive-scale video editing (e.g. given this same podcast style, replicate it with other footages that I have). We have also seen people using the in-app chat where it lives closer to the editor UI, with lower latency for faster iteration.We don't believe that AI is go
Hacker News1mo agoToolAI
Hi HN, We’re Adeel and Umair, co-founders of Unlayer (https://unlayer.com/). We let you add content creation to your applications without having to build an entire editor, renderer, template, and export stack yourself. Unlayer lets you create emails, web pages, and documents inside your app, in three different ways: in code, visually, or with AI.Here’s a demo: https://www.youtube.com/watch?v=0HsDtNkdMpM.We started with an embeddable email editor because a lot of products eventually need one: CRMs, marketing tools, customer engagement platforms, marketplaces, internal tools, and vertical SaaS apps all run into this at some point. At first, it sounds like a small feature: "just" add a drag and drop editor. In practice, it turns into a big pain. You end up dealing with email rendering, Outlook quirks, responsive layouts, templates, merge tags, image uploads, exports, permissions, localization, versioning, and a long tail of edge cases that have nothing to do with your core productOver time, we saw the same problem beyond email. Apps also need landing pages, invoices, proposals, reports, contracts, and PDFs. Some of this content is best created visually by end users. Some of it is better generated in code by developers. Increasingly, some of it is also generated by AI agents. Many teams eventually need all three workflows. That is the direction we have been working toward with Unlayer.There are three parts we are showing today:(1) Unlayer Elements. This is our open-source React component library for creating emails, pages, and documents in code (repo: https://github.com/unlayer/elements, more at https://unlayer.com/elements). Instead of hand-writing raw HTML templates, developers can compose content using React components, reuse sections like headers, footers, CTAs, invoice rows, and branded blocks, keep templates in Git, and render them into production output.One newer use case we are seeing is
Hacker News1mo agoToolAI
I've been building a level editor for Quake 3 that runs entirely in the browser: Radiant-style layout, brush and patch editing, CSG, terrain sculpting, and entity editing. It opens and saves .map file and you can play the maps you build directly in the browser using a webassembly build of ioquake3.
Hacker News1mo agoToolAI
I played a lot of Valorant and got mad, so I made an aim trainer that analyzes your raw crosshair movement to explore your raw motor and perceptual weaknesses instead of scoring scenarios. It also chooses sens and difficulty as part of the tasks, and makes playlists that are optimal difficulty for you to learn and progress faster!
Hacker News1mo agoToolAI
Hi HN - I'm Venkat, founder of Stayflexi (YC), CMU CS grad and Ex-Oracle Query Engine team (patents in core databases)DeepSQL started as an internal tool to stop our own databases from becoming the bottleneck they were becoming (13,000+ hotels in production). It worked well enough that we're releasing it.DeepSQL is an AI agent that operates a database the way a senior DBA and Data Engineer would1. Fixes slow queries (we cutdown DB spend by 4x) 2. Fixes DB bloat (blocks unnecessary schema changes, in vibecoded setup) 2. BI dashboards(we removed spend on tableau, retool and appsmith) 3. Security (We could redact access to sensitive, PII data to our employees) while engaging everyone in the org to interact with our databaseHow it works 1. Deepsql learns your data and relationships from your code base, rules and query logs 2. Deepsql agent has 20 background jobs that continuously monitor the schema changes, bottlenecks, and come up with solutions before the problem arises. (Schema bloat issues are irreversible) 3. Deepsql Brain has CLI and MCP surfaces that can directly work with Claude / Codex and Cursor. 4. Deepsql digest delivers the daily database health report. 5. Your team can connect to deepsql with their favourate surface areas - Web UI, CLI, MCP or Slack.One line install: curl -fsSL https://install.deepsql.ai/install.sh | bashFor community support: https://discord.gg/duEJq7AeeGOr just email me for expert level setup guidance venkat@deepsql.ai
Hacker News1mo agoToolAI
Word in web is a pure JS docx editor/renderer benched against MS Word directly. This was largely inspired by Eigenpal going closed source, and some personal frustrations I had with working on complex Word templates, pleading papers, etc... and not having a clean way to view/edit them without owning MS Word (which I did just eventually buy but it sucked).This was also an exercise in highlighting the value of good evals for Agents to bench against. Instead of just throwing the OOXML standard at an agent and letting it spin, I put together a large corpus of Microsoft Word docs - converted them to pdf and then rasterized them to images. The eval then compared the image diffs measuring the actual differences in the actual pixels. This let me (and more importantly, the agent) catch a lot of the edge cases and optimize aggressively while preventing 'whack a mole' style regressions that would have made this project a lot harder.Edit: I forgot to mention two things, 1. I published the full eval, including the raw diffs and delta over time so you can see all of the fixtures I actually tested against.2. On the DX side, it ships as a typed React package and runs entirely in the browser. You can use it as a viewer or editor, customize the styling and visible toolbar features, build your own controls against the API, and decide where the edited DOCX bytes are saved, so it’s relatively easy to drop into another project
Hacker News1mo agoToolAI
Hey HN, Henry & Roman here from Cactus.A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-trained to know when it's wrong. Every response comes with a confidence score between 0 and 1. Developers can accept the on-device when it's high, hand off to a bigger cloud model when it's low. By routing only 15-35% of queries to Gemini 3.1 Flash-Lite, Gemma-4-E2B matches Gemini 3.1 Flash-Lite on most benchmarks.- ChartQA: 15-20%- LibriSpeech: 25-30%- MMBench, GigaSpeech, MMAU: 30-35%- MMLU-Pro: 45-55%We were always frustrated by the routing signals hybrid apps rely on: asking the model to rate itself in text (unreliable, and you're parsing prose), or token entropy heuristics (barely better than a coin flip in our tests). So we did mechanistic studies on small models, Gemma 4 particularly, and found the hidden state for different layers carry meaningful self-awareness signal for various situations.SO we extended the model with a 68k params probe layer (LayerNorm, low-rank projection, attention pooling, small MLP head) reads one intermediate layer during decoding and predicts p(wrong); confidence = 1 - p(wrong), returned as structured data, never parsed out of the answer text.Across 12 hold-out benchmarks spanning text, vision and audio, the probe averages 0.814 AUROC vs 0.549 for token entropy. The result that convinced us this is real: the probe was trained on zero audio data, yet scores 0.79-0.88 AUROC on four audio benchmarks where entropy is near-random or worse (0.32-0.52). It's reading a modality-independent correctness signal from the hidden state, not memorizing patterns from its training data.We published all weights on HuggingFace and provide copy-pase codes to run it on Transformers, MLX, Llama.cpp or Cactus. With Ollama, vLLM, SGLang etc in the works. For llama.cpp we ship a patch series you compile in once (upstreaming is planne
Hacker News1mo agoToolAI
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness.To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it.Open it in a browser and then you can edit, present, print and save. Share it via email or via Airdrop and all they need is a browser to edit, present and also do live collab on the slides. Drop it in to Claude or ChatGPT to transform existing pptx files into Bento slides. There is no cloud involved, only an encrypted blind relay to allow for shared editing. The relay doesn't see any of the data.Check it out at https://bento.page/slides/ which takes you straight to the editor.Go to https://bento.page/guestbook/ to try out the live guestbook to experience share editing / collab.There is also a gallery with some sample decks on the website - https://bento.page/All the code is MIT licensed and you can find it here - https://github.com/nyblnet/bento . I used reveal.js with several other libraries (including some homegrown ones), and Claude Code.
Hacker News1mo agoToolAI
Justif is a drop-in JavaScript library that progressively enhances web pages to TeX-level text justification. Installation is a single <script> line, standard text and accessibility affordances are unchanged, and users with JS disabled get native browser rendering.I made justif because I've long been a fan of justified text. I think it looks clean and elegant, and makes reading more enjoyable. But bad justification is the opposite, with gaping spaces that distract me to the point of making the text near unreadable.Browsers have got better recently at handling justified text [0][1], but still use suboptimal greedy algorithms for the most part, and are not near that TeX/InDesign level of quality that I crave. `text-wrap: pretty` exists but is far from a panacea, as you can see for yourself in the demo.Justif also has the benefit of providing more consistent text layout across browsers. Blink (Chrome), Gecko (Firefox) and WebKit (Safari) all justify text differently, so normally what the user sees depends on what browser they use.Take a look at the demo, play around with it, see if you can break anything. I'm open to improvements of the API design as well, so please let me know your thoughts.For more details, see the README: https://github.com/lyallcooper/justif0: https://cloudfour.com/thinks/justified-text-better-than-expe...1: https://owickstrom.github.io/the-proportional-web/
Hacker News2mo agoToolAI
Hi HN, I’m Alex Southmayd, the founder of Bloomy (https://bloomylearning.com) – an AI-powered mastery-learning platform for K-12 students. Bloomy provides students with an AI tutor alongside adaptive curriculum (right now Math, English Language Arts, and Writing).How it works: we diagnose students’ skill gaps, place them on personalized learning paths, and give them standards-aligned lessons and a Socratic AI tutor that scaffolds their learning without just giving away the answer.The goal is to solve the Bloom 2-sigma problem (https://en.wikipedia.org/wiki/Bloom%27s_2_sigma_problem) with AI.Short launch video: https://tinyurl.com/bloomylearningLonger product demo: https://youtu.be/XHvoKt6qMeoFamilies access for Bloomy: https://bloomylearning.com/familiesI started as a teacher. I taught 7th-grade English and writing with Teach For America, and every day I struggled to deliver differentiated instruction to 30 students with 30 different sets of needs. Some students needed remediation, some needed acceleration, and many needed a tutor sitting next to them helping them reason through the next step. Benjamin Bloom’s two-sigma result—that one-on-one tutoring can produce much better outcomes than conventional classroom instruction—always felt intuitively true to me. The hard part was making that kind of attention affordable and available to every child.Then AI changed the cost curve. When I saw schools such as Alpha organize academics around mastery rather than seat time, the model clicked. If you’ve heard of Alpha School, that is directionally the kind of learning model that inspired us. But I kept thinking about the families and schools that already exist: homeschool families, microschools, hybrid schools, and regular classrooms where most children are today.Most students and teachers see learning gaps at the wrong resolution. They get a grade, percentile, benchmark score, or broad standard—not “th
Hacker News1mo agoToolAI
Hey HN! This is Divit from Almanac (YC S26). We built CodeAlmanac, a wiki for your coding agents that updates as you talk to them. It is open-source, local, and free.Here’s a demo: https://www.youtube.com/watch?v=XNQWV3TFBWMYour CC/Codex conversations contain a LOT of knowledge that is forgotten because it was never documented. People have their own methods of documenting their chats. We used to make Markdown files like MANUAL.md and DESIGN.md, and would prompt Claude to keep them updated. The problem is that these files quickly become outdated and messy, and there’s only so much you can put in a single file.So we set out to build CodeAlmanac. We wanted something that was 1) maintained automatically, 2) lived inside our repository, and 3) used our existing Codex/Claude Code subscriptions.CodeAlmanac maintains an almanac/ folder inside your repository. It contains connected Markdown pages that cover things not documented in the codebase, including decisions you have made and why the codebase is shaped this way.The pages are indexed in SQLite and are queryable through a CLI. We add instructions to AGENTS.md or CLAUDE.md so future sessions automatically search the wiki before they start coding.Every five hours, CodeAlmanac uses the Codex/CC SDK to spin up an agent that reads your new conversations and updates the relevant pages. We went with a time-based trigger instead of commits because we saw people commit very frequently, which would lead to high token costs.We originally made CodeAlmanac for individual developers, but the team use case has become much more obvious to us while using it ourselves. We are a team of three, and each of us works with our own coding agents. Before this, I would make some change after a lot of thinking and then later have to call my cofounders and explain why it looked this way. There is almost a sense of relief now knowing that the decisions I made are written down somewhere their agents will actually r
Hacker News1mo agoToolAI
Hacker News2mo agoToolAI
With code coming in faster and faster, we've been losing track of context, what's out of date, the source of truth, etc. Also with individuals spending less and less time on any one problem, finding an expert to answer questions has become challenging. People don't have that single domain of expertise like we used to. There's too much surface area to cover.Are we the only ones dealing with this? How's everyone else handling it?
Hacker News1mo agoToolAI
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think.My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert.It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but it fades into the background beyond that. Turns out these things are really cool, but absurdly expensive.Ours was installed in 2008 and cost six figures. It's calculating ball speed and trajectory, camera-based pin detection (object detection and trig, on ICs!), runs the fouling, the animations, the pinsetting machine and ball return. Very cool stuff for its age.From the business perspective, my facility only cost me $105k. To forklift-replace the score keeping system runs anywhere between $80-$120k, depending on features, vendor, and unit age. No upgrades or service contracts, mind you, and every feature and customization is a new line item. That's for a 1:1 replacement on a system installed in 2008. Incredible, given how fast the tech world moves.Replacement parts cost a shocking $4000 per pair of lanes. But wait, the bowling machines themselves are 70 years old, so what's this "advanced" system actually doing back there? Actuating a single relay to trigger that big old machine. Everything else is strictly mechanical. Meanwhile I've got a six-figure invoice in my hand. I'm upset.Given the state of open hardware, computer vision, real-time event streaming, and open source running megascale products worldwide, there had to be a way to do this myself.So far I've built an equivalent prototype for about $200 per
Hacker News1mo agoToolAI
Hi HN, I am co-founder of Kickstage, a software company specializing in solutions for the electrical industry and lately grid operators.We are hiring engineers from different backgrounds, a lot of them software developers with limited experience in the sectors. Deep domain knowledge is key in our industry however, so we are constantly teaching the basics of power flow analysis, active vs reactive power, transmission line properties etc.With Jupyter notebooks and the Python console only, that's a tedious task and hardly ever led to a deep understanding of the topics.So we built BambooGrid: a web-based editor on top of pandapower, a popular simulation library in our industry. You drag elements like buses, lines, loads generators and transformers onto a canvas, wire them up, set parameters and run power flow. It will print results directly on the canvas, color buses according to their voltages, even allows you to see an interactive admittance matrix.You can try it out without installing anything on https://bamboo.kickstage.com (thanks to our friends at Hostzero who sponsored hosting). Start with one of the included samples or draw your own. Just don't forget to add a slack element.Built on a Python backend (driven by the choice of pandapower mainly) and a React frontend. Fully MIT licensed, so feel free to use and modify to your liking. Even better: Give us feedback - we're extremely open to suggestions how to improve the tool and are glad about every user who learns a bit more about power systems through it.Šime, who built most of this, is also in the thread. We are both happy to answer anything about the implementation or power systems in general.
Hacker News2mo agoToolAI
GUI disk analyzers are great for figuring out what's filling up your laptop/desktop drive.On containers or remote servers, the options are limited to purely text based utilities (e.g. du) or list-centric TUIs (e.g. ncdu) which are usually limited to viewing one directory at a time.I created leaves to fill that gap.Inspired by classic utilities like WinDirStat and KDirStat, it uses a 2-dimensional treemap^1 visualization to show the entire directory hierarchy with proportionally sized rectangles.It's performant enough to handle millions of files, thanks to Rust and multi-threading. However, block characters aren't as suited as pixels for resolving a large number of items. Leaves can show file-type summaries per directory or partition the top-level directories by extension, allowing you to see not only where space is being used, but also how.For instance, I can see the largest chunk of my home directory is taken up by uv caches for python and old Linux ISOs that I could easily re-download if needed. Or in a particular container, +600MB is used by standard Rust documentation and tutorials, and that it is the only location with HTML/JS files, when only the libraries and build tools are needed (note to self: remember to use the minimal profile next time).^1: https://github.com/shundhammer/qdirstat/blob/master/doc/Tree...
Hacker News2mo agoToolAI
Hey HN, we’re Nitish and Prateek, the founders of Coasty (https://coasty.ai/computer-use). We’re building computer-use agents that can complete workflows inside legacy desktop software and web applications without usable APIs.Developers send Coasty a natural-language task either through our consumer app or through our API, select a machine or browser environment, and any relevant credentials or files. The agent then operates the interface through screenshots, mouse, and keyboard input, verifies the result, and returns a structured run record with screenshots, actions, outputs, and errors.Here is a raw demo of an agent completing a workflow in a legacy application(It’s a mockup): https://drive.google.com/file/d/1ZghU_3vsAYhHVz1bsvE0pkvZYk7...A lot of important software is still difficult to automate. Healthcare teams submit prior authorizations through payer portals, accounting teams enter data into desktop applications, and operations teams move information between internal systems, spreadsheets, and remote desktops. Many of these applications have no API, incomplete APIs, or integrations that take months to build.The usual alternative is RPA, record a sequence of clicks and replay it. That works when the interface and workflow are predictable, but it often breaks when a button moves, a pop-up appears, a page loads slowly, or the application enters an unexpected state.Coasty takes a different approach. The agent observes the current screen, decides what action to take, executes it, and then observes the resulting state before continuing. It does not require DOM access, an accessibility tree, selectors, or an application-specific integration, so the same API can operate browsers, remote desktops, and older Windows applications.A simplified request looks roughly like this: run = coasty.runs.create( environment="vm_123", task=""" Open the patient record in the billing portal. Ente
Hacker News2mo agoToolAI
Hey HN, we’re Xia and Varun, the founders of Traceforce (https://www.traceforce.ai/). Traceforce provides visibility and control over AI apps such as ChatGPT, Claude etc directly on all devices (laptops, sandboxes, virtual machines) by discovering not just which apps are being used but also how they are connected to other data sources via MCPs. We also have an open-source dynamic MCP pentesting tool https://github.com/traceforce/mcp-xray to detect vulnerable MCPs.The purpose of Traceforce is to:- Give a company’s employees a standardized way to ensure that AI software running on their device is operating safely- Give the company’s security team visibility of the activities of AI software on the company’s devices, and to detect and prevent unsafe actions and security breaches as early as possible.How Traceforce works1. Traceforce is installed on each device as a lightweight binary and browser extension.2. Within 30 minutes, the device is uploading live data to the company profile, displaying all the AI agents/apps running across all company devices on a dashboard.3. Company security staff can monitor the activity of all the agents in real time, implement controls, and be alerted to any security risks as soon as they arise.Here’s the video demo: https://youtube.com/watch?v=IdK2WKg7kaMThe inspiration for Traceforce came via Xia’s experience as Director of Engineering at a startup called Clumio (which was acquired by Commvault in Oct 2024). Being able to monitor how team members are using AI without slowing them down was a top priority at Clumio. After speaking with 50+ CISOs and CIOs, it became clear that this is a much-needed solution right now across industries. We keep hearing that new AI features are being adopted so quickly and so broadly that visibility and control just can't keep up.Traceforce is transparent about what we monitor and collect. By default, Traceforce collects only metadata and telemetry a
Hacker News2mo agoToolAI
Hi HN folks ! I am the author of AVA, a self hosted AI Voice Agent that plugs into Asterisk/Freepbx so you own all the aspects of an AI Voice agent in your own infrastructure. It uses Asterisk native Audiosocket/RTP with python engine to run STT,LLM and TTS loop. The project support several full providers openai, gemini, grok, elevenlabs out of the box and also provides options to build custom pipelines by choosing different stt tts and llm.It also supports full local agent if you have a GPU with 25GB RAM which enables realtime conversation along with tool calling.I started this as a hobby project last year when I started exploring voice agents and every saw every Saas tried to lock you in their eco system. Since then project has taken off and a lot of asterisk people started using it due to ease of setup and wide range of providers and flexibility.Core is MIT: https://github.com/hkjarral/AVA-AI-Voice-Agent-for-Asterisk Free and open source forever.No install Mock UI us hosted at: https://demo.agent6789.comI am also exploring to convert this into a more polished version for Operators to handle multiple customer and multi tenant environment and I would genuinely like to hear feedback on it.Happy to answer any questions and gather any feedback. Thanks.
Hacker News2mo agoToolAI