2,315 results for Tool

vektorgeist.com
Show HN: Vektorgeist- A platform for AI operators and their agent'shttps://vektorgeist.com/VektorGeist is a platform designed for AI operators to discover, share, and distribute AI resources in one place. The platform brings together: AI tools MCP servers Prompts Workflows Templates Agents Technical articles A community for collaboration Recent updates include selectable layouts, customizable themes, an immersive interface, community profiles, and a marketplace for sharing projects and resources. The goal is to create a central hub where AI operators can find practical resources, contribute their own work, and collaborate with others without having to search across dozens of different platforms. Feedback is welcome, especially on: Overall user experience Features that would improve the platform Missing functionality Ideas for making it more useful for AI operators Website: https://vektorgeist.com Discord:https://discord.gg/EEsMTJ73m
Jul 16, 2026 9:52 PM
news.ycombinator.com
Ask HN: Best meeting transcription daemon for macOS?https://news.ycombinator.com/item?id=48936123Granola are cracking down on their auth and I can no longer pull my meeting notes out and put them in Obsidian (my plugin is gonna have to be deprecated: https://github.com/tomelliot/obsidian-granola-sync/).That means I'm gonna need a different meeting transcription/summary pipeline. There's a cambrian explosion of meeting transcription tools (https://hn.algolia.com/?q=Show+HN%3A+transcription). It's awesome.I've tried some, but haven't found one that works how I want. Can you help me find one that suits my use case?- daemon runs in the background- uses local models for transcription, diarization/speaker identification- primary interface is CLI/no UI. It should just happen in the background.- GUI is secondary. Maybe a button in the menu bar for starting/stopping a meetingoptional/secondary- pulls in calendar info for titling and attendees- cleans the transcript- generates summary
Jul 16, 2026 3:44 PM
pastehex.dev
Show HN: I've built tldraw for HTML and Markdown pages (with encryption)https://pastehex.dev/Hello, HN!This is a small app I've built to satisfy three pains/wishes I've had for a while and I think there might be people out there who can benefit from it as well.1. I want to pop up a new tab, start writing my thoughts and, maybe, share them over the internet. As fast as I can and with as little friction possible. tldraw totally does this for drawing stuff in a whiteboard but for text, Obsidian is a local tool that requires installing and Notion is too involved. I want a simple link that just works the moment you navigate to the page.2. Sometimes I wanted to share code or other text artifacts with customers over Discord, but the platform caps messages to a certain length before it forces you to submit a .txt. Pastebin kinda fills this gap but it's an old site and it doesn't handle BIG pastes very well also it doesn't double as your own document vault (plus I don't care about all their "public pastes" thing).3. This is a recent one. Now, due to AI tools, everyone is sharing Markdo
Jul 16, 2026 2:26 PM
github.com
Show HN: An MCP server that frames screen recordings and shots in Apple bezelshttps://github.com/cwooddgr/bezelbub/tree/main/bezelbub-mcpCreating device-framed screenshots and screen recordings for my iOS, macOS, and tvOS apps is a pain so I looked for a tool, preferably with an MCP server that could do it for me. I couldn't find anything that did everything I wanted (images and videos, scaling, transparent backgrounds for both, etc) so I made one: Bezelbub.I started with a macOS app. Handy when putting together App Store listings, which was my first use case. Then I added support for video in/out. But I realized I wanted framed screenshots in more places than that (like social posts) so I made an iOS app that would allow me to just snap a screenshot on-device, share it to Bezelbub, choose my options, and share it directly from there. Neat.But I still found myself doing a lot of the work, which in the age of Claude Code is goofy. So I created a command-line version and a Homebrew tap. Works a treat. I intentionally made it agent-first (no interactivity, complete docs in --help, JSON output, meaningful error codes, sugge
Jul 16, 2026 2:21 PM
pokayoke.codes
Show HN: Pokayoke – turn code conventions into checks for agentshttps://pokayoke.codesHey HN,Something I've been tinkering with in the background is a system to manage the "messy-middle" of TypeScript toolchains. Quite often, when I'm using Biome or any of the other linter / formatters, there will be repo conventions that I want to enforce (especially with AI agents), but which aren't supported by them, such as:- Enforcing lines-of-code limits in modules - Never using custom TailWind colors - Only using lowercase underscores in filenamesLike, this is quite "random" but also bread-and-butter stuff that it's easy to think or talk about when you're working by yourself or with a few other human teammates, but I've found that agents consistently miss these conventions if I put them in an AGENTS.md file for example.I wanted to make my esoteric repo conventions less stochastic, and more deterministic. I realised that agents are adept at writing the kind of code needed to run arbitrary checks on the TypeScript AST or workspace environment -- the kind of code that is cumbersome
Jul 16, 2026 9:40 AM
news.ycombinator.com
Show HN: LHIC – Deterministic device agent which learn and enhance when you usehttps://news.ycombinator.com/item?id=48932029We built LHIC (Local Human Intent Controller) because we were frustrated by existing LLM-based browser agents. Tools like WebVoyager or ServiceNow's baseline agents are amazing, but they are: 1. Slow: Taking 20 to 40 seconds per simple form-fill step. 2. Expensive: Calling GPT or Claude for every single click. 3. Brittle: Failing the second a minor DOM class name shifts. LHIC introduces a "Fast Path / Slow Path" dual-route execution architecture: - Fast Path (Local, 0 LLM call): For standard web flows (logins, forms, search), LHIC matches user intents directly with pre-defined skills and resolved DOM attributes locally. It runs in under 35ms (median) with zero API call costs. - Slow Path (LLM, Fallback): Only activates for complex, open-ended tasks or when a high-risk action is flagged.Key Technical Highlights: * Self-Healing Semantic Locators: We fuzzy-match DOM structural targets using SQLite historical skill memory, achieving an 80% success rate improvement over static CSS/XPath sel
Jul 16, 2026 9:01 AM
github.com
Show HN: Aireceipts, itemized cost receipts for AI coding agentshttps://github.com/anandgupta42/aireceiptsHi HN. I built this at work for fun because I could not answer a basic question: what did that last agent session actually cost me?It does three things:1. A statusline under the agent's input box while it works: which model is billing you, cost so far, dollars per hour, and how much of your rate-limit window is gone. Waste like a stuck Bash retry loop gets flagged on the line as it happens. 2. "npx aireceipts-cli" after a session prints an itemized receipt: every tool priced, plus a "same tokens on a cheaper model" line that is arithmetic on the same token counts, not a prediction. 3. "npx aireceipts-cli pr --post" attaches the cost of the sessions behind a PR as a comment. There is a real one live on the repo's PR #189.How it works: it parses the local transcripts your agent already writes. Claude Code, Codex CLI, and Gemini CLI get full per-turn parsing (models, tools, cache tiers). OpenCode is per-message. Cursor is an honest degraded mode: its logs carry no per-turn usage, so you g
Jul 14, 2026 2:16 PM
news.ycombinator.com
Ask HN: AI Agent and harness containerization/security recommendationshttps://news.ycombinator.com/item?id=48899674Hello HN crew -I am seeing the tendency for people to allow AI agents to access local project & user folders, and beyond (operating system files).I thought to ask the question: How can we best use AI tools safely - where the workflow often runs local system commands and network commands - to protect the integrity of our systems & data AND be easy enough to use productively?Comment structure idea:Operating system / Agent harness / Agent / Security strategy & tool stack / WorkflowTo give some examples: I am currently using OpenCode (+DeepSeek) on Linux Mint Debian Edition (LMDE), and I notice that the Agent & harness is frequently asking to create files in /tmp/ - I usually forbid this, and instruct it to only use files in the current folder. I would rather that the tool ONLY have access to a given project folder (~/Projects/PROJECT-NAME) in a system-enforced way. However, I see that the agent often wants to run system commands (like `ps` to debug a local dev server, `pandoc` or `ffmpeg`
Jul 13, 2026 10:19 PM
duiduidui.app
Show HN: Duiduidui is a new Chinese dictionary and flashcard apphttps://duiduidui.app/en/Hello everyone! I'm a solo developer, and intermediate Chinese learner, and I just launched a new Chinese app I want to share with you.My own Chinese language study stack used to be Pleco (and Goog Translate) for dictionary lookups, and then Anki for flashcard reviews, with a lot of manual copy-pasting in between. Which worked... okay. But the two sides never talked to each other. Pleco doesn't know what I'm studying, and Anki doesn't know anything about Chinese. So it treats 好吃 and 好 as totally unrelated cards, even though getting one right obviously tells you something about the other.So I built duiduidui! (对对对), which is basically those two tools fused together, with a study engine that actually models how Chinese is structured:- A dictionary with 200k+ entries, always available/searchable offline (characters, words, phrases, sample sentences, speech audio) where everything is linked. Every character links to the words it appears in, and the radicals it's built from, so you can (for
Jul 13, 2026 7:15 PM
esa.int
AMAT: charting ESA’s path through the Solar Systemhttps://www.esa.int/Enabling_Support/Operations/AMAT_charting_ESA_s_path_through_the_Solar_SystemEvery space mission starts with a question: how do we get there? At ESA, Advanced Mission Analysis Tools (AMAT) is helping mission analysts answer it, providing a modern, flexible environment for designing complex trajectories from Earth orbit to deep space.
Jul 13, 2026 8:30 AM
github.com
Show HN: 9lives – Self-healing test runner that refuses to mask real bugshttps://github.com/Quality-Max/9livesI built 9lives because coding agents kept breaking my Playwright tests in the dumbest way: rename a button, the test goes red, and the agent — or I — rewrites a perfectly good test.9l heal login.spec.ts runs the test, classifies the failure, and heals it in tiers:Tier 1 is offline and deterministic. When a selector stops matching, 9lives re-finds the element in the page snapshot Playwright captures at failure (data-testid > id > aria-label > text > class — the most stable surviving anchor wins) and rewrites the locator. No LLM, no network, no account. Most selector drift heals in seconds, for free. Unlike Healenium-style tools, it needs no baseline DOM from previous green runs — it works from the failure itself.Tier 2 uses the subscription you already pay for. For structural changes it shells out to your installed claude / codex / opencode CLI in headless mode, so the fix rides your existing coding-agent plan. No new API key to mint. (Raw ANTHROPIC_API_KEY / OPENAI_API_KEY work too.)Ev
Jul 10, 2026 6:01 PM
sxp.studio
Show HN: SubjectiveZero, an open-source agentic node editor for creative codinghttps://sxp.studio/apps/subzHey there,My name is Clem, I've been a solo indie dev for a couple years now, exploring frontier tech like XR and agentic workflows in the context of creative / interactive work.I've been building creation tools for a while and some common design challenge is to figure out the right level of abstraction for your tool. You can always make it super advanced and complex with low level concepts (shader composition, actual code etc.) but then you get something with a high complexity / learning curve. On the other hand, if you make your tool too high level, it might be easier to use at first, but people will most likely hit a wall eventually and start fighting with your tool to get their edge case done (you see that on mobile a lot actually).With this prototype (called SubjectiveZero), I'd like to imagine that we can kind of move the "slider" on the abstraction layer, meaning that you can actually start with prompts that describe the goal, and you can go as high level (stay with abstract pro
Jul 10, 2026 3:23 PM
mojavepaint.app
Show HN: Mojave Paint for macOS, edit images like it's 1999https://mojavepaint.app/We all need a swiss army knife for images. A tool for really getting in there and dealing with the pixels precisely. You might be combining images into a sprite sheet, you might be matting images to squares, cutting out solid backgrounds, re-tinting graphical elements. For a website, a video game, for an app.There's a million photo editors, there's a million design tools, and Mojave Paint can do those things in varying degrees but "graphical asset production" is its first and primary mission.It's cheap! $9.99 (one-time, sad I even have to say that) for the "Pro" version. It's Mac-only, and Apple Silicon Mac at that. Does it look a little like Photoshop 5.5 from the year 1999? Maybe a little but also it's got plenty of its own original ideas. (Blog post on that is forthcoming…)I've always been passionate about image editing tools for the technically-minded so I'm throwing my hat in the ring in that space. And sure GIMP is for the technically-minded but boy is it ugly on the Mac!
Jul 10, 2026 12:29 PM
bing.com
Newsletters Are All the Rage. As an Author, Here’s What to Use Based on Your Needshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8ac5add0154303a78b4726951ac5ad&url=https%3A%2F%2Fwww.cnet.com%2Ftech%2Fservices-and-software%2Fbest-newsletter-platforms%2F&c=5184381445036580967&mkt=en-usNewsletters are some of the most powerful marketing tools around. While a social media post might reach a handful of your followers, newsletters are sent to every subscriber. This makes a newsletter ...
Jul 10, 2026 10:00 AM
whitematterlabs.ai
Show HN: PAI, a Linux-y personal-assistant for Machttps://www.whitematterlabs.ai/Hi HN!I've been spending the past month on PAI, a Linux-esque harness for a personal assistant AI for your Mac. Instead of giving a chatbot a bunch of tools, I wanted to just drop the LLM into a terminal and see how it'd fare.I've been using it to manage my calendar, 5+ email accounts, and engaging with / responding to people in a timely manner (casus belli for this entire project).After seeing how other always-on assistants were designed, I thought the Unix / Linux philosophy of system design could be applied to AI harnesses, and I wanted to experiment with how it'd hold up compared to them. So, I built PAI with the following things in mind:1. Engaging "code mode" in the LLM (LLMs are natural SDEs / SysAdmins) - If you remember the [code mode](https://blog.cloudflare.com/code-mode/) post from a while ago, I wanted to try and utilize those capabilities within the model for it to naturally interface with the harness rather than trying to load it up with a bunch of exposition. An LLM nat
Jul 6, 2026 10:16 AM
lovelyzombieyho.github.io
Show HN: MotionLoom – An open-source video-as-code language for video creationhttps://lovelyzombieyho.github.io/anica-landing-page/motionloom/I am building a motion graphics and VFX language specifically for video creation, image effects, and visual composition. Recently, the generative AI field has really inspired me. Besides diffusion models, one of the projects that influenced me is RemotionJS. My personal view is that 2D can create almost anything, even the perception of 3D, because in the end, we experience everything through a 2D screen. I believe diffusion models will become better and better, but I also think they may not be fully adjustable pixel by pixel in the foreseeable future. Because of that, I believe “video as code” is still a separate and important path for the future. But why create my own domain-specific language (DSL)? When I tried other video-as-code tools, I found that users still need to understand some programming concepts. Not a lot, but still enough to create friction, especially for non-technical users. That made me think about how to make video creation easier for people who are not programmers.
Jul 2, 2026 5:53 PM
rileywrites.ai
Show HN: Riley – Content That Sounds Like You, Not Like AIhttps://rileywrites.aiWorking for a US company with several, very different, lines of business taught me how difficult it is to post on social media consistently and keeping the essence of each brand in all posts. Standard AI tools helped me get the first draft, but that was it. I would spend hours editing the output to make it sound a bit more like me, but in the end this was more time-consuming than starting from a blank page. Tired of choosing between consistency and maintaining the brand’s essence and my voice, I built Riley. My goal was to teach AI how I sound and the essence of each brand to remove endless prompts and constant tweaking, keep creative momentum, and make content creation a smooth and enjoyable process. Riley learns from previous content you’ve written to generate pieces that sounds like you, not like AI. You can import examples (LinkedIn posts, website copy, social media, etc.), define context with @context-pills for background, audience, and style, and refine with feedback and comments
Jul 1, 2026 1:20 PM
lokalbot.com
Show HN: LokalBot – meetings, notes, and autocomplete that never leave your Machttps://www.lokalbot.com/I wanted to have a daily work summary on what I spend my time that is auto generated by an LLM and meeting notes without shipping my calls to someone's cloud, so I built LokalBot.It records, transcribes, and summarizes meetings and your work, entirely on-device on Apple Silicon using a model of your choice. The app has a few tools that are related and share local models: inline autocomplete in any app, and a private day timeline and a chat/search with your meeting notes.It's a native app, built with Swift and open-source. I'm still waiting for my Apple developer account to be approved so I can properly sign/notarize the app but there is a .dmg on GitHub you can install and try.For transcription I recommend IBM Granite Speech 4.1, and for summarization any of the Qwen 3.5/6 models work well.
Jul 1, 2026 9:45 AM
lingochunk.com
Show HN: Turn native language audio into flashcards and shadowing practicehttps://lingochunk.com/tryHere is a tool I built initially for myself to help with my German and Greek language studies. It started as a hack for creating Anki cards from native language audio. It extracts the words, finds their base forms (lemmas) and groups the examples by the lemma. At some point I realised that I have a transcription with word level timestamps that opens a lot of other opportunities. So I added a mode to click the first and last word in the transcript and it starts looping with the right gap and repeat count.Another feature I use a lot is selecting an audio fragment, sending a predefined prompt to an AI to "explain grammar" or "explain nuances of meaning" and I still experimenting with prompts.And because shadowing is so easy I also use it as a player to improve my English pronunciation. (I am not a native English speaker.)I made a quick video showing the workflow for creating Anki cards and shadowing: https://youtu.be/TaR58uuDBvU?si=o5aGLAi2S-BZ7Zy9The app supports 15 input languages (Japa
Jun 25, 2026 11:29 AM
jacobee.netlify.app
Show HN: Jacobi–IDE for Abaqus subroutine with analytical tests and AI diagnosishttps://jacobee.netlify.app/I write Abaqus UMAT subroutines as a graduate student in computational mechanics. These are complex multi-physics simulation models using Abaqus Fortran subroutines (UMAT ~ mechanical behavior, UMATHT ~ heat/diffusion and a lot more) that simulate how different material systems fail under high temperature or manufacturing processes.However, the entire process has been quite challenging, 80-90% of time is actually spent on how make Abaqus CAE simulate a physics you already know on paper or what are the correct subroutines and variables you should use. Huge time is also spent on diving deep into the .sta .msg files to figure out and debug why a simulation failed. The software or current tooling (IDE ~ which is VS Code etc built for software engineering, not computational physics or mechanics) doesn't tell you why the simulation run into a segmentation error, or warn you when your damage variable being 1 (fully damaged) will lead to a zero division error. Silent mistakes or errors propaga
Jun 21, 2026 4:20 PM