7,296 results for Tool · 2.419s

News for “Tool”
19 results • 2407 ms server time
Moozonian News
github.com• Jun 23, 2026• 1 min read
Show HN: Videopython – local-first video processing, editing and AI workflowsI've been building videopython, a Python library for programmatic video editing, processing and AI workflows. Repo: https://github.com/BartWojtowicz/videopythonThe core idea is that edit is just a JSON / Pydantic plan. This plan can be validated against metadata of source video(s) via a dry run, then edit plan can be executed via streaming pipeline (many thanks to ffmpeg!) without holding frames in memory.Thanks to the JSON/Pydantic format of edit schema, you can easily expose it as tool for LLMs and let your agent-of-choice be your personal editor (MCP support included). The usual flow is first analysing videos via a number of ML models to get both visual and audio understanding of all videos. Next, based on the understanding, you build the edit plan, validate it and render the final video. There's a simple refine loop catching errors and fixing the simple mechanical ones, which allows model to converge on executable schema.Currently, the whole ML/AI stack is deliberately local, mostl
Moozonian News
khala.to• Jun 23, 2026• 1 min read
Show HN: Khala – let your AI sessions talk to each other, across any LLMI got tired of babysitting context between my own AI sessions and having to copy-paste summaries or update MD files across sessions for different purposes, so I built this.Every AI session starts with a blank slate. Whatever you built up in the last session, like architecture decisions, debugging history, the reasoning behind every choice, is all gone. So youu re-explain from scratch.Khala fixes the handoff at the source. Instead of writing a summary file, the sending session packages its full context and delivers it directly to a named inbox. The receiving session picks up exactly where the sender left off. Works across any MCP-compatible tool (Claude, Cursor, Codex, ChatGPT, etc.).Demo: https://youtube.com/shorts/i8xgbrY_Y0gInvite-only for now, drop a comment if you want to try it free this month and I'll send you a code.
Moozonian News
omnimod.net• Jun 22, 2026• 1 min read
Show HN: OmniMod – Moderation API for user-generated content platformsWe built OmniMod for platforms that handle user-generated content.What OmniMod does:Send us text or imagesWe apply your business content policyReturns Allow, Flag, Block, or Review with a confidence score, reason code, and full audit trailWhat we are looking for in beta testers:Platforms with user-generated text or imagesTeams currently doing manual review or evaluating moderation toolsHonest feedback on what's missing or brokenHappy to answer any questions about how we built it or what problems we ran into.omnimod.net
Moozonian News
news.ycombinator.com• Jun 22, 2026• 1 min read
Super AI Agentic Android App (BYOK)i am building an Agentic Android App (twent.xyz) that has:SOTA agentic memory + Knowledge Base to see Agent's memory, UI Automation, explain-what's-on-screen, Linux Ubuntu Terminal with Agent CLIs Supported, Connects to 1k+ tools, Infinite MCP Servers & Agent SKILLS, Browser to browse MCP Servers & Agent SKILLS (fetched from public sources) , Fully Bring-your-own-key (as of now) (get API key for any provider from the APP itself), supports local models.I really DONT WANT TO GUESS what my users want.I turned 16 this month and over the past year ive built something which i'd like to deem 'the ONLY Autopilot Agent + Thinking Partner for Android' . this is my BIGGEST passion project so far.I really would want anyone's feedback on what i should change, what you would like to see, what you think is missing, etc.feel free to DM me or comment under this post. Criticisms are ALSO welcome .THANKS :-)again, website is twent.xyz
Moozonian News
github.com• Jun 22, 2026• 1 min read
Show HN: Selector Forge – browser extension for AI-generated resilient selectorsHi HN, I'm Ahmad from the Intuned (https://intunedhq.com) team. Today, we're releasing and open-sourcing Selector Forge (https://selectorforge.ai/), a browser extension that generates reliable CSS/XPath selectors using AI.You can use it to create a selector for a single element or for an array of elements. The selectors it creates are meant to be "semantic" and more resilient to page changes than what Chrome DevTool’s “Copy Selector” (and other similar extensions) give you. Those tend to hand you something brittle like `#top > div.w-100.ph0-l.ph3.ph4-m > h1 > span`, which can break with a minimal page change. Selector Forge aims for selectors that don't break as easily. Here are some selectors that Selector Forge created: `//div[@aria-label="Showing weekly downloads"]//p[@aria-live="polite"]` (item selector) and `//*[local-name()='svg' and @aria-label="Download statistics"]/following-sibling::div` (list selector).Here is a video demo of using the extension: https://www.youtube.com/watc
Advertisement
Moozonian News
news.ycombinator.com• Jun 22, 2026• 1 min read
Show HN: Revenant – automatic LLM powered reverse engineering and reimplementI am a hardware engineer and security researcher and I've been wondering whether my work could be partially automated, so I can focus on other topics as well, so I build revenant - a LLM powered (Claude, OpenAI, local AI) toolkit that builds around radare2, ghidra etc and can fully automatically analyze firmware, implement open source skeletons incl. pinouts, hardware bringup, peripheral bringup etc. or can even 1:1 replicate existing firmware so old hardware can be resurrected with modern toolchains.Some applications are:- Give old hardware new life- Security Analysis of shady firmwareCheck it at: https://github.com/DatanoiseTV/revenantI would love some input on this and maybe some recommendations for improvements.
Moozonian News
bing.com• Jun 22, 2026• 1 min read
The 71 Best Beauty Devices and Treatments to Know in 2026Every item on this page was chosen by an ELLE editor. We may earn commission on some of the items you choose to buy. Beauty tools and treatments have never been so innovative. From a Korean skin care ...
Moozonian News
jacobee.netlify.app• Jun 21, 2026• 1 min read
Show HN: Jacobi–IDE for Abaqus subroutine with analytical tests and AI diagnosisI 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
Moozonian News
trustmux.dev• Jun 21, 2026• 1 min read
Show HN: Trustmux – Lightweight Secure Daemon for Mobile Shell AccessI'm Dustin Kirkland, author of Byobu[1]. I built Trustmux[2] to solve a personal problem: secure, encrypted access to my tmux[3] and Byobu sessions from my phone, without the pain of other mobile shell approaches.I run long-lived shells, Claude, and other sessions in the background on my workstation, and I needed to check in from mobile — securely, with real TLS certificates and Tailscale-backed privacy, not some insecure workaround.Why not SSH / Mosh / Claude Mobile?- SSH/Mosh: Synchronous connection state is brutal on mobile. Latency, network handoffs between WiFi and cellular, laggy UX — neither felt designed for how people actually use phones. - Claude Mobile: Great for Claude, but locked to Claude. I wanted tool flexibility — shell commands, multiple code assistants, whatever's running in my tmux session.The key insight behind Trustmux: mobile terminal access needs to be asynchronous, not synchronous. Connect, run a command, disconnect — without maintaining fragile connection stat
Moozonian News
news.ycombinator.com• Jun 21, 2026• 1 min read
Ask HN: What's your go-to queue system?Hello,I am building a new product and need to have a robust queue system but I'm not sure what product to choose.I've worked in Amazon before and usually AWS tools are the default go-to but in my own time for small project I've used things like: https://github.com/hibiken/asynq for basic tasks.My concern with the above is that it's still in "early" development; from their README:``` Status: The library relatively stable and is currently undergoing moderate development with less frequent breaking API changes.Important Note: Current major version is zero (v0.x.x) to accommodate rapid development and fast iteration while getting early feedback from users (feedback on APIs are appreciated!). The public API could change without a major version update before v1.0.0 release. ```I'm building something right now that will require something very robust; scheduling, long running workflows with several external dependencies (which may have failure and need retries and notifications, webhooks, etc)
Advertisement
Moozonian News
rejourney.co• Jun 21, 2026• 1 min read
Show HN: A GitHub app that suggests code fixes for conversion failuresHi Hacker News!I’m Rashid, a first-year student at UT Austin and the person leading development of Rejourney, a web/app analytics and session replay tool.Recently, a handful of our users emailed us that they only care about a few user recordings (replays) that show conversion issues, and didn't want to waste time watching all the session replays they got. And no matter how many filters/smart capture rules we put in, the deterministic methods of choosing what to capture always missed important session recordings or overshot and recorded everything. Our users also used other platforms like Clarity or Posthog's AI that summarized all the replay issues, but those also either missed important sessions or focused on a few sessions rather than the overall picture in terms of revenue, growth, and conversion leaks.We started to think about the unit of analysis and segmentation strategies for failure patterns across many sessions. That led us to build Marlin (big fish), a GitHub app that looks f
Moozonian News
advertbench.com• Jun 21, 2026• 1 min read
Show HN: AdvertBench, ranking the ability of LLMs to create image adsExperiment that I've made. The models get access to an E2B sandbox and are instructed to create an ad according to the specifications (they can choose whatever tools they want to use for it, e.g. Pillow, Chromium) as a proxy for their ability to use tools, create other kinds of images, do complex layouts etc. Currently Opus 4.8 is on top (not surprising, but it did take 66 conversation turns to create the image) and GLM-5.2 is on fifth (which I do find surprising because it doesn't have image capabilty).
Moozonian News
news.ycombinator.com• Jun 21, 2026• 1 min read
Show HN: Pyor – A desktop PR reviewer for the diffs GitHub chokes onShow HN: Pyor - A better alternative to Github for reviewing PRssince the introduction of AI, the bottleneck for shipping code shifted from producing code to reviewing it, and the PR reviewing experience on Github is lackluster, leaving a lot to be desired.my team now ships too much code and it sits in review for too long, review AI code is not easy and we need a better tool to review code, especially on large PRs.So I built Pyor, a website and a performant desktop app to review code at least 3x faster compared to Github (from experience)As a web dev, I compiled all of my painpoints into this project, what would make a review easy (and even fun) for me, I integrated tools to group noise from actual important bits to focus on reviewing, that speeds up reviewing time immensely, especially on migration PRs where most is mechanical name changes.Try it out at https://www.pyor.review and let me know what you think!it’s free!
Moozonian News
github.com• Jun 21, 2026• 1 min read
Show HN: Quikdown – 17 KB bidirectional Markdown parser and rich-fence editorHi HN-This past year I've built and maintained Quikdown, a bidirectional markdown parser and companion editor in pure js, with batteries included fences for rendering rich content.Try it live: https://deftio.github.io/quikdown/pages/edit/The motivation was working with many different LLM frameworks and wanting to test tool calling and collaborative editing. Often I just wanted a pretty final output with rich support for diagrams, math, or other rendered content but, keep it editable. So a user (often me) could just work on the final (rendered) output while the LLM could see/seek/update/edit just using markdown under the covers. Quikdown editor supports md/split/rendered output and can run headless so you can bring your own UI. MCP support is included as well.The Quikdown parser has zero dependencies and is based on regex and outputs HTML with built-in tags for triggering plugins for fences (like Mermaid, Vega-lite, code syntax, music and many more). A separate set of attributes allow t
Moozonian News
tlaplus-process-studio.com• Jun 20, 2026• 1 min read
Show HN: TLA+ Process StudioDisclaimer: This was made with LLMs.I made this tool to help understand large business processes that can be modelled as a single state machine.The core loop of this is to enable to walk stakeholders through discussing each step, adding comments, and reiterating with an LLM of their choice to generate the TLA+ syntax on the left.Users can click through the green state nodes to see how things work visually.You can see some sample state machines in the dropdown in the top left.The power would come from getting folks on the same page of the business process, so engineers can think about how best to automate/modernize the system once they get all of the context.Additionally, once you have a single canonical model of the process, you could in theory send into a dark factory to produce the software as quickly as possible, but now we can allocate more time in the entire software lifecycle at the design and alignment before coding now that coding is faster.Additional work could be done using t
Moozonian News
argusred.com• Jun 20, 2026• 1 min read
Show HN: We post-trained a model that pen tests instead of refusingAnthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities.AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access.Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals.For this project we've post-trained a specific model on a decade of capture-the-flag contests. This won't be made available to anyone and everyone, but we do believe that responsible SMEs and midmarket companies also need access to these tools in order to identify key vulnerabilities in their systems; not just enterprises.We have developed two modes that run over a CLI:• Security scan: a read-only audit of your local codebase for vulnerabili
Advertisement
Moozonian News
bing.com• Jun 20, 2026• 1 min read
Sea of Thieves Launches Season 20 With Custom SeasXbox Game Studios and Rare have officially launched Season 20 for Sea of Thieves, bringing a few landmark additions to the pirate game. The team has added the Custom Seas toolset, giving players an ...
Moozonian News
schemic.dev• Jun 20, 2026• 1 min read
Show HN: Schemic – your database schema, in the Zod API you knowI want you to give a look to a tool I have been working on for a while, Schemic. It's a tool that lets you author your database schema in Typescript, you forget about the DDL and just think on your database's native lingo.I'd say the strongest points of the project is that it's a SUPERSET of the popular validation library Zod (https://zod.dev), which I'd say shines in representing typescript's type system in code. Schemic wraps it with database-specific flavour (opt-in, for precision) so you can do `s.string()` (zod drop-in, will work with any driver you choose) or `s.varchar()` (flavour added by the postgres driver).I would like you to check it out and to the SurrealDB project (https://surrealdb.com/), right now that's the most complete driver, I'm working on getting the Postgres driver ready as well so more people can try it out.Adoption is simple: `bunx @schemic/cli pull` will introspect your database and generate all schema files for you.Extra bit: the resulting structure after a p