Project URL Category JS Project Title DiffSeek: cut the noise in big GitHub PRs Project A Chrome extension for reviewing big GitHub pull requests. It filters changed files by CODEOWNERS owner, group, format and status, hides generated and already-viewed files, and shows viewed progress on every file and folder in GitHub's file tree. Highlights I'm the developer of DiffSeek. Builds on GitHub's own file tree instead of replacing it: each file and folder gets a viewed badge, and clicking a folder's badge marks its unread files viewed. Filters by every CODEOWNERS owner, by groups (built-in Tests, Docs and Config, or custom ones from .gitattributes), by format with aliases such as ts/tsx, and by viewed, generated and change status, with a live count on each row. Files marked linguist-generated in .gitattributes start hidden and are viewed automatically. No token, account or backend: it uses the existing GitHub session, so private repos work, and it collects no data. MIT-licensed, written in TypeScript. Example Code gitattributes dist/ linguist-generated=true db/migrations/ group=Migrations .tsx linguist-language=TypeScript or Videos
Hi HN, I'm Ruud, co-founder of Lont. We turn company emails into personalized videos. Video captions cost us manual work twice: fixing misheard words, then fixing layout, like lines ending on “the”. Overtone uses multiple models to listen to the audio: gpt-transcribe, Azure STT, and Elevenlabs Scribe. When they return conflicting results, Overtone sends small clips to the models again, and then lets an LLM decide what was actually said. The LLM is like a human doing a sanity check on the transcription model. Humans would easily recognize a word to be different based on context. The LLM basically does the same, using an optional context prompt + its world knowledge. Because of this the Word Error Rate (WER) on many test files is lower when using Overtone, compared to just using a model without it. Sure, the cost is higher because we use up to 3 different STT models + an LLM, but it still removes mistakes, reducing the time needed to fix captions to a minimum, and reducing the chance you'll miss something. For us it's worth it. For ultra high volume use cases it may not be. The rules-based cutter nicely cuts the transcript into captions that look good, depending on screen size: 16:9 is different from 9:16, and the Overtone Format we created supports any type really. Pauses become breaks, captions are grouped per speaker, and names/numbers are never spread out over multiple captions. How to add these captions to your videos? A videojs plugin can do this automatically, so you don't burn in your captions. The plugin lets you cycle between styled captions, plain captions, and off. You can burn them into an MP4 file with overtone burn. Quickly try it out just the cutter? Try: npx overtone-captions recut yoursub.srt Transcribing audio with API keys works too. Use --dry-run to show a cost estimate before you send. We open-sourced this first version (MIT) because we believe many people can benefit from this, especially if your captions just need to be good. There's plenty of room to improve though, so we've made it easy to help contribute to add style packs, languages, and providers/models. You can find a at: https://overtone.lont.ai/ Find the code and benchmarks here: https://github.com/lonthq/overtone-captions
Hi HN, I built cc-pair because I kept noticing that when a coding agent reviews its own work, it tends to go easy on it. cc-pair pairs the two agents I already use — Claude Code and Codex — so one authors a change and the other reviews it, and they iterate until the reviewer approves or the round limit (default 3) escalates to the human. Roles are symmetric: either agent can be author or reviewer. In auto mode, `pair start --as claude` (or `--as codex`) opens the author and starts the other agent as reviewer for each round — no second terminal needed. In manual mode you run both yourself. They communicate through numbered message files in a shared directory (~/.pair/<repo>-<hash>/), so the whole review thread is inspectable on disk. Install: npm install -g claude-codex-pair (Node 22+, macOS/Linux for auto mode; manual mode works on Windows). Both CLIs need to be installed and signed in. https://github.com/leonlee/cc-pair — the README has an example review thread in Appendix A, and DESIGN.md specifies the protocol. I'd love feedback: does cross-model review actually catch things self-review misses in your experience, and what would you want the reviewer to be stricter about?
A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.
SOMA 是一款开源桌面 CAD 应用:你用自然语言描述需要的零件,Claude Code、Codex CLI、OpenCode 等编程智能体用 Python(CadQuery)写出参数化模型,SOMA 实时构建并显示 3D 结果。适合需要外壳、支架、安装座的创客和 3D 打印爱好者,不会 CAD 也能上手,导出 STEP、STL、3MF 即可打印或加工。 亮点 不绑定任何 AI:使用你自己已有的 CLI 智能体和订阅,模型选择和权限都由你掌控 模型即代码:每个模型都是可读的 CadQuery 脚本,每一步都有 Git 历史,可预览和恢复 和智能体“指着说”:在 3D 视图中点选零件、精确测量、直接在画面上标注,再发送给智能体修改 不只是建模:剖切、爆炸视图、参数面板、标准件(螺钉、螺母、热熔螺母)、FEM 强度分析(CalculiX)、动画渲染和带尺寸的工程图(PDF、DXF) 开箱即用:Windows、macOS、Linux 安装包已内置 Python、CadQuery、Git 和 CalculiX,GPL-3.0 开源 (Note from the maintainer: this text was written with the help of an AI translation, as I don't read Chinese. Replies in English are easiest for me, Chinese is fine too.)
Hey HN, I'm Christian and this is a new OSS project I've been noodling on for the last couple of weeks. Hob is a free, MIT-licensed desktop app for Mac, Windows and Linux that works on your files the way the Claude and ChatGPT desktop apps do, except the model runs on your own computer. It uses open-weight models (currently Gemma 4 and gpt-oss). All your chats and files never leave your system. The only things that go online are web search (can be turned off in settings) and any MCP connectors you add yourself. Main features: - Automatically finds the best open-weight model for your hardware on first install (Mac/Linux/Windows) - Writes sandboxed Python code for ad hoc tools (data processing, document conversion, graphs etc.) - Built-in web search (powered by SearXNG) - MCP support - Image recognition - CRUD to your local filesystem - Works fully offline with no internet Before building this I tried every local AI app I could find, but it seemed each one had different problems. The main thing I noticed is that none of them could do what the ChatGPT and Claude apps do with your files, e.g. read and change files in a folder, look at images, run code in a sandbox, draw a chart. The most advanced thing any of them did was paste a plain text file into a small context window, which basically failed as soon as you had a file larger than a few KB. I couldn't find anything that could easily parse images and bigger PDFs. The OSS solutions that were more advanced all seemed to default to hosted models (either OSS or closed), which defeats the entire point of the privacy that on-device OSS offers. They also seemed to push towards an account/open-core style business. I build it using Electron bridged with llama.cpp in its own process. On initial load, the system will try and figure out if you have a compatible graphics card and if not default to CPU-only (I ran into a lot of issues of graphics card beeing seemingly compatible but then crashing on first query, there's a whole saga to this lol). Code execution happens in a sandbox that can only write to the chat's folder and has no network unless asked (sandbox-exec on macOS, Landlock on Linux and a low-integrity process on Windows). Images go to a small Qwen3-VL model. Dictation is a local Whisper model. The hardest part was definitely to get the smaller models to use tools reliably. Ran into a ton of issues of 4B models happily saying "here's your chart" without ever calling the chart tool or get stuck in an infinite call loop. I spent a fair amount of the work building guards vs tweaking prompts (that didn't really work for small models). I understand the pushback that local models are weaker than frontier cloud models. This is true, but for most tasks for most normal people, I'd argue you rarely need the newest frontier model. From my own evals, systems with 16+ GB of RAM do really well, and if you have a GPU or more RAM, you get very close to what you'll get out of the box with a frontier hosted model. Excited to hear what you think and see how it runs on other systems!