nowfound

AI · August 23, 2025

OS

Open-source+local Cursor for code review (use this instead of GitHub)

Hey again HN. Isaac and I originally released a voice-first code review tool, but have since open-sourced it and turned it into just a better way to review your and your team's Github PRs. Main things we've heard that make code reviews slower are: 1) PRs are too big and overwhelming 2) Need to jump around to find the right context and relevant code 3) Need to spend time thinking (should not be a thing since AI exists), and writing comments What we built to address these: 1) PRs are split up into sub-PRs without needing to actually split them up and stack them yourself -> Automatically done…

What it does

In the maker’s words, at launch

Hey again HN. Isaac and I originally released a voice-first code review tool, but have since open-sourced it and turned it into just a better way to review your and your team's Github PRs. Main things we've heard that make code reviews slower are: 1) PRs are too big and overwhelming 2) Need to jump around to find the right context and relevant code 3) Need to spend time thinking (should not be a thing since AI exists), and writing comments What we built to address these: 1) PRs are split up into sub-PRs without needing to actually split them up and stack them yourself -> Automatically done with AI -> Features a CLI you can use in place of `git push` where you can control how many sub-PRs it should split them into, with a guiding message for how they should be split up (otherwise it will decide on its own) -> When you want to split and merge a PR lower in the stack, you can do so 'just-in-time' 2) Brought all context (comments, diffs, file-tree) into one IDE-like UI -> When you ask the AI anything, it pulls up a view of all of the relevant code sections that would be helpful to have in view while reading its response -> Unlike Github, which has separate tabs for discussion and file changes, everything is consolidated into one view -> You can press and highlight comments/code to automatically include them in the chat context, just like Cursor 3) Cursor-like chat pane to use the AI as a review partner as you go through it -> Ask dumb questions - nobody will know -> Use voice mode to speak your thoughts/comments to the AI as they come (like a live review session with a colleague) -> It'll auto-draft comments for you based on your discussion with it -> Suggestion bubbles for one-click common questions to code or comments (e.g. What are some counter-arguments to this comment? What are some potential concerns with this piece of code? Can you explain this part to me? etc.) Simple to get started - just follow the README instructions and ping here or create an issue if you have any problems. When you enter the dashboard, you'll see all the PRs you're involved in. You can also paste in a public Github PR URL to try it out. Or, like I said, use the CLI to create a draft PR of your working branch with split sub PRs and view it in LightLayer. We vibe-coded a good chunk of this tbh, so it's not perfect and not everything's finished (see README for incomplete features) - feel free to contribute :) Hope this helps you get through your code reviews quicker!!

Does the same job

all alternatives →

More ai this month

the category →
  • I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.

    AI · 17d ago · simedw.com

  • Astute585

    Automate your B2B brand going viral, with new media creators

    AI · 18d ago · company-app.joinastute.com

  • Grok Bot547

    AI teammates that you can give real work to

    AI · 25d ago · x.ai

  • Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…

    AI · 26d ago · cactuscompute.com

  • Make your software self-driving

    AI · 30d ago · coldtea.ai

  • Soloop472

    Approval-first Agent OS for solo founders

    AI · 30d ago · soloop.io

Launched alongside, August 2025

the whole month →
  • Trace1,556

    Workflow Automations for the Human 👾 AI Workforce

    AI · 2025 · trace.so

  • IS

    I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/

    Work · 2025 · benholmen.com

  • Job boards are dead. Your network is alive

    AI · 2025 · contra.com

  • KT

    Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…

    Dev tools · 2025 · github.com

  • IW

    I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!

    Life & fun · 2025 · visualrambling.space

  • TC

    For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html

    Dev tools · 2025 · sky.dlazaro.ca