Auto-fix your GitHub PR issues with Proton for FREE
Hey HN! We just launched Proton, a GitHub app that listens to PR review comments and suggests code changes to address them. It creates a new PR based on top of your working branch, so you can simply review and merge. How is it different from other AI code review tools? Others focus on pointing out issues, whereas Proton focuses on addressing them. Although some of them can also suggest fixes, they tend to only work on nearby lines or within a single file. But real-world feedback often involves cross-file changes like “Let’s extract this to a separate component”, or “We should follow the same…
In plain words
Proton is a free GitHub app that automatically generates code fixes in response to pull request review comments. When reviewers suggest changes, Proton analyzes the feedback and creates a new pull request with proposed modifications that developers can review and merge. Unlike similar tools that flag issues or suggest fixes within single files, Proton understands full repository context to handle cross-file changes and complex refactoring requests that reflect real-world code review feedback.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! We just launched Proton, a GitHub app that listens to PR review comments and suggests code changes to address them. It creates a new PR based on top of your working branch, so you can simply review and merge. How is it different from other AI code review tools? Others focus on pointing out issues, whereas Proton focuses on addressing them. Although some of them can also suggest fixes, they tend to only work on nearby lines or within a single file. But real-world feedback often involves cross-file changes like “Let’s extract this to a separate component”, or “We should follow the same pattern of doing things in file X, Y and Z”. Proton has full repo context, so it can handle these kinds of feedback. Want to see it in action? Here’s a short demo: https://youtu.be/zDEfw-R2jWc, and there’s the PR shown in the demo video: https://github.com/proton-codes/demos/pull/2 It’s free, takes two clicks to install, and works out of the box. Here’s the install link: https://github.com/apps/proton-app We'd love to get some early users and hear your thoughts — reply here or email us at [[email protected]](mailto:[email protected]) Cheers!
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
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
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
Launched alongside, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
