an AI copilot for Next.js developers
Hey HN! I'm Andrew, one of the creators of Glass, a copilot for Next.js and React developers. Glass appears as a chat bar on your locally running Next.js server, and you can tell it to make changes like "build a dashboard" or "add a login button". Glass makes the changes to your sourcecode in real-time. Our goal with Glass is to automate away the easy but slow parts of frontend development, like locating the right file to edit, writing tailwind by trial-and-error, and copy-pasting boilerplate from Claude and other tools. We want to let you do all the tedious work entirely from your browser.…
In plain words
Glass is an AI copilot for Next.js and React developers that runs as a chat interface on local development servers. Users can request changes like "build a dashboard" or "add a login button," and Glass modifies source code in real-time. It automates tedious frontend tasks including locating files to edit, writing Tailwind CSS, and generating boilerplate code. Built using a VS Code extension and SWC plugin, Glass enables developers to accomplish repetitive work directly through their browser.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! I'm Andrew, one of the creators of Glass, a copilot for Next.js and React developers. Glass appears as a chat bar on your locally running Next.js server, and you can tell it to make changes like "build a dashboard" or "add a login button". Glass makes the changes to your sourcecode in real-time. Our goal with Glass is to automate away the easy but slow parts of frontend development, like locating the right file to edit, writing tailwind by trial-and-error, and copy-pasting boilerplate from Claude and other tools. We want to let you do all the tedious work entirely from your browser. We built Glass using a VS Code extension that handles communications with an LLM (4o) and reads/writes to your codebase. We also built an SWC plugin to map where clicked in your browser to a location in your sourcecode - this was interesting because we determine which component you clicked on and where its instance is located in your codebase, so we did a lot of interesting prop injections to make this work. Lastly, we render our UI directly on your project using a React Provider - this was mainly to avoid building yet another interface you have to install (although it has its downsides, like disappearing when there's an error). We're super excited to build the tool out more, but we wanted to get a sense of what you think! The jump-to-code and hover-component features have been the most helpful for me developing projects in general, and the AI part can help with easier tasks like rearranging a component and doing annoying tailwind work. You can install Glass on your Next.js project here: https://useglass.ai/. Everything is free for now, and we'd love to hear your feedback.
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 · 27d ago · cactuscompute.com
Launched alongside, August 2024
the whole month →
- IY
Life & fun · 2024 · ytch.xyz
- IA
Hey there HN! We’re Joe and Stopa, and today we’re open sourcing InstantDB, a client-side database that makes it easy to build real-time and collaborative apps like Notion and Figma. Building modern apps these days involves a lot of schleps. For a basic CRUD app you need to spin up servers, wire up endpoints, integrate auth, add permissions, and then marshal data from the backend to the frontend and back again. If you want to deliver a buttery smooth user experience, you’ll need to add optimistic updates and rollbacks. We do these steps over and over for every feature we build, which can…
Dev tools · 2024 · github.com