Zuni (YC S24) – AI Copilot for the Browser
Hi HN, I'm Will, and along with my co-founder George, we've built Zuni (https://zuni.app) - a browser extension that adds contextual AI capabilities to your browser. It understands what you're reading and working on, whether that's email, research, or anything else in your tabs. We started out building a full email client with AI built in (you might have seen that version showcased in YC’s AI Design Review - https://www.youtube.com/watch?v=DBhSfROq3wU&t=1601s), but learned that people don't actually want to leave their existing tools - they just want them to work…
In plain words
Zuni is a browser extension that adds AI capabilities to existing tools like Gmail and email clients. The extension understands the content users are reading and working with across their tabs, offering contextual assistance without requiring users to switch platforms. It analyzes emails to identify action items and provide suggestions, integrating AI features directly into familiar applications rather than replacing them with new tools.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I'm Will, and along with my co-founder George, we've built Zuni (https://zuni.app) - a browser extension that adds contextual AI capabilities to your browser. It understands what you're reading and working on, whether that's email, research, or anything else in your tabs. We started out building a full email client with AI built in (you might have seen that version showcased in YC’s AI Design Review - https://www.youtube.com/watch?v=DBhSfROq3wU&t=1601s), but learned that people don't actually want to leave their existing tools - they just want them to work better. Gmail might be frustrating, but it has years of features people rely on. So we pivoted to enhance the tools people already use, rather than replace them entirely. Some specific things Zuni does today: - Analyzes emails as you read them in Gmail, identifying action items and suggesting possible responses - Lets you discuss how to handle tricky emails, almost like having a thought partner - Maintains context across your browsing session so you can ask follow-up questions naturally - Runs locally first for speed and privacy - Doesn't store chats, emails or anything sensitive in the cloud We're still early and focusing on getting the core experience right before adding more integrations. The goal is to make AI actually useful in your daily work, rather than just another "AI feature" checkbox. Would genuinely love feedback from the HN community - what would make this truly useful for your workflow? What are we missing? Happy to answer any questions about the technical implementation too.
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
