Embra – A fast, Chat-GPT like assistant for your Mac. App integrated
Hey HN! We're building Embra, an always-one-second away GPT assistant that integrates into your OS, apps, and workflows. Everyone is talking about the "context problem" as it relates to GPT, in that the answers you get out are only as good as the information you put in. And, well, a lot of users don't want to type in a bunch of text. With Embra, you can pick and choose which context to feed the AI within the interface itself. And that context can be anywhere on your computer -- text in a PDF document, any tabs within Chrome, etc. One of the primary use cases is improved coding, debugging,…
In plain words
Embra is a Mac application that brings a GPT-like assistant directly into your operating system and applications. It addresses the context problem by letting users select and feed specific information from anywhere on their computer—PDFs, browser tabs, documents—into the AI without manual typing. The tool is designed primarily for developers who need coding help, debugging assistance, and code generation multiple times daily, integrating seamlessly into existing workflows.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! We're building Embra, an always-one-second away GPT assistant that integrates into your OS, apps, and workflows. Everyone is talking about the "context problem" as it relates to GPT, in that the answers you get out are only as good as the information you put in. And, well, a lot of users don't want to type in a bunch of text. With Embra, you can pick and choose which context to feed the AI within the interface itself. And that context can be anywhere on your computer -- text in a PDF document, any tabs within Chrome, etc. One of the primary use cases is improved coding, debugging, and software workflows. We especially want to gather feedback in this direction, as engineers engage in Q&A workflows and code creation 15+ times a day. Really awesome. :) Just launching our closed beta signup page today, and rolling out first invites to broader community. https://embra.app/ And the twitter launch thread: https://twitter.com/zachtratar/status/1623015294569713665 We're also looking for the following feedback: 1) What do you think about OS-level integration vs VSCode extension? Both have filesystem access, but do you perceive them differently security or capability wise? 2) What do you use ChatGPT for today primarily, and would desktop access improve those workflows meaningfully? 3) What context would you like to pull into the AI, as an engineer? Thanks! And feel free to poke at the idea. We've been around the block and welcome the classic, ruthless HN constructive criticism.
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
