100% native Swift harness (NOT Electron)
hi everybody, I’ve been working on this harness that is all native Swift for macOS. It’s fully featured with every feature i could find in cline, codex, and claude code. There is all swift command line too It’s taking me a long, long time, a few months to build this, and it’s fully open source Apache 2 licensed. Hoping people fork this and make many branches I’m looking for people who want to work on something that has much lower memory usage and much more potential to be just more efficient. Every other single harness has is written in using electron, so this harness is really unique in…
In plain words
Quill Cowork is a native Swift coding agent for macOS that combines project-aware chat, local tools, Git workflows, and a workspace terminal in a single desktop application. Built entirely in Swift rather than Electron, it offers lower memory usage and includes features like Computer Use, automations, plugins, and automatic updates with rollback capability. The open-source Apache 2 licensed tool is designed for real project work and supports multiple AI models through TrustedRouter integration, with an enterprise version available for confidential work.
written from the facts on this page · September 2026
From the sources
Native macOS coding agent and AI coworker with local tools, Computer Use, worktrees, automations, plugins, and verified auto-updates. - Lore-Hex/QuillCode
A 100% Swift coding agent and AI coworker for real project work. Quill Cowork combines project-aware chat, local tools, Git workflows, Computer Use, automations, plugins, and a full workspace terminal in one SwiftUI desktop app. The desktop app and agent runtime are written entirely in Swift, with no Electron or web-app shell. Bounded background work, persistent local state, and a verified updater with automatic rollback are built into that Swift architecture. Confidential Cowork by TrustedRouter is the locked enterprise distribution of the same native Swift app. It defaults to trustedrouter/confidential , requires Confidential-tier providers for every model-backed request, supports US or…from github.com
In the maker’s words, at launch
hi everybody, I’ve been working on this harness that is all native Swift for macOS. It’s fully featured with every feature i could find in cline, codex, and claude code. There is all swift command line too It’s taking me a long, long time, a few months to build this, and it’s fully open source Apache 2 licensed. Hoping people fork this and make many branches I’m looking for people who want to work on something that has much lower memory usage and much more potential to be just more efficient. Every other single harness has is written in using electron, so this harness is really unique in this way. It’s connected to trusted router so that it has end-to-end encryption confidential mode as well as access to hundreds of models, any model in the world. It works great with Deepseek. it’s great for swift development ios development. and for people who love Linux, I also made a compatibility layer that lets you compile SwiftUI into native Linux so that you either can new or QT actually so that you can just compile all the code directly and make it run on Linux
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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