{"slug": "show-hn-quill-desktop-lightweight-ai-harness-no-electron-webkit-native-gui", "title": "Show HN: Quill Desktop; Lightweight AI harness, no electron/WebKit native GUI", "summary": "An independent developer released Quill Desktop, a lightweight AI agent harness built on Zed's GPUI native rendering framework instead of Electron, claiming a memory footprint under 70MB of RAM and a Rust core. Quill Desktop ships as portable executables for Windows (x64 and Arm64), macOS (Arm64, unsigned), and Linux (x64 and Arm64), supports every LLM provider, and uses the Apache 2.0-licensed goose agent harness from the Agentic AI Foundation. The project carries an unconventional non-commercial license with a clause asking anyone training AI models on the code to compensate the author.", "body_md": "- Native Desktop UI APIs (No Electron)\n- Minimal resource footprint, under 70mb of ram\n- Extremely fast Rust core\n- Supports every LLM provider, no lock down\n\nDownload from Github releases and run. Uses portable executables so no install is required.\n\nTo uninstall delete the executable and the config under `$HOME/.config/quill`.\n\n| Platform | Link | \n|---|---|\n| Windows | [quill.exe](https://github.com/alshlabs/quill/releases/latest/download/quill-windows-amd64.zip) | \n| Windows Arm64 | [quill.exe](https://github.com/alshlabs/quill/releases/latest/download/quill-windows-arm64.zip) | \n| MacOS | [Quill.app](https://github.com/alshlabs/quill/releases/latest/download/quill-macos-arm64.tar.gz) | \n| Linux | [Quill.AppImage](https://github.com/alshlabs/quill/releases/latest/download/quill-linux-amd64.tar.gz) | \n| Linux Arm64 | [Quill.AppImage](https://github.com/alshlabs/quill/releases/latest/download/quill-linux-arm64.tar.gz) | \n\n*Note: the MacOS build is unsigned because I am not spending US$99/year for an Apple developer account*\n\n## recording-2026-10-25.mp4\n\nQuill uses the work done by the [Zed editor](https://zed.dev/), utilizing their cross platform [gpui-kit](https://crates.io/crates/gpui-kit).\n\nSimply put, gpui leverages native APIs (Metal, Vulkan and DirectX) to draw the UI. You can think of it as using a game engine to render a UI, except it only renders frames when things are moving, ensuring power usage / battery life is unaffected.\n\nIt renders frames at your screen's refresh rate (e.g. 144fps) so the experience is buttery smooth.\n\nAll the current desktop harnesses are built on top of Electron (basically a full-fat dedicated clone of Chrome running only one website).\n\nConventionally, this is done to minimize the friction associated with cross-platform application development and be competitive in feature delivery. Essentially, sacrifice a little user experience in exchange for the ability to move faster than competitors.\n\nIn my view, harnesses have reached a level of maturity now where the features we expect from them are well enough defined. In addition, there is no longer the pressure to be a first mover in the Desktop Agent Harness space.\n\nI think we can now afford a high quality tool that respects your computers resources while also supporting all model providers.\n\nAdditionally, the technology powering Quill means that adding features is not so hard that it justifies an Electron build.\n\n- UI Icons from [Codicons](https://github.com/microsoft/vscode-codicons) by Microsoft ([CC BY 4.0](https://github.com/microsoft/vscode-codicons/blob/main/LICENSE) ).\n- UI Icons from [Font Awesome Free](https://github.com/FortAwesome/Font-Awesome) by Fonticons, Inc. ([CC BY 4.0](https://fontawesome.com/license/free) ).\n- UI Icons from [Bootstrap Icons](https://github.com/twbs/icons) by The Bootstrap Authors ([MIT](https://github.com/twbs/icons/blob/main/LICENSE) ).\n- UI framework [GPUI](https://github.com/zed-industries/zed/tree/main/crates/gpui) from the[Zed](https://zed.dev) editor by Zed Industries ([Apache 2.0](https://github.com/zed-industries/zed/blob/main/crates/gpui/LICENSE-APACHE) ).\n- Agent harness [goose](https://github.com/aaif-goose/goose) by the[Agentic AI Foundation](https://aaif.io/) ([Apache 2.0](https://github.com/aaif-goose/goose/blob/main/LICENSE) ).\n\nI have gone with an unconventional non-commercial license that has an clause for AI training. I'm not anti-AI at all (obviously) and have no expectations that my license will be respected.\n\nThe intention is that - should this code be included in training data - throw a little something my way for the training data.\n\nIf you're doing research or working on an open weight model, feel free to include this in your training data.\n\nThis is a weekend project of mine. If you genuinely enjoy it and want to see more, please consider starring the repo and supporting my efforts.", "url": "https://wpnews.pro/news/show-hn-quill-desktop-lightweight-ai-harness-no-electron-webkit-native-gui", "canonical_source": "https://github.com/alshlabs/quill", "published_at": "2026-10-26 06:18:12+00:00", "updated_at": "2026-10-26 06:44:01.461603+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "artificial-intelligence"], "entities": ["Quill Desktop", "Zed", "GPUI", "goose", "Agentic AI Foundation", "Microsoft", "Font Awesome", "Bootstrap Icons"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-quill-desktop-lightweight-ai-harness-no-electron-webkit-native-gui", "markdown": "https://wpnews.pro/news/show-hn-quill-desktop-lightweight-ai-harness-no-electron-webkit-native-gui.md", "text": "https://wpnews.pro/news/show-hn-quill-desktop-lightweight-ai-harness-no-electron-webkit-native-gui.txt", "jsonld": "https://wpnews.pro/news/show-hn-quill-desktop-lightweight-ai-harness-no-electron-webkit-native-gui.jsonld"}}