AI · March 11, 2026
Skales - AI Desktop Agent for Win & Mac
Local AI that acts. Not chats. Installs in 30 seconds. 🦎
What it does
The Desktop Buddy sits persistently in the corner of your screen as a small animated gecko. Click it once, describe what you need, and it handles it - without you switching windows, opening new tabs, or navigating menus. Skales is a local first AI desktop agent for Windows and macOS. It manages emails, calendar, browser tasks and research autonomously. Asks before anything destructive. Works with any LLM: OpenRouter, Anthropic, Gemini or fully offline via Ollama. No Docker - No terminal.
Does the same job
all alternatives →- SISkales – I built a desktop AI agent a 6-year-old can useApr 2026 · github.com · ▲12
Solo dev from Vienna. Skales is a local-first AI desktop agent for Windows, macOS, and Linux. v9.0.0 just shipped with Agent Skills (SKILL.md import from Claude Code, Codex, Copilot), autonomous coding (Codework), multi-agent teams (Organization), Computer Use, and 15+ providers including Ollama offline. No Docker, no terminal. Download, install, done. My 6-year-old built a Snake game with it. BSL-1.1, free for personal use. DevKit: https://github.com/skalesapp/devkit
- ADAgent-desktop – Native desktop automation CLI for AI agentsMay 2026 · github.com · ▲99
I've been building computer-use tools for a while, and I quietly launched this about a month ago (122 Stars on GH). I figured it was worth sharing here. Over the last few months, a lot of computer-use agents have come out: Codex, Claude Code, CUA, and others. Most of them seem to work roughly like this: 1. Take a screenshot 2. Have the model predict pixel coordinates 3. Click x,y 4. Take another screenshot 5. Repeat That works, but it's slow, expensive in tokens, and fragile. If the UI shifts a few pixels, things break. And the model still doesn't know what any element actually is. But the…
AgentOne DesktopAug 2026 · agent-one.dev · ▲78Automate boring work. Extensible and free desktop AI agent.
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
Astuteâ–²585Automate 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, March 2026
the whole month →- Lightfield▲891
AI-native CRM that builds itself and does work for you
AI · Mar 2026 · lightfield.app
Claude Import Memoryâ–²725Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
