AgentOne Desktop
Automate boring work. Extensible and free desktop AI agent.
What it does
Automate any boring task with AgentOne. With over 19,000 built-in extensions, it's easy to integrate nearly any app or website. Connect Gmail, GitHub, Canva, Blender, Chrome, Discord, and more. AgentOne can do work while you do something else. It runs as a desktop app in the background, similar to Claude Cowork. But unlike Claude Cowork, it's free! Plus, you can use any OpenAI-compatible provider (or Claude) to choose from over 8000 AI models.
AgentOne can do the work while you do something else. Connects with 22,000+ websites and services out of the box, supports 10,000+ models, and more.
AgentOne isn't a chatbot, it's an AI agent. Tell it what you need done and it does it by itself, just like a human would. It works across 22,000 + apps, services, and websites , solving complex tasks that require multiple steps. It keeps going autonomously, no human intervention required, until the job is finished. Most AI tools are either too simple (like a chatbot) or too specialized (only work for a specific task). AgentOne unifies all yours tools and does the work, from first step to finished result. Everyday productivity, from email to expenses, is handled end-to-end. AgentOne can understand the context in your connected apps, draft thoughtful responses, organize follow-ups, and take…from agent-one.dev
Does the same job
all alternatives →
- AEAgent.exe, a cross-platform app to let 3.5 Sonnet control your machine2024 · github.com · ▲406
- 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 goes Open Source!19d ago · agent-one.dev · ▲3We've fully open-sourced the desktop app for AgentOne
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
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