Agent-desktop – Native desktop automation CLI for AI agents
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…
Agent-desktop – Native desktop automation CLI for AI agents launched on May 2, 2026 with 99 votes, #319 of 20,539 launches that month and more than 95% of that year's launches.
In plain words
Agent-desktop is a native desktop automation CLI tool for AI agents that uses structured accessibility APIs instead of screenshot-based pixel clicking. It works with macOS Accessibility API, Windows UI Automation, and Linux AT-SPI to give AI models direct access to UI element information, making automation faster, cheaper in tokens, and more reliable than traditional coordinate-prediction methods. The tool is designed for developers building computer-use agents who need a more robust alternative to visual-based interaction methods.
written from the facts on this page · September 2026
From the sources
Agent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions stay safe to retry, instead of guessing from pixels. - lahfir/agent-desktop
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
ComputerX2025 · computerx.ai · ▲560Introducing the first-ever desktop AI agent that gets your computer tasks done for you. Like having your own AI operator that seamlessly integrates with every app on your computer!
Atomic2023 · github.com · ▲140Hey HN, I’ve been building Atom (https://github.com/rush86999/atom), an open-source, self-hosted AI automation platform. I built this because while tools like OpenClaw are excellent for one-off scripts and personal tasks, I found them difficult to use for complex business workflows (e.g., managing invoices or SaaS ops). The main issue was State Blindness: the agent would fire a command and assume it worked, without "seeing" if the UI or state actually updated. I just shipped a new architecture to solve this called Canvas AI Accessibility. The Technical Concept: Instead of…
I spent 3 months making desktop automation stop lying to AI agentsAug 2026 · github.com · ▲6That's a bold claim. But I genuinely feel like I might have actually solved computer use (demo: https://x.com/mdlahfir/status/2088109763783700827?s=20) For context, I've been building agent-desktop (Inspired by agent-browser by Vercel Labs), an automation CLI for desktop apps. It's like Playwright but for desktops, not just native, but for Chromium apps as well. Trust me, yes, Chromium apps whose accessibility tree is dense. MacOS is GA; I'm almost close to launching for Windows and Linux! So, how did I solve it? Basically interoperability. The biggest issue with…
Libretto – Making AI browser automations deterministicApr 2026 · github.com · ▲134Libretto (https://libretto.sh) is a Skill+CLI that makes it easy for your coding agent to generate deterministic browser automations and debug existing ones. Key shift is going from “give an agent a prompt at runtime and hope it figures things out” to: “Use coding agents to generate real scripts you can inspect, run, and debug”. Here’s a demo: https://www.youtube.com/watch?v=0cDpIntmHAM. Docs start at https://libretto.sh/docs/get-started/introduction. We spent a year building and maintaining browser automations for EHR and payer portal…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 19d ago · stillwet.art
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com