agent-browser
A fast browser-automation CLI built for AI agents.
Vercel Agent Desktop ist ein Open-Source-Projekt aus der Kategorie KI-Agenten von vercel-labs (vercel-labs/agent-desktop auf GitHub). Es hat 24.053 Sterne auf GitHub und 1.789 Forks, wird unter der Lizenz Apache-2.0 veröffentlicht und wurde zuletzt am 15. November 2026 auf GitHub aktualisiert.
Computer use for AI agents through the OS accessibility tree — no screenshots, no pixel matching
Install globally with npm, or with Homebrew on macOS and Linux.
Confirm the platform, permissions and supported surfaces.
Walk through the accessibility grant for your OS.
The agent reads the UI tree, acts on refs, and re-reads to verify.
The agent reads the accessibility tree as JSON, with a ref for every actionable element.
Act on a ref, read the UI again, check the result, repeat.
macOS, Windows and Linux, with native binaries for x64 and ARM64.
Use it from the command line or embed it through the C library.
It is pure computer-use plumbing — the model and the loop live in your agent.
A guided walkthrough for the macOS accessibility grant and other permissions.
Install globally with npm.
npm install -g agent-desktopConfirm platform, permissions and supported surfaces.
agent-desktop statusWalk through the permission setup for your OS.
agent-desktop permissions --guideTwo more from the same shelf: agent-browser — A fast browser-automation CLI built for AI agents, and openclaw — A personal AI that really does things. Browse every AI Agents tool in the catalogue to compare the category. Before running a model locally, check how much VRAM you need for local LLMs — model size has to match your hardware.
A Vercel Labs CLI and C library that gives AI agents computer use on macOS, Windows and Linux through the OS accessibility tree.
No — it has no model inside. The loop lives in your agent; agent-desktop only reads the UI and performs the clicks and typing.
It reads the accessibility tree as structured JSON with refs, so the agent acts on real elements instead of guessing pixels.
Yes, Apache-2.0 licensed.
Snapshots, clipboard reads and debug artifacts can contain private desktop content — keep them out of public logs and uploads.
A fast browser-automation CLI built for AI agents.
A personal AI that really does things — on any OS, with your data staying yours.
Chrome DevTools for coding agents: an MCP server that lets agents debug and inspect real Chrome
Reliable computer use for any agent: drive real apps through accessibility trees, not pixel guessing.
Benchmark computer-use agents on long, real-world desktop tasks.
Mobile-Agent — multimodal GUI agents that operate phones and PCs from screenshots and instructions.
Die anderen Projekte der Kategorie KI-Agenten mit den meisten Sternen im LibreAI-Katalog — die realistische Auswahl, falls Vercel Agent Desktop nicht das Richtige ist.
A personal AI that really does things — on any OS, with your data staying yours.
Matt Pocock's engineering skills for coding agents — grill the spec first, then build it right, MIT
An agentic skills framework & software development methodology that works.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
The agent that grows with you — a Python framework for adaptive AI agents.
Verwandte Projekte der Kategorie KI-Agenten im Katalog, die Vercel Agent Desktop bei den Sternen am nächsten stehen — zum Weiterstöbern auf beiden Seiten.
The official Python SDK for Model Context Protocol servers and clients.
Google’s official Agent Skills for Google Cloud, Gemini and Workspace — one command installs them into your coding agent, Apache-2.0
Stateful AI agents with memory that learns and improves.
Jev Ultrafast — the fastest browser agent from browser-use: one decision-model request per action cycle drives a real browser, MIT
Autonomous AI agents for penetration testing — self-hosted, multi-agent, with a full web UI
One RAG framework for everything — including multimodal documents.
Kostenlos und offen — hol dir den Quellcode, gib dem Repository einen Stern und leg los.