AI agent tools for desktop automation
Short answer: Our top pick for desktop automation: Cua, with the highest AgentPick Score (87/100) among tools tagged "desktop-automation". Runners-up: GenericAgent (74) and open-codex-computer-use (70). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | Cua | Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation. | 87/100 | ★ 30k | MIT | 15 Oct 2026 |
| #2 | GenericAgent | Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption | 74/100 | ★ 14k | MIT | 14 Oct 2026 |
| #3 | open-codex-computer-use | 👾 Open Computer Use – Open-Source Alternative to Codex Computer Use | 70/100 | ★ 2.4k | MIT | 14 Oct 2026 |
| #4 | lcu | Codex computer use, decoupled from the app, for usage inside any harness. | 68/100 | ★ 1.1k | MIT | 14 Oct 2026 |
| #5 | agent-desktop | 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 tree… | 66/100 | ★ 1.8k | Apache-2.0 | 14 Oct 2026 |
| #6 | solidworks-automation-skill | Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation. | 66/100 | ★ 1.2k | MIT | 12 Oct 2026 |
| #7 | clawdcursor | Local MCP server that gives any AI agent safe desktop control on Windows, macOS and Linux. Reads the screen as text and structure (accessibility + OCR… | 64/100 | ★ 405 | MIT | 14 Oct 2026 |
| #8 | RPA | Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control… | 59/100 | ★ 2.1k | See repo | 13 Oct 2026 |
| #9 | Interceptor | Browser automation and computer use for AI agents. One CLI and MCP server for your signed-in browser, native macOS apps, and real iPhones. | 59/100 | ★ 538 | See repo | 14 Oct 2026 |
| #10 | nuphus-mcp | Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio).… | 59/100 | ★ 325 | MIT | 13 Oct 2026 |
| #11 | lnwjud | lnwjud — local AI-agent runtime & MCP gateway | 57/100 | ★ 205 | MIT | 14 Oct 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.