by kortix-ai · Agent Tool · ★ 65
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/kortix-ai/agent-computer-use
cargo install --git https://github.com/kortix-ai/agent-computer-use --path cliTaken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 65 |
| Forks | 16 |
| Language | Rust |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 72/100 |
| Open Issues | 5 |
| Last Updated | 2026-10-02 |
| Created | 2026-03-30 |
| Platforms | claude-code, cli, rust |
| Est. Tokens | ~25k |
agent-computer-use [!WARNING] This project is no longer maintained. We recommend Cua and its Cua Driver instead. One CLI. Any desktop app. Like a human would. Click buttons, type text, read screens on macOS / Linux / Windows / Electron — no vision tokens, no screenshots, deterministic. For AI agents (Claude, Cursor, Codex, local models) and humans alike. Why agent-cu O
These tools work well together with agent-computer-use for enhanced workflows:
Looking for a agent-computer-use alternative? If you're comparing agent-computer-use with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app
Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ to
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Personal Assistant Wizard for Claude Code — npx pawmode
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGr
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron C
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: