by 777genius · Agent Tool · ★ 181
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Flagged: sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
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 | 181 |
| Forks | 18 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 72/100 |
| Open Issues | 3 |
| Last Updated | 2026-05-26 |
| Created | 2025-09-14 |
| Platforms | browser, claude-code, cli, python |
| Est. Tokens | ~1467k |
OS AI Computer Use The most capable open-source desktop automation agent — 75.0% on OSWorld, surpassing human performance. Supports OpenAI GPT-5.4 and Anthropic Claude. Cross-platform. Production-ready. Coming soon: MCP-first architecture with sandboxed code execution, plug & play model backends, and isolated environments — in active development.
Looking for a os-ai-computer-use alternative? If you're comparing os-ai-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.
State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key
AI cursor assistant for macOS, Windows, Linux. Hold a hotkey, ask a question about what's on your screen, get
Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, M
Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.
Your own digital life form — local AI companion with persistent memory, IDE workspace, MCP support, and 30+ to
The AI cursor companion. Hold a key, ask a question, get an answer about whatever your cursor is pointing at.
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: