by suitedaces · Agent Tool · ★ 710
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
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 | 710 |
| Forks | 89 |
| Language | Rust |
| Category | Agent Tool |
| Quality Score | 63/100 |
| Open Issues | 10 |
| Last Updated | 2026-08-13 |
| Created | 2024-10-25 |
| Platforms | browser, claude-code, rust |
| Est. Tokens | ~22k |
Taskhomie (Computer Use AI Agent) Local AI agent that controls your computer. Give it natural language instructions and watch it take screenshots, move your mouse, click, type, and run terminal commands. Built with Tauri, React, and Rust. Demo https://github.com/user-attachments/assets/8edd92a7-7d3e-472a-9e48-3b561f0257d6 Here, I used it to autonomously read and reply to tweets, lol.
Looking for a computer-agent alternative? If you're comparing computer-agent 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.
A desktop companion app for AI coding tools. Browse Claude Code chat history, manage configurations, commands,
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app
📜 An MCP server for conversation history search and retrieval in Claude Code
A mcp server to allow LLMS gain context about shadcn ui component structure,usage and installation,compaitable
AI computer use powered by open source LLMs and E2B Desktop Sandbox
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: