by jim-schwoebel · Agent Tool · ★ 2.0k
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 | 1,983 |
| Forks | 690 |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 56/100 |
| Open Issues | 246 |
| Last Updated | 2026-03-28 |
| Created | 2025-01-03 |
| Platforms | cli |
| Est. Tokens | ~671k |
🤖 Awesome AI Agents: Tools, Resources, and Projects Welcome to the Ultimate Hub for AI Agents, your one-stop destination for all things related to AI-driven agents. Whether you're a researcher, developer, or enthusiast, this repository brings together the most advanced tools, resources, and inspiring projects in the world of AI agents.
These tools work well together with awesome_ai_agents for enhanced workflows:
Looking for a awesome_ai_agents alternative? If you're comparing awesome_ai_agents 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.
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
Private AI agents for highly regulated teams, and for anyone who wants AI on their own computer. Open-source P
Multi-agent systems, memory, planning, reasoning loops
🏆 Ranked list of 187 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored wee
A set of tools that gives agents powerful capabilities.
AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate
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: