by christopherkarani · Agent Tool · ★ 588
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 588 |
| Forks | 43 |
| Language | Swift |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 70/100 |
| Open Issues | 6 |
| Last Updated | 2026-11-08 |
| Created | 2025-12-12 |
| Est. Tokens | ~17k |
Swarm Build production AI agents in Swift. Swarm is a Swift-native agent runtime for type-safe tools, on-device Apple Foundation Models, composable workflows, memory, guardrails, and streaming. Build for iOS, macOS, and Linux with the same agent loop. Get started · Browse examples · ⭐ Star on GitHub The example uses Apple Foundation Models on supported devices.
These tools work well together with Swarm for enhanced workflows:
Looking for a Swarm alternative? If you're comparing Swarm 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.
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,
An introduction to the world of AI Agents
Local-first AI coding quotas and ship status, on your menu bar, iPhone, Watch and an ESP32 desk display.
Give git-like & traceable memory to OpenClaw and any coding agents. By https://memov.ai/ aka Entire CLI for ev
A set of tools that gives agents powerful capabilities.
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: