by jorge-menjivar · Agent Tool · ★ 252
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 | 252 |
| Forks | 76 |
| Language | TypeScript |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 56/100 |
| Open Issues | 26 |
| Last Updated | 2025-02-25 |
| Created | 2023-04-17 |
| Platforms | claude-code, node |
| Est. Tokens | ~447k |
🎉 Welcome to unsaged unsaged is a cutting-edge chat kit engineered for seamless interaction with AI models. It allows you to easily have conversations with different AI models from a variety of providers, all in one place. It also allows you to manage multiple users and conversations, and synchronize them across different devices.
Looking for a unsaged alternative? If you're comparing unsaged 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.
Command-line interface for ChatGPT, Claude and Bard
Ruby Implementation of Nano Bots: small, AI-powered bots that can be easily shared as a single file, designed
Personal and autonomous AI coding agent. Writes and edits code automatically. No third-party servers, token li
Why juggle 6 AI tools? AI Gate does it. No API keys. A single gateway to ChatGPT, Gemini, Claude, Grok, Perple
Modern AI chatbot supporting multiple LLMs. Switch between Gemini, Mistral, Llama, Claude and ChatGPT.
A Reactive CLI that generates commit messages for Git and Jujutsu with Ollama, ChatGPT, Gemini, Claude, Mistra
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: