by LiangNiang · Agent Tool · ★ 110
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/LiangNiang/OpenMantis.gitTaken from the project's README on GitHub.
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.
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 | 110 |
| Forks | 9 |
| Language | TypeScript |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 59/100 |
| Last Updated | 2026-05-16 |
| Created | 2026-04-11 |
| Platforms | browser, node |
| Est. Tokens | ~584k |
OpenMantis 中文 | English 基于 Bun + Vercel AI SDK 构建的个人 Agent 聊天框架——一次部署，自己用。 将多个 LLM 供应商连接到多个通讯平台，配合可组合的工具、定时任务、浏览器自动化、记忆系统、定时任务等能力 —— 一次部署，全部搞定。 [!NOTE] OpenMantis 是为个人单用户使用而设计的：假设只有一位用户（项目所有者本人）通过飞书/企业微信/QQ 等渠道与 Agent 对话。因此不内置多租户、用户隔离或权限管理，记忆、路由、调度等均不按用户区分。 特性 多 LLM 供应商 — OpenAI、Anthropic、字节跳动/豆包、DeepSeek、小米 MiMo，以及任意 OpenAI 兼容端点。支持按通道或按会话切换 LLM 供应商。 多平台 —...
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: