by AQBot-Desktop · Codex Skill · ★ 911
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AQBot safe to install? View the security audit →
简体中文 العربية 运行截图
Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 911 |
| Forks | 96 |
| Language | TypeScript |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 63.6401815274292/100 |
| Open Issues | 5 |
| Last Updated | 2026-10-09 |
| Created | 2026-03-24 |
| Platforms | cli, node |
| Est. Tokens | ~15k |
These tools work well together with AQBot for enhanced workflows:
Looking for a AQBot alternative? If you're comparing AQBot with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Unified LLM gateway with weighted load balancing, observability & cost tracking. 统一的 LLM 网关，提供权重负载均衡、可观测性与费用追踪
Run your own organization of agents
Run your own organization of agents
Tactical AI Workspace Monitor & EDR
Agentic Engineering that actually scales. Run Claude Code, Codex, Gemini and any other CLI Agents in parallel
An app to monitor the (Codex) situation
Explore other popular codex skill tools:
AQBot is ☁️ 轻量级高性能跨平台AI对话 + AI Agent + AI网关桌面客户端 | Lightweight, high-performance cross-platform AI dialogue + AI Agent + AI gateway desktop client. It is categorized as a Codex Skill with 911 GitHub stars.
AQBot is primarily written in TypeScript. It covers topics such as ai, ai-client, ai-desktop.
You can find installation instructions and usage details in the AQBot GitHub repository at github.com/AQBot-Desktop/AQBot. The project has 911 stars and 96 forks, indicating an active community.
AQBot is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to AQBot on Agent Skills Hub include llmio, huddol, fora. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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: