by KiraAI-Dev · Codex Skill · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
KiraAI, a modular, multi-platform AI digital life that connects Large Language Models (LLMs) and various chat adapters (QQ, Telegram...)
| Stars | 70 |
| Forks | 21 |
| Language | Python |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 52.0310638192928/100 |
| Open Issues | 18 |
| Last Updated | 2026-08-22 |
| Created | 2025-10-31 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with KiraAI for enhanced workflows:
Looking for a KiraAI alternative? If you're comparing KiraAI 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.
KiraAI, a modular, multi-platform AI digital lifeform that connects Large Language Models (LLMs) and various c
Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco
QQ bot platform with cognitive memory architecture and multi-agent Skills, via OneBot V11.
MCP Server for Telegram
c4 GenAI Suite
AI-native TypeScript bot framework — one codebase for 20+ chat platforms (QQ, Discord, Telegram, Slack, WeChat
Explore other popular codex skill tools:
KiraAI is KiraAI, a modular, multi-platform AI digital life that connects Large Language Models (LLMs) and various chat adapters (QQ, Telegram...). It is categorized as a Codex Skill with 70 GitHub stars.
KiraAI is primarily written in Python. It covers topics such as ai, bot, chatbot.
You can find installation instructions and usage details in the KiraAI GitHub repository at github.com/KiraAI-Dev/KiraAI. The project has 70 stars and 21 forks, indicating an active community.
KiraAI is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to KiraAI on Agent Skills Hub include KiraAI, golembot, Undefined. 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: