Ross ROSS = Recommend OSS · open-source software intelligence for agents

lss233/kirara-ai

🤖 可 DIY 的 多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenAI | 工作流系统、网页搜索、AI画图、人设调教、虚拟女仆、语音对话 | observed · 2026-08-28

github.com/lss233/kirara-ai · homepage · Python · AGPL-3.0 (copyleft) observed · 2026-08-28

Health v2 · maintenance only

46/100

  • Activity 29
  • Release rhythm 40
  • Longevity 97
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 10.0
  • age_days: 1367
  • days_rel: 515
  • days_push: 431
  • n_releases_24m: 5

Full methodology

Adoption not part of the score

18972 stars · 1834 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Kirara AI is a self-hosted, DIY multimodal AI chatbot framework that connects large language models (DeepSeek, ChatGPT, Claude, Gemini, Ollama, Grok) to chat platforms like QQ, Telegram, Discord, and WeChat. It offers a WebUI, workflow-based agent orchestration, and a plugin ecosystem for features like web search, AI drawing, personas, and voice conversations.

Use cases

  • run an AI chatbot on QQ groups
  • connect ChatGPT or DeepSeek to Telegram
  • build a virtual AI companion with a custom persona
  • add an AI assistant to a Discord server
  • deploy a self-hosted LLM chatbot with Docker
  • create AI workflows with web search and image generation
  • make a voice-chatting AI maid bot

When to choose

  • you want an LLM-powered bot on Chinese chat platforms like QQ or WeChat
  • you need a WebUI and workflow system to customize bot behavior without heavy coding
  • you want to switch between multiple LLM providers easily
  • you want a plugin ecosystem for extending bot capabilities

When to avoid

  • you need a simple single-platform bot library to embed in your own code
  • you require a permissive license for commercial closed-source use (AGPL-3.0)
  • you only need a headless API without chat-platform integration

Facets

application · maturity active

chatbot agent-framework llm-inference plugin-system workflow-automation web-framework chatbots artificial-intelligence large-language-models messaging-platforms self-hosted python cross-platform windows self-hosted qq-bot telegram-bot wechat-bot discord-bot multimodal webui persona voice-chat ai-drawing web-search ai-agents docker linux macos

3 sources

Member repositories

RepositoryRoleHealth v2
lss233/kirara-aimain46

For agents

markdown · JSON · MCP: product_card(name="lss233/kirara-ai")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem