Charivo — AI skill for Claude Code
Interactive Live2D AI characters — modular TypeScript framework for LLM, TTS, STT, and realtime voice.
How to install Charivo
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open zeikar/charivo and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Charivo does
Interactive Live2D AI characters — modular TypeScript framework for LLM, TTS, STT, and realtime voice.
Alternatives in AI
- Pixel Agents — Compressed Reference — VS Code extension with embedded React webview: pixel art office where AI agents (Claude Code terminals) are an 6.5k ★
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Qwen Audio Agent — A realtime voice runtime that keeps Agents talking, working, and present 2.3k ★
README
Charivo
[](https://github.com/zeikar/charivo/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@charivo/core) [](https://www.npmjs.com/package/@charivo/core) [](./LICENSE) [](http://zeikar.dev/hyperclaude/)
Build Live2D AI characters that talk, react, and look at you.
Charivo is a modular TypeScript framework for voice, expression, motion, gaze, and real-time conversation. It separates orchestration, stateful managers, browser-side clients, and server-side providers so you can swap pieces without rewriting the whole stack.

Live demos
- Live2D web app — https://charivo.vercel.app/
- Companion (Realtime voice + cross-session memory) — https://charivo-companion.vercel.app/
Documentation
Built with Charivo
- LiveClaw (Electron desktop companion driven by a local OpenClaw agent) — https://github.com/zeikar/liveclaw
Try it locally
Want to watch a full Live2D character talk before wiring your own app? The [`examples/web`](./examples/web) demo bundles the Live2D models and every modality. Clone the repo, add an OpenAI key (and a Gemini key for realtime voice, which defaults to Gemini Live), and run:
pnpm install
cp examples/web/.env.example examples/web/.env.local # then set OPENAI_API_KEY and GEMINI_API_KEY
pnpm dev:web
Open . The in-app settings menu lets you compare the serve
Related Skills
Lyns Voice
The voice of Claude Code - speak with Oracle. Local-first desktop app: on-device Whisper STT + neural Kokoro T
AI Vtuber
AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain(本地/llm)/chatglm/text-generation-webui/闻达】 驱动的虚拟主播【Live2D】,可
Localvoxtral
Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and
Agent Voice Chat
TypeScript SDK and CLI for building AI agents that autonomously join, listen, and speak in X/Twitter Spaces. S
Echook
🔊 echook — AI-operated audio notifications for Claude Code, Cursor IDE & Codex CLI — 26 hooks, voice + chime
Jarvis Line
Voice notifications for Codex, Claude Code, Gemini CLI, and other AI coding agents, powered by hook-driven TTS
Related Agents
Create Character
D&D character creation wizard. Use PROACTIVELY when players want to create new characters. Guides through race
Realtime API Engineer
Use proactively for all OpenAI Realtime API integration - WebRTC setup, audio streaming, session management, a
Voice Engineer
GAIA voice interaction specialist. Use PROACTIVELY for Whisper ASR, Kokoro TTS, the Talk SDK, speech-to-speech