moeru-ai/airi
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
What it solves
Project AIRI aims to create a "digital human" or AI companion that goes beyond simple chat interfaces. It seeks to provide a persistent, interactive virtual character (inspired by Neuro-sama) that can interact with the user's environment, play games like Minecraft and Factorio, and communicate across platforms like Discord and Telegram.
How it works
AIRI is built using a combination of Web technologies (WebGPU, WebAssembly, WebAudio) for cross-platform accessibility and native performance layers (NVIDIA CUDA, Apple Metal via the candle project) for the desktop version. It integrates various AI components:
- Brain: Connects to multiple LLM providers (via xsai) and is being developed to handle game-playing logic and memory systems.
- Ears: Implements client-side speech recognition and talking detection for audio input from browsers and Discord.
- Mouth: Uses multi-provider voice synthesis (TTS) including ElevenLabs, Azure, and local Kokoro TTS.
- Body: Supports VRM and Live2D models with automated animations for blinking, looking, and idle movements.
Who it’s for
Users who want a personal AI companion or virtual streamer (VTuber) that can interact with them in real-time, play games, and exist across browser, desktop, and mobile (PWA) environments.
Highlights
- Cross-Platform: Runs on modern browsers, desktop (Windows, macOS, Linux), and mobile devices.
- Game Integration: Capable of playing Minecraft and Factorio (with a PoC for the latter).
- Broad LLM Support: Compatible with a wide array of providers including OpenAI, Claude, Gemini, and local engines like Ollama and vLLM.
- Visual Fidelity: Full support for 3D VRM and 2D Live2D avatars with autonomous animations.
Related
- Project
coulsontl/ai-toolboxAI Toolbox is a cross‑platform desktop manager that centralises configuration, prompts, plugins, session history and backup for many AI coding assistants (Claude, Codex, Gemini, Grok, Kimi, etc.). It offers a GUI, local proxy gateway, WSL/SSH sync, skill marketplace, and system‑tray shortcuts, built with React/Tauri and SQLite.
- Project
dromara/wgaiWGAI is an industrial-grade multimodal AI management platform that integrates computer vision, speech recognition, and robotics navigation with support for offline deployment.
- Project
PunithVT/ai-avatar-systemAvatarAI is an open‑source, production‑grade system that turns any portrait photo and a short voice sample into a real‑time, lip‑synced talking avatar. It streams Whisper‑transcribed speech to a selectable LLM (Claude, GPT‑4o, or local Ollama/vLLM), feeds the generated text to a multilingual TTS (Chatterbox/XTTS), and renders video frames with MuseTalk V1.5. The stack includes Next.js front‑end, FastAPI back‑end, PostgreSQL, Redis, Celery, Prometheus, and Docker‑Compose, with optional one‑click AWS GPU deployment. Features include zero‑shot voice cloning, barge‑in interruption, multi‑LLM support, JWT auth, conversation memory summarisation, and optional face‑restoration via GFPGAN.
- Project
luoguoxiong/aipackA lightweight, extensible TypeScript Agent framework providing a runtime and pluggable ecosystem for building AI agents with built-in support for memory, context compression, and MCP.
- Project
hypothesi/mcp-server-tauriMCP Server Tauri is a Node‑based Model Context Protocol server that connects AI assistants (Claude, Cursor, Windsurf, etc.) to a running Tauri v2 app. It streams screenshots, DOM snapshots, console logs, and Tauri IPC traffic, and exposes 21 commands for UI automation, IPC inspection, log streaming, and mobile device listing. By installing a small Rust bridge plugin into the Tauri binary, the server gives the assistant rich, real‑time context, enabling AI‑driven debugging, code generation, and cross‑platform UI control without external drivers.