Logo
Deploy Now

SaaS Alternative

Character.AI Replika

Categories

Self-Hosted Gaming AI Companion VTuber Virtual Character Real-Time Voice WebGPU

Stars

48,304

Forks

4,781

Watchers

181

Developer links

Last Updated: 08-24-2026 03:57 AM (UTC)

Airi

Project AIRI is the most popular open-source AI companion platform — a self-hosted recreation of Neuro-sama that brings AI-powered virtual characters into your world across web, desktop, and mobile. The system renders Live2D, Spine, and VRM 3D character models with auto-blink, eye tracking, and lip-sync driven by real-time voice synthesis, while the xsAI abstraction layer connects to 40+ LLM providers including OpenAI GPT-4, Anthropic Claude, Google Gemini, DeepSeek, and local models via Ollama and OpenRouter. Built from day one on WebGPU, WebAudio, Web Workers, WebAssembly, and WebSocket technologies, the browser version runs entirely client-side with PWA offline support while the server runtime enables persistent memory via PostgreSQL with pgvector embeddings and DuckDB WASM for client-side storage. The Minecraft agent plays autonomously using mineflayer with pathfinding, and a Factorio integration provides cooperative gameplay. Social integrations deploy your companion as a Discord bot joining voice channels, a Telegram bot, and a Twitter/X agent posting and replying autonomously. The desktop Stage Tamagotchi app provides an always-on-screen companion for Windows and macOS, while Stage Pocket brings the experience to mobile. Voice features include client-side speech recognition via VAD, multiple TTS providers including ElevenLabs, and screen vision capabilities. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Airi

Benefits

  • 40+ LLM Provider Support
  • Connects to OpenAI, Anthropic, Gemini, DeepSeek, Ollama, and OpenRouter through the xsAI abstraction layer, enabling both cloud and fully local model inference without vendor lock-in.
  • Multi-Platform Character Rendering
  • Renders Live2D, Spine, and VRM 3D models with auto-blink, eye tracking, and lip-sync across web browsers via WebGPU, desktop applications, and mobile with PWA offline support.
  • Autonomous Game-Playing Agent
  • Plays Minecraft autonomously using mineflayer with pathfinding and cooperative Factorio gameplay, joining as a teammate that navigates, builds, and communicates in real-time.
  • Social Platform Integration
  • Deploys as a Discord bot joining voice channels, a Telegram conversational bot, and a Twitter/X agent that posts, replies, and interacts autonomously with configurable personality.

Features

  • Real-Time Voice Chat
  • Client-side speech recognition via VAD with multiple TTS providers including ElevenLabs for high-quality voice synthesis with lip-sync and emotional expression mapping.
  • WebGPU Browser Runtime
  • Runs entirely in modern browsers using WebGPU, WebAudio, Web Workers, and WebAssembly with Progressive Web App support for offline operation without server dependencies.
  • Persistent Memory System
  • Server-side PostgreSQL with pgvector for semantic memory retrieval and client-side DuckDB WASM for local persistence across conversations and interactions.
  • Screen Vision Capability
  • Sees and understands screen content in real-time, enabling contextual commentary, assistance with visible tasks, and reactive behavior based on visual input.
  • Character Customization
  • Import custom Live2D or VRM models with configurable personality traits, behavioral parameters, voice settings, and appearance for unique companion creation.