Aikeya is an open-source alternative to Grok Companion. This is a platform where you can have a virtual AI waifu that learns and grows with you, bundled with optional mechanics inspired by Japanese dating sim games. Aikeya is privacy-focused - your data is stored locally and never leaves your device.

"Aikeya" - a container for AI to inhabit visually.

• VRM Model Viewer: Load and display VRM 3D avatar models with orbit controls
• Model-Centric UI: Full-screen 3D model with unobtrusive overlay controls
• 3D Speech Bubbles: Chat responses appear as bubbles that track the model's head in 3D space
• Chat Interface: Bottom-centered input bar with streaming responses
• Voice Input: Speech-to-text via Groq (Whisper) or Web Speech API with real-time audio visualization
• LLM Integration: Support for 7 LLM providers including OpenAI, Anthropic, Google, and local options
• Text-to-Speech: Support for ElevenLabs and OpenAI TTS
• Lip-sync: Audio-driven mouth animation synced to TTS playback
• Animations: VRMA-based idle and talking animations with automatic blinking
• Character Customization: Customize your companion's name, personality, and system prompt
• Companion System: Multi-axis relationship tracking with mood, events, and semantic memory
• Semantic Memory: Local AI-powered memory search using Transformers.js - finds memories by meaning, not just keywords
• Memory Graph: Interactive visualization showing how memories connect semantically
• Data Export/Import: Download your data as a save file, restore anytime
• Theming: Light and dark mode support with system preference detection
• Desktop App (beta, macOS only): Native desktop app with transparent overlay mode — your companion floats on your desktop

All your data is stored locally on your device using IndexedDB:

• No database setup required
• Works offline after initial load
• Export/import save files to back up or transfer your data
• Settings > Data to manage your save files

Build a meaningful relationship with your AI companion through a dating sim-inspired progression system:

• Multi-axis Relationships: Track affection, trust, intimacy, comfort, and respect separately
• 8 Relationship Stages: Progress from Stranger → Acquaintance → Friend → Close Friend → Romantic Interest → Dating → Committed → Soulmate
• Dynamic Mood: Real-time emotions with causality tracking (she remembers why she feels a certain way)
• Visual Novel Events: Milestone moments, romantic scenes, and choices that matter - with custom dialogue and branching responses
• Semantic Memory: Facts are indexed with vector embeddings for meaning-based retrieval - "outdoor activities" finds memories about hiking. Runs locally using Transformers.js, no API calls
• Natural Progression: Hybrid system combining app heuristics + LLM suggestions for believable relationship growth
• Time-Aware: Your companion notices when you've been away and reacts accordingly

See the Companion System Architecture for full details.

A native desktop app built with Tauri that includes all web features plus:

• Overlay Mode: Your companion floats on your desktop with a transparent background
• Always-on-Top: The overlay stays visible over all other windows
• Draggable Positioning: Click and drag the character to reposition anywhere on screen
• Floating Chat: Expandable chat input that appears when you click the chat icon
• Window Switching: Seamlessly switch between the full app and overlay mode
• Global Hotkeys: Push-to-talk, toggle overlay, and focus chat with keyboard shortcuts

The desktop app uses the same codebase as the web version — your save files are compatible between both.

Voice input is accessed via the microphone button in the chat bar. Groq STT uses Whisper for accurate transcription on any platform (including desktop). Web Speech API works without an API key in Chrome, Edge, and Safari. If a Groq API key is configured, it takes priority automatically.

Use Aikeya directly at aikeya.org — no installation required. Or download the macOS desktop app from GitHub Releases.

If you prefer to run Aikeya locally or host your own instance:

• Node.js 22+
• pnpm (recommended) or npm
• A modern browser (Chrome, Firefox, Safari, Edge) — for the web version

# Clone the repository
git clone https://github.com/aikeyaorg/aikeya.git
cd aikeya

# Install dependencies
pnpm install

# Start development server
pnpm dev

The app will be available at http://localhost:5173

To run the desktop app from source, you'll need the Rust toolchain in addition to the web prerequisites:

# Install Rust (if not already installed)
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

# Run the desktop app
pnpm tauri dev

1. Click the Settings (gear icon) in the sidebar
2. Navigate to LLM Providers to configure your chat provider:
   • Select a provider and enter your API key
   • Or use a local server like Ollama or LM Studio
3. Navigate to TTS Providers to configure text-to-speech (optional):
   • Select a TTS provider
   • Enter your API key
   • Configure voice settings

All API keys are stored locally on your device and are never sent to any server except the respective API providers.

1. Go to Settings > Avatar
2. Click "Load VRM" to select a local .vrm file
3. Or enter a URL to load a VRM model from the web

Your companion data is stored locally on your device. To back up or transfer your data:

1. Go to Settings > Data
2. Click Export Save to download a JSON file with all your data
3. To restore, click Import Save and select your save file
4. Choose Replace (wipe and restore) or Merge (add to existing)

aikeya/
├── src/
│   ├── lib/
│   │   ├── ai/             # LLM response parsing and prompt building
│   │   ├── assets/         # Static assets
│   │   ├── components/     # Svelte components
│   │   ├── config/         # App and docs configuration
│   │   ├── data/           # Event definitions and static data
│   │   ├── db/             # IndexedDB database (Dexie)
│   │   ├── engine/         # Companion engine (state, memory, events)
│   │   ├── services/       # LLM, TTS, STT, storage services
│   │   ├── stores/         # Svelte 5 stores (state management)
│   │   ├── styles/         # Shared CSS (prose, etc.)
│   │   ├── types/          # TypeScript types
│   │   └── utils/          # Utility functions
│   ├── content/
│   │   ├── blog/           # Blog post markdown content
│   │   └── docs/           # Documentation site markdown content
│   └── routes/
│       ├── (app)/          # Main application routes
│       ├── api/            # API routes
│       ├── blog/           # Blog routes
│       ├── docs/           # Documentation site routes
│       └── overlay/        # Desktop overlay route
├── src-tauri/               # Tauri desktop app (Rust)
├── static/
│   └── models/             # Place default VRM models here
└── package.json

pnpm dev          # Start web development server
pnpm build        # Build web app for production
pnpm preview      # Preview production build
pnpm lint         # Type-check the project (svelte-check)
pnpm check        # Same as lint (alias)
pnpm check:watch  # Type-check in watch mode
pnpm tauri dev    # Run the desktop app in development mode
pnpm tauri build  # Build desktop app installer

• VRM model loading and display with orbit controls
• 3D speech bubbles tracking model head position
• Multi-provider LLM support (7 providers)
• Multi-provider TTS support (2 providers)
• Audio-driven lip-sync
• VRMA-based animations (idle, talking, blinking)
• Companion system with multi-axis relationships
• 8-stage relationship progression (Stranger → Soulmate)
• Visual novel event system with choices
• Semantic memory system with local embeddings (Transformers.js)
• Time-based mood and relationship decay/recovery
• Local-first IndexedDB storage with export/import
• Theme system with light/dark modes
• Voice input via Groq STT (Whisper) and Web Speech API
• Desktop application with transparent overlay mode (macOS only, Windows/Linux planned)

• Companion Gender System - Gender selection with male/female specific animations and behaviors
• Multi-provider STT - Support for additional speech-to-text providers beyond Groq and Web Speech API
• Enhanced User Controls - More granular control over companion behavior and responses
• Custom Lighting Controls - Adjust 3D scene lighting, environment, and atmosphere
• LLM-Controlled Expressions - Dynamic facial animations and emotions driven by LLM responses
• Live2D Support - Alternative to VRM for 2D animated avatars
• Expanded Default Avatars - More built-in 3D avatar options to choose from
• Photo Mode - Full-featured photo mode with character posing, lighting adjustments, and high-quality saves

Contributions are welcome! Please read our Contributing Guide for details on how to submit pull requests, report issues, and contribute to the project.

For information about security considerations and how to report vulnerabilities, please see our Security Policy.

Aikeya is built on the shoulders of these excellent projects:

• Airi - The original inspiration for this project. A beautiful AI companion with VRM avatar support.
• Amica - Open-source AI companion with VRM support and emotional expressions.
• Riko Project by JustRyan - AI waifu project showcasing VRM avatar interactions.

• @pixiv/three-vrm - VRM model loading and rendering for Three.js
• xsAI - Unified LLM and TTS provider integration
• Three.js - 3D graphics engine
• Threlte - Svelte components for Three.js
• SvelteKit - Web application framework
• Tauri - Desktop application framework
• Tailwind CSS - Utility-first CSS framework
• Transformers.js - In-browser ML for semantic memory embeddings

• bits-ui - Headless UI components for Svelte
• Dexie.js - IndexedDB wrapper for local storage
• force-graph - Force-directed graph visualization for memory graph
• simple-icons - SVG icons for provider logos

• n8ao - Ambient occlusion for Three.js
• postprocessing - Post-processing effects

This project is licensed under the MIT License - see the LICENSE file for details.