Alice
Alice is a voice-first desktop AI assistant application built with Vue.js, Vite, and Electron. Advanced memory system, function calling, MCP support, optional f
What is Alice?
Alice is a voice-first desktop AI assistant application built with Vue.js, Vite, and Electron. Advanced memory system, function calling, MCP support, optional fully local use, and more.
Overview of Alice
What it is
Alice is an open-source desktop AI assistant application built with Vue.js, Vite, and Electron. It is designed for voice-first interaction and includes an advanced memory system, function calling, MCP support, and optional fully local operation. The application can work with cloud LLMs (OpenAI, OpenRouter, DeepSeek, etc.) or local LLMs (Ollama, LM Studio).
Key features
- Voice interaction with VAD-powered recognition, natural-sounding TTS (OpenAI/Google/Piper), and interruptible speech - Memory system with short-term thoughts (Hnswlib vector DB), long-term memories (local DB), summarization, emotion awareness, and local RAG for documents - Vision capabilities: screenshot interpretation via Vision API and image generation via gpt-image-2 - Computer use tools: file system browsing, shell command execution with granular permissions (one-time, session, permanent)
- Function calling: web search (including Searxng), Google Calendar/Gmail integration, torrent search/download (Jackett + qBittorrent), clipboard management, task scheduler, MCP server support - Wake word support with local STT model, auto language detection or manual selection - Dedicated Chrome extension for asking about active tab and context menu actions (fact check, summarize, tell me more)
- Custom tools defined in JSON backed by local scripts, custom avatars with video loops
Use cases
- Voice-controlled personal assistant for daily tasks, reminders, and information retrieval - Local document Q&A using RAG with uploaded files - Automating system operations (file management, shell commands) with user-approved permissions - Integrating with web services (search, email, calendar) through function calling - Creative work support via image generation and vision-based analysis
Getting started
bash # 1. Clone the repo $ git clone https://github.com/pmbstyle/Alice.git # 2. Install dependencies $ npm install # 3. Set up your .env file (see .env.example for reference) # 4. Download ONNX Runtime and the pinned multi-lang Memory/RAG model npm run setup:embeddings # 5. Compile backend npm run build:go # 6. Run dev environment $ npm run dev For production builds, see the repository README. Prebuilt installers are available for Windows, macOS, and Linux.
License and pricing
The project is open source under the MIT license. It is free to use.
Based on the project's public README and repository metadata.