pmbstyle/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.
Combines local vector search (Hnswlib) with structured SQLite memory to maintain conversational context, emotion-aware summaries, and local RAG capabilities. Supports multi-provider flexibility—swapping between OpenAI, OpenRouter, Ollama, and LM Studio—with VAD-powered voice activity detection, optional fully-local STT/TTS via whisper.cpp and Piper, and MCP server integration. Desktop permissions system grants granular, revocable command approval for file system and shell access, plus extensibility through JSON-defined custom tools and user-swappable avatar video loops.
228 stars.
Stars
228
Forks
32
Language
TypeScript
License
MIT
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/pmbstyle/Alice"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ob-labs/ChatBot
ChatBot, show how to implement a RAG based on OceanBase or OceanBase seekdb AI capabilities...
stackitcloud/rag-template
Template for AI chatbots & document management using Retrieval-Augmented Generation with vector...
GGyll/condo_gpt
An intelligent assistant for querying and analyzing real estate condo data in Miami.
rustyneuron01/Conversation-Genome-Project
Structured data & semantic tagging pipeline. Turns raw text (conversations, web pages, surveys)...
zaldivards/ContextQA
ContextQA - The open-source tool for data-driven conversations