# semperai/amica

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

Repository: https://github.com/semperai/amica
Canonical: https://ross.abutalabs.com/products/amica
Homepage: https://heyamica.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, assistant-chat-bots, computer-vision, llm, speech-recognition, tts
Last push: 2025-07-23T20:57:17+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 33, release rhythm 8, longevity 74
- inputs: {"age_days": 1040, "days_push": 406, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1593, forks 269 (observed 2026-08-28T04:05:08.787976+00:00)

## What it is
Amica is an open-source web application for conversing with customizable 3D characters through voice chat, speech recognition, and vision. It supports VRM avatar imports, emotion expression, and pluggable AI backends like llama.cpp and ChatGPT.

## Use cases
- chat with a 3D AI character using voice
- build a personal AI assistant with a VRM avatar
- create a virtual companion with emotion expressions
- run a local voice chatbot with llama.cpp
- give an LLM assistant speech recognition and TTS
- make an interactive 3D character that can see via webcam

## When to choose
- you want a self-hostable, customizable 3D AI companion
- you need VRM avatar support with voice and vision interaction
- you want to swap between local and cloud LLM backends

## When to avoid
- you need a plain text-only chatbot without avatars
- you require production-grade enterprise assistant infrastructure
- you need mobile-native apps rather than a web interface

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, chatbot, llm-inference, computer-vision, chat-interface
- domain: artificial-intelligence, chatbots, large-language-models, speech-processing, computer-vision, web-development
- platform: cross-platform, windows
- tags: 3d-characters, vrm, voice-chat, virtual-assistant, emotion-engine, threejs, whisper, vtuber, web-server, macos, linux, nodejs

## Member repositories
- semperai/amica (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:08.787976+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:54:15.638774+00:00, confidence not recorded.
  - readme: https://github.com/semperai/amica (fetched 2026-08-28T04:05:08.787976+00:00, sha 3ad4d1875838)
- Data as of 2026-08-30T08:39:29.467469+00:00.