# Jackywine/Bella

Bella is best

Repository: https://github.com/Jackywine/Bella
Canonical: https://ross.abutalabs.com/products/bella
Language: JavaScript
License Family: other
Last push: 2026-02-05T02:58:42+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 35, longevity 29
- inputs: {"age_days": 413, "days_push": 209, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6379, forks 969 (observed 2026-08-28T04:09:42.948899+00:00)

## What it is
Bella is a self-hosted Node.js web application that acts as a personalized AI digital companion with voice interaction. It combines Whisper-based speech recognition, LLM-driven dialogue, and an animated visual interface served locally on port 8081.

## Use cases
- run a personal AI companion on my own machine
- chat with an AI assistant using my voice
- self-host a Siri-like assistant with Whisper speech recognition
- build a digital companion with emotional feedback
- experiment with local LLM dialogue and TTS
- create a voice-activated assistant web app

## When to choose
- you want a self-hosted, privacy-friendly AI companion with voice input
- you want to experiment with an alpha-stage companion AI built on Node.js and Whisper
- you need a ready-made web UI for LLM-based conversation

## When to avoid
- you need a production-stable assistant - the project is explicitly alpha with many features unimplemented
- you require a permissive license - no license file is present despite MIT badges
- you want a mature memory system, facial recognition, or proactive behavior - these are only planned

## Facets
- artifact type: application
- maturity: experimental
- function: speech-recognition, tts, llm-inference, chatbot, http-server, web-framework
- domain: artificial-intelligence, chatbots, speech-processing, web-development
- platform: browser, cross-platform
- tags: ai-companion, virtual-assistant, voice-interaction, whisper-asr, self-hosted, alpha, natural-language-processing, nodejs, web-server

## Member repositories
- Jackywine/Bella (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:42.948899+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 2026-08-29T17:45:09.635746+00:00, confidence not recorded.
  - readme: https://github.com/Jackywine/Bella (fetched 2026-08-28T04:09:42.948899+00:00, sha 884cedf4c01f)
- Data as of 2026-08-30T08:39:29.467469+00:00.