# idootop/migpt-next

让小爱音箱「听你的」，解锁无限可能。

Repository: https://github.com/idootop/migpt-next
Canonical: https://ross.abutalabs.com/products/migpt-next
Language: TypeScript
License: MIT
License Family: permissive
Archived: true
Last push: 2026-04-04T08:02:28+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 75, release rhythm 35, longevity 36
- inputs: {"age_days": 514, "days_push": 151, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1442, forks 206 (observed 2026-08-28T04:04:44.750913+00:00)

## What it is
MiGPT-Next is a TypeScript library and Docker-runnable service that connects Xiaomi's XiaoAI smart speakers to OpenAI-compatible large language models, letting users customize the speaker's replies with custom prompts and message handlers. It is the successor to MiGPT and is now officially unmaintained.

## Use cases
- make my xiaomi smart speaker answer with chatgpt
- customize xiaoai speaker responses with an llm
- connect xiaoai speaker to openai api
- run a custom ai assistant on mi smart speaker
- replace xiaoai's built-in answers with a large language model
- hook custom message handlers into xiaomi speaker

## When to choose
- you own a Xiaomi/XiaoAI smart speaker and want LLM-powered custom replies via OpenAI-compatible APIs
- you want a simple Docker or Node.js setup with custom onMessage handlers
- you need a self-hosted bridge between a Mi speaker and any LLM provider

## When to avoid
- you need active maintenance, updates, or support - the project is discontinued
- you require continuous/streaming conversation, which was removed due to API latency
- you need low-latency responses that can reliably interrupt the speaker's native replies
- you want an official or commercially supported integration

## Facets
- artifact type: library
- maturity: abandoned
- function: llm-inference, chatbot, tts, speech-recognition, sdk
- domain: large-language-models, chatbots, iot, artificial-intelligence
- platform: self-hosted, cross-platform
- tags: xiaomi, xiaoai-speaker, smart-speaker, openai, typescript, voice-assistant, unmaintained, automation, nodejs, docker

## Member repositories
- idootop/migpt-next (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.750913+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 2026-08-30T04:36:24.294259+00:00, confidence not recorded.
  - readme: https://github.com/idootop/migpt-next (fetched 2026-08-28T04:04:44.750913+00:00, sha f6a7947326ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.