MiGPT-Next is an upgraded branch of the MiGPT concept focused on customizable responses for Xiaomi XiaoAI smart speakers. It lets developers intercept recognized messages and define how the speaker should respond through programmable handlers. The project can connect to OpenAI-compatible model endpoints and allows configuration of models, API URLs, headers, system prompts, and speaker credentials. It can be launched through Docker or installed as the @mi-gpt/next Node.js package. Unlike the earlier MiGPT release, the newer implementation removed continuous conversation and streaming response support because of API latency and device-state limitations. The repository is no longer maintained, but it remains useful as an example of programmable XiaoAI response routing.

Features

  • Programmable custom message responses
  • OpenAI-compatible model integration
  • Configurable system prompts and models
  • Custom API endpoints and request headers
  • Docker deployment support
  • Reusable Node.js package

Project Samples

Project Activity

See All Activity >

License

MIT License

Follow MiGPT-Next

MiGPT-Next Web Site

Other Useful Business Software
Build Agents and Models on One Platform Icon
Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of MiGPT-Next!

Additional Project Details

Programming Language

TypeScript

Related Categories

TypeScript Artificial Intelligence Software

Registered

1 day ago