aidea
An APP that integrates mainstream large language models and image generation models, built with Flutter, with fully open-source code.
A fully open-source iOS, Android, macOS, and Windows app that gives you a single chat interface for multiple AI language models and image generators, so you do not need separate subscriptions for each service.
AIdea is a fully open-source mobile and desktop app that gives you a single interface for chatting with multiple AI language models and generating images. Rather than signing up for each AI service separately, you open AIdea and access several of them from one place. The app runs on iOS, Android, macOS, and Windows.
The app connects to large language models for text conversation and to image generation models for creating pictures from text descriptions. The README mentions support for services including GPT-4, Tongyi Qianwen (Alibaba), and Wenxin Yiyan (Baidu), alongside image generation tools like Stable Diffusion. A managed hosted version is available at a website linked in the README, so users who do not want to run their own server can sign up there instead.
For developers who want to self-host, the project is split across three repositories: this one (the Flutter client app), a separate server written in Go, and a Docker deployment configuration. The README notes that v2 is under active development and that people wanting a stable self-hosted setup should use the v1.x branch. Build environment tutorials are available in linked articles, though they are written in Chinese.
The client code is written in Dart using the Flutter framework, which allows the same codebase to compile for mobile and desktop platforms. The server is written in Go. Both are open source under the MIT license.
Where it fits
- Chat with GPT-4, Tongyi Qianwen, and other models from one app without switching between services.
- Generate images from text descriptions using Stable Diffusion through a mobile app interface.
- Self-host the full stack (Flutter app plus Go server) to keep all AI conversations on your own infrastructure.
- Build on top of the open-source Flutter client to create a customized AI chat app for a specific audience.