mylxsw/aidea

★ 6,947DartAudience · generalComplexity · 4/5LicenseSetup · hard

Mindmap

mindmap
  root((AIdea))
    What It Does
      Multi-model AI chat
      Image generation
    Supported Models
      GPT-4
      Tongyi Qianwen
      Wenxin Yiyan
      Stable Diffusion
    Platforms
      iOS and Android
      macOS and Windows
    Architecture
      Flutter client
      Go server
      Docker deployment
    Options
      Self-hosted
      Managed hosted version

mindmap root((AIdea)) What It Does Multi-model AI chat Image generation Supported Models GPT-4 Tongyi Qianwen Wenxin Yiyan Stable Diffusion Platforms iOS and Android macOS and Windows Architecture Flutter client Go server Docker deployment Options Self-hosted Managed hosted version

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Chat with GPT-4, Tongyi Qianwen, and other models from one app without switching between services.

USE CASE 2

Generate images from text descriptions using Stable Diffusion through a mobile app interface.

USE CASE 3

Self-host the full stack (Flutter app plus Go server) to keep all AI conversations on your own infrastructure.

USE CASE 4

Build on top of the open-source Flutter client to create a customized AI chat app for a specific audience.

Tech stack

DartFlutterGo

Getting it running

Difficulty · hard Time to first run · 1day+

Self-hosting requires three separate repositories (Flutter client, Go server, Docker config) and setup tutorials are written in Chinese.

Free to use and modify for any purpose, including commercial use, as long as the MIT copyright notice is kept.

In plain English

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.

Copy-paste prompts

Prompt 1

I want to self-host AIdea using Docker. Walk me through pulling the Docker deployment repo and getting the Go server and Flutter client connected.

Prompt 2

How do I add a new AI language model provider to the AIdea Flutter client? Show me where the API connection code lives.

Prompt 3

I want to use the stable v1.x branch of AIdea for a production self-hosted setup. What are the differences from v2 and how do I pin to that branch?

Prompt 4

Help me build the AIdea Flutter app for iOS from source. What dependencies and environment variables do I need?

Prompt 5

Show me how to configure AIdea to use only self-hosted or open-source AI models instead of commercial APIs.

Open on GitHub → Explain another repo

← mylxsw on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.