Go backend server for the AIdea app, providing chat with mainstream LLMs and Stable Diffusion image generation with an OpenAI-compatible API.
yangjian102621/geekai
Open-source AI creation platform in Go and Vue3 that bundles chat, image, music, and video generation with an admin backend and billing.
Open-source alternative to:ChatGPT
Midjourney
- Stars
- 4,718
- Forks
- 1,068
- Open issues
- 33
- Last commit
- 2 months ago
What is it?
GeekAI is a self-hostable, multi-model AI creation platform. It brings chat with models such as ChatGPT and Claude, image generation through engines like MidJourney, DALL-E and Stable Diffusion, music generation via Suno AI, video generation, and mind-mapping into one web workspace.
The backend is written in Go with Gin, MySQL and Redis, and the frontend uses Vue3 with Element Plus and Vant for desktop and mobile layouts. Deployment is described as Docker-based, started with docker-compose. Files can be stored on Qiniu, Alibaba Cloud OSS, Tencent Cloud OSS or MinIO.
For operators, it includes user registration and login, permission management, points recharge, pay-per-use or subscription billing, usage statistics, and an administrator console. Private deployments are supported, but the project notes that private installs need manual upgrades.
Key features
- 01Chat with multiple LLM providers, including ChatGPT and Claude.
- 02Image generation through MidJourney, DALL-E, Stable Diffusion and other engines.
- 03Music generation with Suno AI and video generation with several providers.
- 04Built-in admin console with user, permission and billing management.
- 05Docker Compose deployment with Go backend and Vue3 frontend.
- 06Multiple cloud storage backends for generated works.
Use cases
- Running a branded AI creation site for a team or customers.
- Offering paid AI chat and image generation with points or subscriptions.
- Prototyping a multi-model AI workspace on top of an existing Go and Vue stack.
Quick start
- 1
Install Docker and docker-compose yourself
- 2
Start the project from the project root
docker-compose up -d
Things to know
- Private deployments do not support automatic upgrades and must be upgraded manually.
- The stack depends on Go, MySQL and Redis, so self-hosting takes setup effort.
In collections
Topics
FAQ
- What is geekai?
- Open-source AI creation platform in Go and Vue3 that bundles chat, image, music, and video generation with an admin backend and billing. GeekAI is a self-hostable, multi-model AI creation platform. It brings chat with models such as ChatGPT and Claude, image generation through engines like MidJourney, DALL-E and Stable Diffusion, music generation via Suno AI, video generation, and mind-mapping into one web workspace.
- Is geekai free to use? What license does it have?
- geekai is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is geekai still maintained?
- Updated within 6 months. The last commit to geekai was on Sep 13, 2026.
- What can I use geekai for?
- Running a branded AI creation site for a team or customers. Offering paid AI chat and image generation with points or subscriptions. Prototyping a multi-model AI workspace on top of an existing Go and Vue stack.
- How do I install geekai?
- Install Docker and docker-compose yourself Start the project from the project root: docker-compose up -d
- Where can I get geekai?
- The source code and installation instructions are on GitHub: https://github.com/yangjian102621/geekai
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A numbered library of 331 hand-drawn illustration styles, 167 layouts and 36 solid color themes that turns picks into bilingual prompts for AI image generators.
A modular web UI for Stable Diffusion image generation, built to make advanced tools easy to reach and extensible.
A Vue 3 and Electron chat app built on Tencent IM SDK, with multi-model AI chat (OpenAI, Ollama, DeepSeek) and a legacy repo superseded by PureChatNext.
A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.
A modular web UI for AI image, video and audio generation, built on Stable Diffusion, Flux, Wan and other models, with a ComfyUI workflow tab.