53AIHub
53AI Hub is an open-source AI portal, which enables you to quickly build a operational-level AI portal to launch and operate AI agents, prompts, and AI tools. It supports seamless integration with development platforms like Coze, Dify, FastGPT, RAGFlow.
claude mcp add --transport stdio 53ai-53aihub docker run -i 53aihub:latest
How to use
53AI Hub is an open-source AI portal designed to help you quickly build and operate an AI agent ecosystem, including agents, prompts, and tools. It supports integration with common AI platforms and cloud services, and offers full lifecycle management, user access control, and one-click deployment for local or cloud environments. To get started, deploy the Docker-based setup and access the admin panel to configure agents, prompts, and tools, then bind a domain if needed. The system is designed to be operating-ready for teams with varying roles and permissions, enabling you to publish and organize your AI assets with ease.
Once running, you can use the admin interface to manage AI agents, prompts, and tools, group and sort items, set user permissions, and monitor usage. The platform also supports multiple deployment modes and templates for customization, including local deployment via Docker Compose for local development and testing, and enterprise configurations for integration with organizational SSO and cloud services. The community edition provides the core capabilities needed to build and operate a production-grade AI portal, while enterprise editions offer additional integration options and customization.
To use the tools and capabilities, navigate to the administrative URL (e.g., http://localhost:3000 when running locally) to configure deployment options, manage assets, and set up permissions. If you choose cloud deployment, follow your preferred cloud provider workflow to expose the portal and ensure proper domain binding and SSL configuration.
How to install
Prerequisites:
- Docker and Docker Compose installed on your machine
- Basic familiarity with Docker commands
Installation steps:
-
Clone the repository (or pull the official Docker image if provided by the maintainers): git clone https://github.com/53ai/53aihub.git cd 53aihub
-
Build or pull the Docker image (depending on the provided deployment method). If using a prebuilt image, skip to step 3. If building locally, follow the repository's Dockerfile guidance to build 53aihub: docker build -t 53aihub:latest .
-
Run the Docker container for 53AI Hub (single-node deployment): docker run -d --name 53aihub -p 3000:3000 53aihub:latest
-
Access the admin panel in your browser: http://localhost:3000 Complete the initial setup to configure agents, prompts, and tools.
Notes:
- If the project provides a docker-compose.yaml, you can use docker-compose up -d for an easier setup. Example: git clone https://github.com/53ai/53aihub.git cd 53aihub/docker docker compose up -d
- Copy and customize the .env example to .env for environment-specific settings before starting the containers.
- Ensure firewall rules allow access to the configured port (default 3000).
- For production, set up a reverse proxy (e.g., Nginx) and TLS termination, and configure domain binding via the provided options.
Additional notes
Tips and common considerations:
- If you encounter port conflicts, adjust the -p host_port:container_port mapping in your docker run command or docker-compose file.
- Review .env.example and set environment variables for domain binding, database connections, and authentication as needed.
- Enterprise scenarios may require integration with SSO providers (WeCom, DingTalk, Feishu). Check documentation for specific environment variables and setup steps.
- When upgrading, backup your assets (agents, prompts, tools) and review any breaking changes in the release notes.
- For local development, enable hot-reload or use a development mode if available in the Docker image to speed up iterations.
Related MCP Servers
mcp-language
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
NagaAgent
A simple yet powerful agent framework for personal assistants, designed to enable intelligent interaction, multi-agent collaboration, and seamless tool integration.
agentcontrolplane
ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.
mcp-client-go
mcp client for Go (Golang). Integrate multiple Model Context Protocol (MCP) servers
kodit
👩💻 MCP server to index external repositories
mcp-web-ui
MCP Web UI is a web-based user interface that serves as a Host within the Model Context Protocol (MCP) architecture. It provides a powerful and user-friendly interface for interacting with Large Language Models (LLMs) while managing context aggregation and coordination between clients and servers.