Environment Requirements#
- Python version 3.12
- Dify plugin scaffold tool (
dify-plugin-daemon)
For setup instructions, see Initializing Development Tools.
Obtain the Dify Plugin Development Package#
Download the Dify Plugin CLI from the GitHub releases page.
Installation Methods for Different Platforms#
macOS Brew (Global Installation):
After installation, open a new terminal window and enter the dify version command. If it outputs the version information, the installation was successful.
macOS ARM (M Series Chips):
macOS Intel:
Linux:
Global Installation (Recommended):
Run the Development Package#
The following examples use dify as the command. If you installed locally, replace the command accordingly—for example, ./dify-plugin-darwin-arm64 plugin init.
Plugin Development Process#
1. Create a New Plugin#
Follow the prompts to configure the basic plugin information.
For a full walkthrough, see Dify Plugin Development: Hello World Guide.
2. Run in Development Mode#
Configure the .env file, then run the following command in the plugin directory:
For debugging details, see Remote Debugging Plugins.
3. Package and Deploy#
Package the plugin:
For publishing details, see the Publishing Overview.
Plugin Categories#
Tool Labels#
Category tags are defined in ToolLabelEnum:
Plugin Type Reference#
Dify supports several plugin types:
- Tool plugin: Integrate third-party APIs and services. See Dify Plugin Development: Hello World Guide.
- Model plugin: Integrate AI models. See Model Plugin and Quick Integration of a New Model.
- Agent strategy plugin: Customize Agent thinking and decision-making strategies. See Agent Strategy Plugin.
- Extension plugin: Extend Dify platform functionality, such as Endpoints and web apps. See Extension Plugin.
- Data source plugin: Serve as the document data source and starting point for knowledge pipelines. See Data Source Plugin.
- Trigger plugin: Automatically trigger workflow execution on third-party events. See Trigger Plugin.