Skip to main content

​
Publish and Register Your Plugin

To create a plugin for the Python Hedera Agent Kit, you will need to create a plugin in your own repository, publish a PyPI package, and provide a description of the functionality included. Once you have a repository, published PyPI package, and documentation, you can add it to the Hedera Agent Kit by:
  1. Include the plugin in the README.md under the Third Party Plugins section
  2. Include the same information in docs/PLUGINS.md
Feel free to reach out to the Hedera Agent Kit maintainers on Discord so we can test your plugin and promote it through our channels.

​
Plugin Interface

Every plugin must implement the Plugin interface: 
from typing import Callable, List, Optional
from hedera_agent_kit.shared.types import Tool, Context

class Plugin:
    name: str
    version: Optional[str]
    description: Optional[str]
    tools: Callable[[Context], List[Tool]]

​
Creating a Plugin

​
Step 1: Create Plugin Structure

my_custom_plugin/
├── __init__.py           # Plugin exports
├── plugin.py             # Plugin definition
└── tools/
    └── my_tool.py        # Individual tool implementation

​
Step 2: Implement Your Tool

# tools/my_tool.py
from pydantic import BaseModel, Field
from hedera_agent_kit.shared.types import Tool, Context

class MyToolParams(BaseModel):
    required_param: str = Field(..., description="Description of required parameter")
    optional_param: str = Field(None, description="Description of optional parameter")

def my_tool_prompt(context: Context = None) -> str:
    return """
    This tool performs a specific operation.
    
    Parameters:
    - required_param (string, required): Description
    - optional_param (string, optional): Description
    """

async def my_tool_execute(client, context: Context, params: MyToolParams):
    try:
        # Your implementation here
        result = await some_hedera_operation(params)
        return result
    except Exception as e:
        return str(e)

MY_TOOL = "my_tool"

def tool(context: Context) -> Tool:
    return Tool(
        method=MY_TOOL,
        name="My Custom Tool",
        description=my_tool_prompt(context),
        parameters=MyToolParams,
        execute=my_tool_execute,
    )

​
Step 3: Create Plugin Definition

# plugin.py
from hedera_agent_kit.shared.types import Plugin, Context
from .tools.my_tool import tool as my_tool, MY_TOOL

my_custom_plugin = Plugin(
    name="my-custom-plugin",
    version="1.0.0",
    description="A plugin for custom functionality",
    tools=lambda context: [my_tool(context)],
)

my_custom_plugin_tool_names = {
    "MY_TOOL": MY_TOOL,
}

​
Using Your Plugin

from hedera_agent_kit.langchain.toolkit import HederaLangchainToolkit
from hedera_agent_kit.shared.configuration import Configuration, Context, AgentMode
from my_custom_plugin import my_custom_plugin

configuration = Configuration(
    tools=[],
    plugins=[
        my_custom_plugin,
    ],
    context=Context(
        mode=AgentMode.AUTONOMOUS,
        account_id=str(operator_id),
    ),
)

hedera_toolkit = HederaLangchainToolkit(
    client=client,
    configuration=configuration,
)

tools = hedera_toolkit.get_tools()

​
Plugin README Template

## Plugin Name

This plugin was built by <?> for the <project>. It enables <who?> to <do what?>

### Installation

'''bash
pip install <plugin-name>
'''

### Usage

'''python
from my_plugin import my_custom_plugin

configuration = Configuration(
    plugins=[my_custom_plugin],
    context=Context(mode=AgentMode.AUTONOMOUS),
)
'''


| Tool Name | Description | Usage |
|-----------|-------------|-------|
| `MY_TOOL` | What it does | How to use with parameters |

​
Resources