hedera-agent-kit 3.0.0

Use the Hedera Agent Kit to build agents that can interact with the Hedera network in any framework you like

Hedera Agent Kit (Python)

Build Hedera-powered AI agents in under a minute.

📋 Contents

• Key Features
• About the Agent Kit Functionality
• Developer Examples
• 🚀 60-Second Quick-Start
• Agent Execution Modes
• Hedera Plugins & Tools
• Creating Plugins & Contributing
• License
• Credits

---

Key Features

This is the Python edition of the Hedera Agent Kit, providing a flexible and extensible framework for building AI-powered Hedera agents.

• 🔌 Plugin architecture for easy extensibility
• 🧠 LangChain integration with support for multiple AI frameworks
• 🪙 Comprehensive Hedera tools, including:
  • Token creation and management (HTS)
  • Smart contract execution (EVM)
  • Account operations
  • Topic (HCS) creation and messaging
  • Transaction scheduling
  • Allowances and approvals

---

Agent Kit Functionality

The list of currently available Hedera plugins and functionality can be found in the Plugins & Tools section of this page.

👉 See docs/HEDERAPLUGINS.md for the full catalogue & usage examples.

Want to add more functionality from Hedera Services? Open an issue!

---

Developer Examples

You can try out examples of the different types of agents you can build by following the instructions in the Developer Examples doc in this repo.

First follow instructions in the Developer Examples to clone and configure the example, then choose from one of the examples to run:

• Option A - Plugin Tool Calling Agent (LangChain v1)
• Option B - Tool Calling Agent (LangChain Classic)
• Option C - Plugin Tool Calling Agent (LangChain Classic)
• Option D - Structured Chat Agent (LangChain Classic)

---

🚀 60-Second Quick-Start

See more info at https://pypi.org/project/hedera-agent-kit/

🆓 Free AI Options Available!

• Ollama: 100% free, runs on your computer, no API key needed
• Groq: Offers generous free tier with API key
• Claude & OpenAI: Paid options for production use

1 – Project Setup

Create a directory for your project:

mkdir hello-hedera-agent-kit
cd hello-hedera-agent-kit

Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

Install dependencies:

pip install hedera-agent-kit langchain langchain-openai langgraph python-dotenv

2 – Configure: Add Environment Variables

Create an .env file in the root directory of your project:

touch .env

If you already have a testnet account, you can use it. Otherwise, you can create a new one at https://portal.hedera.com/dashboard

Add the following to the .env file:

# Required: Hedera credentials (get free testnet account at https://portal.hedera.com/dashboard)
ACCOUNT_ID="0.0.xxxxx"
PRIVATE_KEY="0x..." # ECDSA encoded private key

# Optional: Add the API key for your chosen AI provider
OPENAI_API_KEY="sk-proj-..."      # For OpenAI (https://platform.openai.com/api-keys)
ANTHROPIC_API_KEY="sk-ant-..."    # For Claude (https://console.anthropic.com)
GROQ_API_KEY="gsk_..."            # For Groq free tier (https://console.groq.com/keys)
# Ollama doesn't need an API key (runs locally)

3 – Simple "Hello Hedera Agent Kit" Example

Create a new file called main.py:

touch main.py

Add the following code:

# main.py
import os
from dotenv import load_dotenv
from hiero_sdk_python import Client, Network, AccountId, PrivateKey
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
from langgraph.checkpoint.memory import MemorySaver

from hedera_agent_kit.langchain.toolkit import HederaLangchainToolkit
from hedera_agent_kit.shared.configuration import Configuration, Context, AgentMode
from hedera_agent_kit.plugins import (
    core_account_plugin,
    core_account_query_plugin,
    core_token_plugin,
    core_consensus_plugin,
)

load_dotenv()

def main():
    # Hedera client setup (Testnet by default)
    account_id = AccountId.from_string(os.getenv("ACCOUNT_ID"))
    private_key = PrivateKey.from_string(os.getenv("PRIVATE_KEY"))
    client = Client(Network(network="testnet"))
    client.set_operator(account_id, private_key)

    # Prepare Hedera toolkit
    hedera_toolkit = HederaLangchainToolkit(
        client=client,
        configuration=Configuration(
            tools=[],  # Empty = load all tools from plugins
            plugins=[
                core_account_plugin,
                core_account_query_plugin,
                core_token_plugin,
                core_consensus_plugin,
            ],
            context=Context(
                mode=AgentMode.AUTONOMOUS,
                account_id=str(account_id),
            ),
        ),
    )

    # Fetch tools from toolkit
    tools = hedera_toolkit.get_tools()

    llm = ChatOpenAI(
        model="gpt-4o-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    agent = create_react_agent(
        model=llm,
        tools=tools,
        checkpointer=MemorySaver(),
    )

    print("Sending a message to the agent...")

    response = agent.invoke(
        {"messages": [{"role": "user", "content": "what's my balance?"}]},
        config={"configurable": {"thread_id": "1"}},
    )

    print(response["messages"][-1].content)

if __name__ == "__main__":
    main()

4 – Run Your "Hello Hedera Agent Kit" Example

From the root directory, run your example agent:

python main.py

If you would like, try adding in other prompts to the agent to see what it can do:

# original
response = agent.invoke(
    {"messages": [{"role": "user", "content": "what's my balance?"}]},
    config={"configurable": {"thread_id": "1"}},
)

# or
response = agent.invoke(
    {"messages": [{"role": "user", "content": "create a new token called 'TestToken' with symbol 'TEST'"}]},
    config={"configurable": {"thread_id": "1"}},
)

# or
response = agent.invoke(
    {"messages": [{"role": "user", "content": "transfer 5 HBAR to account 0.0.1234"}]},
    config={"configurable": {"thread_id": "1"}},
)

# or
response = agent.invoke(
    {"messages": [{"role": "user", "content": "create a new topic for project updates"}]},
    config={"configurable": {"thread_id": "1"}},
)

To get other Hedera Agent Kit tools working, take a look at the example agent implementations at https://github.com/hashgraph/hedera-agent-kit-py/tree/main/python/examples

---

About the Agent Kit

Agent Execution Modes

This tool has two execution modes with AI agents; autonomous execution and return bytes:

Mode	Description
AgentMode.AUTONOMOUS	The transaction will be executed autonomously using the operator account.
AgentMode.RETURN_BYTES	(Coming Soon) The transaction bytes will be returned for the user to sign and execute.

Hedera Plugins & Tools

The Hedera Agent Kit provides a set of tools, bundled into plugins, to interact with the Hedera network. See how to build your own plugins in docs/HEDERAPLUGINS.md

Currently, the following plugins are available:

Core Account Plugin: Tools for Hedera Account Service operations

• Transfer HBAR
• Create, Update, Delete Account
• Approve and Delete Allowances

Core Consensus Plugin: Tools for Hedera Consensus Service (HCS) operations

• Create, Update, Delete Topic
• Submit a message to a Topic

Core Token Plugin: Tools for Hedera Token Service operations

• Create Fungible and Non-Fungible Tokens
• Mint Tokens
• Associate and Dissociate Tokens
• Airdrop Fungible Tokens
• Transfer with Allowances

Core EVM Plugin: Tools for EVM smart contract operations

• Create and Transfer ERC-20 Tokens
• Create and Transfer ERC-721 Tokens

Core Query Plugins: Tools for querying Hedera network data

• Get Account Info and HBAR Balance
• Get Token Info and Balances
• Get Topic Info
• Get Transaction Records
• Get Exchange Rate

See more in docs/HEDERAPLUGINS.md and docs/HEDERATOOLS.md

---

Creating Plugins & Contributing

• You can find a guide for creating plugins in docs/HEDERAPLUGINS.md

• If you would like to contribute and suggest improvements for the Python SDK, see CONTRIBUTING.md for details on how to contribute to the Hedera Agent Kit.

---

License

Apache 2.0

---

Credits

Special thanks to the developers of the Stripe Agent Toolkit who provided the inspiration for the architecture and patterns used in this project.