✔️Quickstart

This quickstart covers:

1. Setting up the dev environment

2. Creating and running a simple agent that uses the web search tool

3. Creating and running a Web3 agent that uses the Dexscreener tool

​Setup

​1. Requirements

Python >=3.10

​2. Dev Environment

First, set up your local environment and then install the Lunet Python package.

Copy

python -m venv venv
source venv/bin/activate
pip install Lunet

​Create a Simple Web Search Agent

​1. Agent Code

Create a file named agent.py with the following Python code.

Add your OpenAI API Key.

Copy

import asyncio
from Lunet import AgentRuntime, CodeAgent
from Lunet .clients import SimpleMessageClient
from Lunet.core_agent import LiteLLMModel, DuckDuckGoSearchTool

# Set up the model (replace with your API key)
model = LiteLLMModel(model_id="gpt-4o", api_key="<YOUR_OPENAI_API_KEY>")

# Create the AI agent with web search capabilities
agent = CodeAgent(
    model=model,
    tools=[DuckDuckGoSearchTool()],
)

# Define a simple terminal client so you can chat with the agent
client = SimpleMessageClient("What is the capital of Estonia?")

# Set up and run the agent runtime
runtime = AgentRuntime(
    agent=agent,
    inputs=[client],
    outputs=[client],
)

asyncio.run(runtime.run())

​Running the Agent

Execute the script:

Copy

python agent.py

When the agents starts to execute the task, it prints the output similar to this one:

Copy

╭────────────────────────────────── New run ───────────────────────────────────╮
│                                                                              │
│ What is the capital of Estonia?                                              │
│                                                                              │
╰─ LiteLLMModel - gpt-4o ──────────────────────────────────────────────────────╯
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Step 1 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 ─ Executing parsed code: ─────────────────────────────────────────────────────
  capital_estonia = web_search(query="capital of Estonia")
  print(capital_estonia)
 ──────────────────────────────────────────────────────────────────────────────

Which will be followed by more steps until the results reaches the output

Copy

======== simple_message_client.post_output ========
request: content='What is the capital of Estonia?'
response: content='Tallinn'

​How it Works

This simple agent receives a question from the client and executes a series of reasoning steps to provide an answer. It autonomously determines when to search the web.

It leverages:

• gpt-4o model from OpenAI for agent reasoning.

• SimpleMessageClient to send and receive messages.

• AgentRuntime to connect the agent to the client and execute tasks.

• DuckDuckGoSearchTool for web-based information retrieval.

​Create a Web3 Agent

​Create Wallet

Before creating a Web3 agent, you’ll need a Solana wallet. You can either create a new one or import an existing wallet.

​Create a New Wallet

Use the LunetCLI to create a new wallet:

Copy

Lunet wallet create --path <YOUR_SOLANA_KEYPAIR_PATH>

And get airdropped by running:

Copy

Lunet wallet airdrop

For details about how to use the wallet, see wallet setup.

​Agent Code

Let’s extend the web search agent with Web3 capabilities to fetch real-time market data and execute an onchain swap.

Modify your script to include:

Copy

from Lunet.tools.web3.onchain.solana import raydium
from Lunet.tools.web3.market_data import dexscreener

We’ll use Dexscreener to fetch real-time market data and Raydium for executing token swaps based on market conditions.

Dexscreener is a popular Web3 platform for monitoring cryptocurrency market data including prices, trading volumes, and new token listings.

Raydium is Solana’s leading decentralized exchange (DEX) that enables automated market making and token swaps with deep liquidity.

First, we need to initialize the Solana wallet that was created in the previous step to allow agents to access it. This wallet will be used to sign transactions and interact with the Solana blockchain.

Copy

solana_wallet = SolanaWallet(key_path=os.getenv("SOLANA_KEY_PATH"))

Next, update the CodeAgent initialization with Web3-specific tools:

Copy

agent = CodeAgent(
    model=model,
    tools=[
        dexscreener.SearchTokenPairTool(),
        raydium.SwapTokenTool(solana_wallet)
    ],
    additional_authorized_imports=["json"]
)

Note additional_authorized_imports=["json"] parameter in the CodeAgent initialization. It is required because dexscreener.SearchTokenPairTool() imports json module and the Python interpreter doesn’t allow imports by default outside of a safe list.

Now let’s update the client’s input to ask a Web3-specific question that will utilize our new market data tools:

Copy

client = SimpleMessageClient(
    "What is the price of today? Buy 0.001 SOL of if the price is below 0.5 USD"
)

​Running the Agent

Execute the script:

Copy

python agent.py

When you run the script, the agent will:

1. Fetch the current market data for token and its Raydium trading pairs

2. Check if the current price meets our condition (below 0.5 USD)

3. If the condition is met, execute a swap of 0.001 SOL to tokens

4. Output the transaction hash of the completed swap

The agent will output something

​🎉 Gratz on Building Your First Agent!

You’ve successfully built both a generic web search agent and a Web3-focused agent using Lunet.

But this is just scratching the surface - what’s next? To unlock more capabilities for your agent, check out these resources:

• Tutorials section with Agents, Client, Wallet

• Deep dive into fundamental concepts like AgentRuntime

• Real-world examples of building more complex agents

Happy coding! 🚀