Remote agents¶
μAgents can also interact remotely from different locations across the internet. All you need to know is the recipient agent's address to query it's information in the Almanac contract. See Addresses for more information about μAgent addresses.
In this example, we will simulate remote communication between agents by running two agents on different ports and terminals on the same device.
Alice¶
We will start by defining agent alice and the recipient address (bob's address in this example). Then we will include
a send function and a handler as we have learned in agent interactions:
from uagents.setup import fund_agent_if_low
from uagents import Agent, Context, Model
class Message(Model):
message: str
RECIPIENT_ADDRESS = "agent1q2kxet3vh0scsf0sm7y2erzz33cve6tv5uk63x64upw5g68kr0chkv7hw50"
alice = Agent(
name="alice",
port=8000,
seed="alice secret phrase",
endpoint=["http://127.0.0.1:8000/submit"],
)
fund_agent_if_low(alice.wallet.address())
@alice.on_interval(period=2.0)
async def send_message(ctx: Context):
await ctx.send(RECIPIENT_ADDRESS, Message(message="hello there bob"))
@alice.on_message(model=Message)
async def message_handler(ctx: Context, sender: str, msg: Message):
ctx.logger.info(f"Received message from {sender}: {msg.message}")
if __name__ == "__main__":
alice.run()
Bob¶
In a different script, we will define agent bob with just a message handler to print out alice's messages and respond to her afterward.
from uagents.setup import fund_agent_if_low
from uagents import Agent, Context, Model
class Message(Model):
message: str
bob = Agent(
name="bob",
port=8001,
seed="bob secret phrase",
endpoint=["http://127.0.0.1:8001/submit"],
)
fund_agent_if_low(bob.wallet.address())
@bob.on_message(model=Message)
async def message_handler(ctx: Context, sender: str, msg: Message):
ctx.logger.info(f"Received message from {sender}: {msg.message}")
# send the response
await ctx.send(sender, Message(message="hello there alice"))
if __name__ == "__main__":
bob.run()
Now, we first run bob and then alice from different terminals. They will register automatically in the Almanac contract using their funds. The received messages will print out in each terminal.
In bob's terminal:
In alice's terminal:
For a more complex example visit restaurant booking demo.
The Agentverse Explorer¶
μAgents can also interact remotely using a mailbox server. For example, you can use The Agentverse Explorer to find other agents and register your own.
To register agents in the Agentverse mailbox, you need to sign in at The Agentverse Explorer. Then, in the upper right corner click on your profile and select API Keys, select Create new key and name it. This will generate your own API Key that will allow you to use the mailbox server.
Then, navigate to the Mailroom tab and select + Mailbox to register an agent, you need to select a name for it and provide the agent's address. Finally, you need to define the μAgent specifying the mailbox server and the API Key
# First generate a secure seed phrase (e.g. https://pypi.org/project/mnemonic/)
SEED_PHRASE = "put_your_seed_phrase_here"
# Copy the address shown below
print(f"Your agent's address is: {Agent(seed=SEED_PHRASE).address}")
# Then sign up at https://agentverse.ai to get an API key and register your agent
API_KEY = "put_your_API_key_here"
# Now your agent is ready to join the agentverse!
agent = Agent(
name="alice",
seed=SEED_PHRASE,
mailbox=f"{API_KEY}@wss://agentverse.ai",
)
Now, you can recreate the example we showed at the begining of this section by also registering agent bob in The Agentverse Explorer.