A powerful Python framework for managing and orchestrating AI agents with ease. Agentarium provides a flexible and intuitive way to create, manage, and coordinate interactions between multiple AI agents in various environments.
Installation • Quick Start • Features • Examples • Documentation • Contributing
pip install agentariumfrom agentarium import Agent
# Create agents
agent1 = Agent(name="agent1")
agent2 = Agent(name="agent2")
# Direct communication between agents
alice.talk_to(bob, "Hello Bob! I heard you're working on some interesting ML projects.")
# Agent autonomously decides its next action based on context
bob.act()- 🤖 Advanced Agent Management: Create and orchestrate multiple AI agents with different roles and capabilities
- 🔄 Autonomous Decision Making: Agents can make decisions and take actions based on their context
- 💾 Checkpoint System: Save and restore agent states and interactions for reproducibility
- 🎭 Customizable Actions: Define custom actions beyond the default talk/think capabilities
- 🧠 Memory & Context: Agents maintain memory of past interactions for contextual responses
- ⚡ AI Integration: Seamless integration with various AI providers through aisuite
- ⚡ Performance Optimized: Built for efficiency and scalability
- 🛠️ Extensible Architecture: Easy to extend and customize for your specific needs
Create a simple chat interaction between agents:
from agentarium import Agent
# Create agents with specific characteristics
alice = Agent.create_agent(name="Alice", occupation="Software Engineer")
bob = Agent.create_agent(name="Bob", occupation="Data Scientist")
# Direct communication
alice.talk_to(bob, "Hello Bob! I heard you're working on some interesting projects.")
# Let Bob autonomously decide how to respond
bob.act()Add new capabilities to your agents:
from agentarium import Agent, Action
# Define a simple greeting action
def greet(name: str, **kwargs) -> str:
return f"Hello, {name}!"
# Create an agent and add the greeting action
agent = Agent.create_agent(name="Alice")
agent.add_action(
Action(
name="GREET",
description="Greet someone by name",
parameters=["name"],
function=greet
)
)
# Use the custom action
agent.execute_action("GREET", "Bob")Save and restore agent states:
from agentarium import Agent
from agentarium.CheckpointManager import CheckpointManager
# Initialize checkpoint manager
checkpoint = CheckpointManager("demo")
# Create and interact with agents
alice = Agent.create_agent(name="Alice")
bob = Agent.create_agent(name="Bob")
alice.talk_to(bob, "What a beautiful day!")
checkpoint.update(step="interaction_1")
# Save the current state
checkpoint.save()More examples can be found in the examples/ directory.
Create agents with custom characteristics:
agent = Agent.create_agent(
name="Alice",
age=28,
occupation="Software Engineer",
location="San Francisco",
bio="A passionate developer who loves AI"
)Configure your LLM provider and credentials using a YAML file:
llm:
provider: "openai" # The LLM provider to use (any provider supported by aisuite)
model: "gpt-4" # The specific model to use from the provider
aisuite: # (optional) Credentials for aisuite
openai: # Provider-specific configuration
api_key: "sk-..." # Your API key- Agent: Core class for creating AI agents with personalities and autonomous behavior
- CheckpointManager: Handles saving and loading of agent states and interactions
- Action: Base class for defining custom agent actions
- AgentInteractionManager: Manages and tracks all agent interactions
Contributions are welcome! Here's how you can help:
- Fork the repository
- Create a new branch (
git checkout -b feature/amazing-feature) - Make your changes
- Commit your changes (
git commit -m 'feat: add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
Thanks to all contributors who have helped shape Agentarium 🫶