Enki Runtime

Python bindings for the Enki agent runtime, providing a powerful framework for building AI agents with memory, tools, and HTTP server capabilities.

Features

• Agent Runtime: Run and manage AI agents with built-in lifecycle management
• Memory System: Pluggable memory stores with in-memory and custom implementations
• Tool System: Decorator-based tool registration for agent capabilities
• HTTP Server: Built-in HTTP API server for agent interactions
• Multi-Agent Support: Run multiple agents concurrently with dynamic registration

Installation

pip install enki-runtime

Quick Start

Basic Agent

from enki_sdk import Agent, tool
import enki_runtime

@Agent
class MyAgent:
    """A simple agent example"""
    
    @tool
    def greet(self, name: str) -> str:
        """Greet someone by name"""
        return f"Hello, {name}!"

# Create and run agent
config = enki_runtime.AgentConfig(
    name="my-agent",
    model="gpt-4",
    system_prompt="You are a helpful assistant."
)

agent = MyAgent(config)
response = agent.chat("Say hello to Alice")
print(response)

Memory Store

from enki_sdk import InMemoryStore

# Use built-in memory store
memory = InMemoryStore()
memory.save("key", "value")
value = memory.get("key")

HTTP Server

from enki_runtime import EnkiRuntime

# Start runtime with HTTP server
runtime = EnkiRuntime()
runtime.start_server("0.0.0.0", 8000)

# Register agents dynamically
runtime.register_agent("agent-1", agent_config)

Documentation

For more examples and detailed documentation, see the examples directory.

Requirements

• Python >= 3.8
• Rust (for building from source)

License

MIT License - see LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit issues or pull requests.