trytet-client 0.2.0

Official Python SDK for the Trytet Engine — sub-millisecond Wasm sandbox for AI agents

Trytet Python SDK

Official Python client for the Trytet Engine — a sub-millisecond, hyper-ephemeral Wasm execution substrate for AI agents.

Installation

pip install trytet-client

Quick Start

import asyncio
from trytet_client import TrytetClient, TetExecutionRequest

async def main():
    async with TrytetClient(base_url="http://localhost:3000") as client:
        # Execute a Wasm payload
        with open("my_agent.wasm", "rb") as f:
            payload = list(f.read())

        result = await client.execute(TetExecutionRequest(
            payload=payload,
            allocated_fuel=1_000_000,
            alias="my-agent",
        ))
        print(f"Status: {result.status}")
        print(f"Fuel consumed: {result.fuel_consumed}")

        # List available MCP tools
        tools = await client.list_tools()
        for tool in tools:
            print(f"  {tool.name}: {tool.description}")

        # Invoke a cartridge
        from trytet_client import CartridgeInvocation
        cart_result = await client.invoke_cartridge(CartridgeInvocation(
            component_id="js-evaluator",
            payload="2 + 2",
            fuel=1_000_000,
        ))
        print(cart_result.output)

asyncio.run(main())

Features

• Full async HTTP client with retry and backoff
• MCP (Model Context Protocol) support — tools, resources, prompts
• Cartridge management API
• WebSocket telemetry streaming
• Pydantic models for all API types
• Type-safe request/response handling