agentroute 1.0.0

Build, deploy, and monetize AI agents

agentroute (Python SDK)

Build, deploy, and monetize AI agents. Phase 1 (Foundation) ships the core Agent + @agent.tool loop against any OpenAI-compatible model (OpenRouter default, plus Ollama and custom HTTP endpoints).

Install

pip install agentroute

Quick start

Layer 0 — three-line hello world

from agentroute import Agent

agent = Agent("my-bot", model="claude-sonnet-4")
print(agent.run("Tell me a joke"))

Set AGENTROUTE_API_KEY (or OPENROUTER_API_KEY) to an OpenRouter key. One key works for every model string (claude-sonnet-4, gpt-4o, gemini-2.0-flash, deepseek-v3, ...).

Layer 1 — add a tool

from agentroute import Agent

agent = Agent("weather-bot", model="claude-sonnet-4")

@agent.tool
def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return "Sunny, 22C"

print(agent.run("What's the weather in Zurich?"))

The SDK reads the function's name, type hints, and docstring — no extra schema is required.

Async

import asyncio
from agentroute import Agent

async def main() -> None:
    agent = Agent("bot", model="claude-sonnet-4")
    result = await agent.arun("hi")
    print(result.output)

asyncio.run(main())

Local models (Ollama)

agent = Agent("local", model="ollama/llama3")
print(agent.run("hi"))

Development

cd packages/python
pip install -e '.[dev]'
pytest            # unit tests
pytest -m integration  # live tests (requires API key)
ruff check src tests
mypy src/agentroute

Phase 1 scope: Agent, Tool, Context, Result, Event, ModelCloud, resolve_model(), Config, exceptions. Memory, structured output, multi-agent, guards, MCP, A2A, and deployment land in later phases.