Open Source Agent Simulation SDK

Ship Reliable AI Agents

A modern testing framework that transforms AI agents into production-grade systems.

$pip install tenro

from tenro import link_agent
from tenro.simulate import llm, agent

@link_agent
def support_agent(request: str) -> str:
    return call_llm(request)

def test_cancel_order(construct):
    llm.simulate(Provider.OPENAI, response="Order #123 cancelled")

    support_agent("Cancel order #123")

    agent.verify(support_agent, result="Order #123 cancelled")

How it works

Link. Simulate. Verify.

Battle test your agents. Full control, zero API costs.

Link

@link_agent | @link_tool

Decorate your agents, tools, and LLM calls.

Simulate

llm.simulate(...)

Control external responses. No API calls during tests.

Verify

agent.verify(...)

Assert calls happened with expected inputs and outputs.

Simulation engine for agents

Test without burning through tokens. Simulate LLM responses, verify agent behavior, and run your test suite in milliseconds.

API calls in tests

100%

reproducible

not seconds

Integrations

Works with your stack

Compatible with major LLM providers and agent frameworks.

LLM Providers

OpenAI

Anthropic

Google Gemini

Agent Frameworks

LangChain

LangGraph

LlamaIndex

CrewAI

AutoGen

PydanticAI

Custom

Stay in the loop

Get early access & updates

Be the first to know about new features. No spam.