synkro

# Synkro

![](https://static.scarf.sh/a.png?x-pxid=f08f2a53-e0cf-4291-83f4-b518f620bf69)
[![PyPI version](https://img.shields.io/pypi/v/synkro.svg?cacheSeconds=3600)](https://pypi.org/project/synkro/)
[![Downloads](https://static.pepy.tech/badge/synkro)](https://pepy.tech/project/synkro)
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![Documentation](https://img.shields.io/badge/docs-synkro.sh-purple.svg)](https://synkro.sh/docs)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)

Synkro reads your policy documents, auto-generates diverse test scenarios, runs multi-turn conversations against your agent with a simulated user, and verifies every response against the policy rules. No hand-written test cases. No manual review.

## Installation

```bash
pip install synkro
```

## Simulate Your Agent

```python
import synkro

def my_agent(messages):
    resp = openai.chat.completions.create(model="gpt-4o", messages=messages)
    return resp.choices[0].message.content

results = synkro.simulate(
    agent=my_agent,
    policy="All refunds require a receipt. Max refund is $500.",
    scenarios=10,
    turns=3,
)

print(results.pass_rate)  # 0.85
print(results.passed)     # 8 of 10 passed

for r in results:
    if not r.passed:
        print(r.scenario.description, r.issues)
```

Works with any agent — just pass a callable that takes messages and returns a string. Sync or async.

## Generate Training Data

Use the same pipeline to generate training datasets for fine-tuning:

```python
import synkro

dataset = synkro.generate(
    "All refunds require a receipt. Max refund is $500.",
    traces=100,
)
dataset.save("training.jsonl")
```

Or use the CLI:

```bash
synkro generate policy.pdf --traces 50

# Quick demo with built-in policy
synkro demo
```

## Features

- **Agent simulation** — Test agents against auto-generated, policy-grounded scenarios
- **