Metadata-Version: 2.4
Name: dae-client
Version: 0.1.1
Summary: Decision Audit Engine — Python SDK for AI agent audit trails
Author-email: DAE Team <dev@hermes-agent.nousresearch.com>
License: MIT
Project-URL: Homepage, https://hermes-agent.nousresearch.com
Project-URL: Repository, https://github.com/DanceNitra/hermes-tools
Keywords: ai-audit,hash-chain,compliance,decision-audit,langchain
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.11
Description-Content-Type: text/markdown

# DAE Client — Python SDK for Decision Audit Engine

Log, query, and verify AI agent decisions with cryptographic audit trails.

```python
from dae_client import DAE

# Auto-configure from env vars (DAE_API_URL, DAE_API_KEY)
client = DAE.from_env()

# Log a decision
client.log("my-agent",
    input={"query": "approve loan"},
    output={"decision": "approved", "amount": 50000},
    confidence=0.95,
)

# Check system health
print(client.health())

# Verify hash chain integrity
print(client.verify())

# Get CSD early-warning diagnosis
print(client.csd("my-agent"))

# Or use the decorator
@client.log_decorator(agent_id="my-agent")
def critical_func(x):
    return x * 2
```

## Installation
```bash
pip install dae-client
```

## Features
- Full API coverage: health, log, query, csd, kdi, verify, audit, pii
- Auto-retry (3x) + circuit breaker
- Decorator for zero-friction agent logging
- Typed response dataclasses with all fields
- `from_env()` for zero-config setup
