Metadata-Version: 2.4
Name: agentreputation
Version: 0.1.0
Summary: Python SDK for AgentTrust — trust scores and reputation for the agent-to-agent economy.
Project-URL: Homepage, https://github.com/bch1212/agenttrust-mcp
Project-URL: Repository, https://github.com/bch1212/agenttrust-mcp
Project-URL: Issues, https://github.com/bch1212/agenttrust-mcp/issues
Author-email: Brett Halverson <brett.halverson@gmail.com>
License: MIT
Keywords: a2a,agent-to-agent,agents,mcp,reputation,trust
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Internet
Classifier: Topic :: Software Development :: Libraries
Requires-Python: >=3.9
Requires-Dist: httpx>=0.26
Description-Content-Type: text/markdown

# agenttrust — Python SDK for AgentTrust

Thin Python client for the AgentTrust trust-score API.

## Install

```bash
pip install agenttrust
```

## Use

```python
from agenttrust import AgentTrustClient

client = AgentTrustClient(api_key="agenttrust-dev-...")

# Public reads (no key needed)
print(client.get_trust_score("demo-platinum-001"))
print(client.get_leaderboard(limit=5))

# Writes (require API key)
client.register_agent("my-agent", name="My Agent", capabilities=["search"])
client.record_transaction(
    from_agent="my-agent",
    to_agent="demo-platinum-001",
    amount_usd=42.0,
    success=True,
    description="data lookup",
)
```

## Self-host

```python
client = AgentTrustClient(
    api_key="...",
    base_url="https://your-agenttrust-deploy.up.railway.app",
)
```

## License

MIT — see the [main repo](https://github.com/bch1212/agenttrust-mcp) for full details.
