Metadata-Version: 2.4
Name: agenttrust
Version: 0.1.0
Summary: Runtime security, observability, and compliance for AI agents
Author-email: AgentTrust <hello@agenttrust.dev>
License: MIT
Project-URL: Homepage, https://agenttrust.dev
Project-URL: Documentation, https://docs.agenttrust.dev
Project-URL: Repository, https://github.com/agenttrust/agenttrust
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
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 :: Security
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: click>=8.0
Requires-Dist: rich>=13.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: cryptography>=41.0
Provides-Extra: langchain
Requires-Dist: langchain-core>=0.1.0; extra == "langchain"
Provides-Extra: crewai
Requires-Dist: crewai>=0.1.0; extra == "crewai"
Provides-Extra: autogen
Requires-Dist: pyautogen>=0.1.0; extra == "autogen"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Provides-Extra: all
Requires-Dist: langchain-core>=0.1.0; extra == "all"
Requires-Dist: crewai>=0.1.0; extra == "all"
Requires-Dist: pyautogen>=0.1.0; extra == "all"
Dynamic: license-file

# 🛡️ AgentTrust

**Runtime security, observability, and compliance for AI agents.**

AgentTrust provides a comprehensive security layer for autonomous AI agents, offering real-time monitoring, threat detection, compliance enforcement, and cryptographic identity management.

## Quick Start (3 lines)

```python
import agenttrust

at = agenttrust.init(framework="langchain")
# That's it — monitoring is now active
```

## Installation

```bash
pip install agenttrust
```

With LangChain integration:
```bash
pip install agenttrust[langchain]
```

## CLI

```bash
# Initialize for your framework
agenttrust init --framework langchain

# Real-time monitoring dashboard
agenttrust monitor --live

# Check agent fleet status
agenttrust status

# View configuration
agenttrust config
```

## Four Security Layers

### Layer 1: AgentObserve
Traces every agent action with <5ms overhead. Tool calls, LLM invocations, chain executions — all captured.

### Layer 2: AgentProtect
Behavioral firewall with pattern-based threat detection: prompt injection, privilege escalation, data exfiltration, and behavioral drift.

### Layer 3: AgentComply
Compliance engine supporting EU AI Act, NIST RMF, ISO 42001, and SOC2. Automated audit trails and risk dashboards.

### Layer 4: AgentIdentity
Cryptographic identity management for agents. Register, verify, and compute trust scores across your agent fleet.

## License

MIT
