Metadata-Version: 2.4
Name: GuardianLayer
Version: 2.0.1
Summary: Meta-cognition layer for AI agents - prevents infinite loops, learns from failures, provides self-awareness
Author-email: Michael <contact@example.com>
Maintainer-email: Michael <contact@example.com>
License: MIT
Project-URL: Homepage, https://github.com/your-org/GuardianLayer
Project-URL: Repository, https://github.com/your-org/GuardianLayer
Project-URL: Documentation, https://guardianlayer.readthedocs.io
Project-URL: Issue Tracker, https://github.com/your-org/GuardianLayer/issues
Project-URL: Discussions, https://github.com/your-org/GuardianLayer/discussions
Project-URL: Changelog, https://github.com/your-org/GuardianLayer/blob/main/CHANGELOG.md
Project-URL: Funding (PayPal), https://www.paypal.com/paypalme/MicaPaul138
Keywords: ai,agent,loop-detection,circuit-breaker,meta-cognition,llm,langchain,autogen,mcp,model-context-protocol,ai-safety,guardrails,observability
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
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: Environment :: Console
Classifier: Operating System :: OS Independent
Classifier: Framework :: AsyncIO
Classifier: Framework :: Pydantic
Classifier: Typing :: Typed
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: aiosqlite>=0.19.0
Requires-Dist: sqlalchemy>=2.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Requires-Dist: mypy>=1.0.0; extra == "dev"
Requires-Dist: black>=23.0.0; extra == "dev"
Requires-Dist: pre-commit>=2.20.0; extra == "dev"
Provides-Extra: docs
Requires-Dist: sphinx>=5.0.0; extra == "docs"
Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "docs"
Requires-Dist: sphinx-autodoc-typehints>=1.23.0; extra == "docs"
Requires-Dist: myst-parser>=1.0.0; extra == "docs"
Provides-Extra: postgres
Requires-Dist: asyncpg>=0.28.0; extra == "postgres"
Provides-Extra: redis
Requires-Dist: redis>=4.5.0; extra == "redis"
Provides-Extra: all
Requires-Dist: GuardianLayer[postgres]; extra == "all"
Requires-Dist: GuardianLayer[redis]; extra == "all"
Dynamic: license-file

# GuardianLayer

[![PyPI](https://img.shields.io/pypi/v/GuardianLayer.svg)](https://pypi.org/project/GuardianLayer/)
[![Tests](https://github.com/your-org/GuardianLayer/actions/workflows/ci.yml/badge.svg)](https://github.com/your-org/GuardianLayer/actions)
[![Docs](https://img.shields.io/badge/docs-Sphinx-blue)](https://your-docs-url)
[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)

**GuardianLayer** is a meta-cognition layer for AI agents that prevents infinite loops, learns from failures, and provides self-awareness capabilities. It acts as a safety shield between your AI agent and external tools, ensuring robust and reliable agent behavior.

## 🌟 Key Features

### 🛡️ 5-Layer Protection System

- **Layer 0: Smart Circuit Breaker** - Three-state pattern (CLOSED/OPEN/HALF_OPEN) with automatic recovery and error classification
- **Layer 1: Loop Detection** - Hash-based O(1) detection of infinite loops and repetitive behavior
- **Layer 2: Schema Validation** - MCP-compatible tool call validation with custom hooks
- **Layer 3: Experience Learning** - Multi-tiered storage (Session/Process/Global) that learns from past successes and failures
- **Layer 4: Advice Injection** - Context-aware prompt injections to guide AI behavior

### 🚀 Performance

- **O(1) loop detection** using SHA-256 hashing instead of string comparison
- **Smart caching** for validation results and advice generation
- **Async/await support** for high-performance applications
- **Pluggable backends** - Bring your own database (PostgreSQL, Redis, etc.)

### 📊 Observability

- **Health scoring** (0-100) for each tool
- **Detailed metrics** for ROI visibility (tokens saved, loops prevented, etc.)
- **Error classification** (system vs user vs business errors)
- **Tool reliability tracking** based on historical success rates

## 📦 Installation

Install from PyPI:

```bash
pip install GuardianLayer
```

Or install from source for development:

```bash
git clone https://github.com/your-org/GuardianLayer.git
cd GuardianLayer
pip install -e '.[dev]'
```

## 🚀 Quick Start

### Basic Usage

```python
from GuardianLayer import GuardianLayer, AdviceStyle

# Initialize the guardian
guardian = GuardianLayer(
    db_path="experience.db",
    max_repeats=2,
    advice_style=AdviceStyle.EXPERT
)

# Register MCP tools
mcp_tools = [{
    "name": "web_search",
    "description": "Search the web",
    "inputSchema": {
        "type": "object",
        "properties": {
            "query": {"type": "string"}
        },
        "required": ["query"]
    }
}]
guardian.ingest_tools(mcp_tools)

# Check a tool call before executing
tool_call = {"tool": "web_search", "arguments": {"query": "Python tutorials"}}
result = guardian.check(tool_call)

if result["allowed"]:
    # Execute the tool
    response = execute_tool(tool_call)
    # Report success/failure for learning
    guardian.report_result(tool_call, success=True)
else:
    print(f"Blocked: {result['reason']}")
    print(f"Suggestion: {result['suggestion']}")
```

### Async Usage

```python
import asyncio
from GuardianLayer import GuardianLayer

async def main():
    guardian = GuardianLayer()
    
    # Async check
    result = await guardian.check_async(tool_call)
    
    if result["allowed"]:
        response = await execute_tool_async(tool_call)
        await guardian.report_result_async(tool_call, success=True)
    
    await guardian.close_async()

asyncio.run(main())
```

### Prompt Injection for Self-Awareness

```python
# Get awareness context to inject into your LLM prompt
awareness = guardian.get_awareness_context()

prompt = f"""
You are an AI assistant.

{awareness}

User: {user_message}
"""
```

## 🏗️ Architecture

GuardianLayer uses a layered protection model:

```
┌─────────────────────────────────────┐
│      AI Agent (LLM)                 │
└─────────────┬───────────────────────┘
              │ Proposed Tool Call
              ▼
┌─────────────────────────────────────┐
│  GuardianLayer                      │
│  ┌─────────────────────────────┐    │
│  │ L0: Circuit Breaker         │    │ ← Health monitoring
│  ├─────────────────────────────┤    │
│  │ L1: Loop Detection          │    │ ← Hash-based O(1)
│  ├─────────────────────────────┤    │
│  │ L2: Schema Validation       │    │ ← MCP compatible
│  ├─────────────────────────────┤    │
│  │ L3: Experience Learning     │    │ ← SQLite/PostgreSQL
│  ├─────────────────────────────┤    │
│  │ L4: Advice Generation       │    │ ← Prompt injection
│  └─────────────────────────────┘    │
└─────────────┬───────────────────────┘
              │ ✅ Allowed / ❌ Blocked
              ▼
┌─────────────────────────────────────┐
│      External Tools/APIs            │
└─────────────────────────────────────┘
```

## 📚 Documentation

- **[Quick Start Guide](docs/quickstart.rst)** - Get started in 5 minutes
- **[Architecture](docs/architecture.rst)** - Understanding the protection layers
- **[API Reference](docs/api.rst)** - Complete API documentation
- **[Configuration](docs/configuration.rst)** - All configuration options
- **[Integration Guide](docs/integration.rst)** - Integration with LangChain, AutoGen, etc.
- **[Examples](examples/)** - Real-world usage examples

## 🔧 Advanced Features

### Custom Storage Providers

```python
from GuardianLayer import GuardianLayer
from GuardianLayer.interfaces import StorageProvider

class PostgreSQLStorageProvider(StorageProvider):
    # Implement your custom storage backend
    pass

guardian = GuardianLayer(storage_provider=PostgreSQLStorageProvider())
```

### Custom Advice Resolvers

```python
from GuardianLayer import AdviceContext

def my_custom_advice(context: AdviceContext) -> str:
    if context.failure_count > 5:
        return "🚨 CRITICAL: This tool is failing repeatedly!"
    return ""

guardian.set_custom_advice_resolver(my_custom_advice)
```

### Health Monitoring

```python
# Get health metrics for all tools
health = guardian.health_monitor.get_all_health()

for tool_name, status in health.items():
    print(f"{tool_name}: {status['score']}/100 - {status['state']}")

# Manually reset a tool's health
guardian.reset_tool("problematic_tool")
```

### Metrics and ROI

```python
# Get comprehensive metrics
metrics = guardian.get_metrics()

print(f"Loops prevented: {metrics['loops_prevented']}")
print(f"Circuit breaks: {metrics['circuit_breaks']}")
print(f"Estimated tokens saved: {metrics['tokens_saved']}")
print(f"Estimated latency saved: {metrics['latency_saved_ms']}ms")
```

## 🧪 Testing

Run the test suite:

```bash
pytest tests/ -v --cov=src
```

Run the demo examples:

```bash
python examples/demo.py
python examples/demo_v2.py
python examples/demo_cache_perf.py
```

## 🤝 Contributing

We welcome contributions! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.

### Development Setup

```bash
# Clone the repository
git clone https://github.com/your-org/GuardianLayer.git
cd GuardianLayer

# Install development dependencies
pip install -e '.[dev]'

# Run tests
pytest -v

# Run linters
ruff check src/
mypy src/
```

## 📄 License

GuardianLayer is licensed under the MIT License. See [LICENSE](LICENSE) for details.

## 🙏 Acknowledgments

- Inspired by the need for safer AI agent systems
- Built for the MCP (Model Context Protocol) ecosystem
- Designed to work with any AI framework (LangChain, AutoGen, CrewAI, etc.)

## 💖 Support the Project

If you find GuardianLayer useful, consider supporting its development:

- **PayPal**: [paypal.me/MicaPaul138](https://www.paypal.com/paypalme/MicaPaul138)
- **Litecoin**: `ltc1qr3qrxyccu5ssm22ny5ere5rl0ts0yergx6cy9c`

Your support helps maintain and improve GuardianLayer!

## 📞 Support

- **Documentation**: [https://your-docs-url](https://your-docs-url)
- **Issues**: [GitHub Issues](https://github.com/your-org/GuardianLayer/issues)
- **Discussions**: [GitHub Discussions](https://github.com/your-org/GuardianLayer/discussions)

---

**Made with ❤️ for safer AI agents**
