Metadata-Version: 2.4
Name: enmem-client
Version: 0.4.21
Summary: Python client for enn-memory - Long-term memory system for AI agents
Author: enn-memory Team
Requires-Python: >=3.10
Requires-Dist: aiohttp-retry>=2.8.3
Requires-Dist: aiohttp>=3.8.4
Requires-Dist: pydantic>=2
Requires-Dist: python-dateutil>=2.8.2
Requires-Dist: typing-extensions>=4.7.1
Requires-Dist: urllib3<3.0.0,>=2.1.0
Provides-Extra: test
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'test'
Requires-Dist: pytest>=7.0.0; extra == 'test'
Requires-Dist: requests>=2.28.0; extra == 'test'
Description-Content-Type: text/markdown

# enmem-client

Python client for **enn-memory** - Long-term memory system for AI agents.

## Installation

```bash
pip install enmem-client
```

## Quick Start

```python
from enmem_client import Enmem

# Initialize client
client = Enmem(base_url="http://localhost:8888")

# Store a memory
client.retain(
    bank_id="my-bank",
    content="User prefers Python programming"
)

# Search memories
results = client.recall(
    bank_id="my-bank",
    query="What does the user like?"
)
for r in results.results:
    print(r.text)

# Generate contextual answer
answer = client.reflect(
    bank_id="my-bank",
    query="What are the user's interests?"
)
print(answer.text)
```

## Documentation

Full documentation: https://github.com/enn-memory/ennmem-docs

## Features

- **Retain**: Store memories with automatic fact extraction
- **Recall**: Search memories using semantic similarity
- **Reflect**: Generate contextual responses using memories and mental models
- **Mental Models**: Create living documents that auto-refresh
- **Directives**: Set hard rules for reflect operations
- **Bank Management**: Create and configure memory banks

## License

MIT
