Metadata-Version: 2.4
Name: limbicdb
Version: 2.1.2
Summary: Debuggable memory layer for AI agents
Author-email: Kousoyu <770668004@qq.com>
License: MIT
Project-URL: Homepage, https://github.com/Kousoyu/limbicdb
Project-URL: Repository, https://github.com/Kousoyu/limbicdb
Project-URL: Documentation, https://github.com/Kousoyu/limbicdb
Keywords: ai,memory,debuggable,agents,llm
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Requires-Python: >=3.8
Description-Content-Type: text/markdown

# LimbicDB Python SDK

> Debuggable AI Memory for Python

Your AI is not wrong. Its memory is.

LimbicDB makes AI memory **observable, explainable, and debuggable**.

## Installation

```bash
pip install limbicdb
```

> **Note**: This package requires [LimbicDB](https://github.com/Kousoyu/limbicdb) to be installed locally.
> The Python SDK is a thin wrapper around the LimbicDB CLI.

## Quick Start

```python
from limbicdb import Memory

# Initialize memory with default path
memory = Memory()

# Explain memory retrieval decisions
explanation = memory.explain("anime")
print(explanation)

# Check for conflicts
if explanation["conflicts"]:
    print("⚠️  Conflicting memories detected!")
```

## Core Features

- **🔍 Inspect Memory**: See what your AI actually remembers
- **⚠️ Detect Conflicts**: Identify contradictory information automatically  
- **🧠 Explain Decisions**: Understand why specific memories were chosen
- **🛠️ Debug Behavior**: Fix AI inconsistencies at the memory level

## Integration

Works seamlessly with:
- LangChain
- AutoGen  
- Custom AI agents

## Philosophy

Memory should not be a black box. LimbicDB makes AI memory observable, explainable, and controllable.

## License

MIT
