Metadata-Version: 2.4
Name: memorylayer-server
Version: 0.0.3
Summary: MemoryLayer.ai - API-first memory infrastructure for LLM-powered agents (open source core)
Project-URL: Homepage, https://memorylayer.ai
Project-URL: Documentation, https://docs.memorylayer.ai
Project-URL: Repository, https://github.com/scitrera/memorylayer
Project-URL: Issues, https://github.com/scitrera/memorylayer/issues
Author-email: Scitrera <open-source-team@scitrera.com>
License: Apache 2.0
Keywords: agents,ai,llm,memory,rag,vector-search
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.12
Requires-Dist: aiosqlite>=0.22.1
Requires-Dist: click>=8.3.1
Requires-Dist: fastapi>=0.128.7
Requires-Dist: httpx>=0.28.1
Requires-Dist: numpy>2.0.0
Requires-Dist: pydantic-settings>=2.12.0
Requires-Dist: pydantic>=2.12.5
Requires-Dist: python-multipart>=0.0.22
Requires-Dist: scitrera-app-framework>=0.0.67
Requires-Dist: scitrera-rt-data>=0.0.7
Requires-Dist: sqlalchemy[asyncio]>=2.0.46
Requires-Dist: sqlite-vec>=0.1.7a2
Requires-Dist: uvicorn[standard]>=0.30.0
Provides-Extra: all
Requires-Dist: anthropic>=0.79.0; extra == 'all'
Requires-Dist: google-genai>=1.62.0; extra == 'all'
Requires-Dist: mypy>=1.19.1; extra == 'all'
Requires-Dist: openai>=2.18.0; extra == 'all'
Requires-Dist: pytest-asyncio>=1.3.0; extra == 'all'
Requires-Dist: pytest-cov>=7.0.0; extra == 'all'
Requires-Dist: pytest>=9.0.2; extra == 'all'
Requires-Dist: respx>=0.22.0; extra == 'all'
Requires-Dist: ruff>=0.15.0; extra == 'all'
Requires-Dist: sentence-transformers>=5.2.2; extra == 'all'
Requires-Dist: smolagents<2.0,>=1.0; extra == 'all'
Requires-Dist: tiktoken>=0.12.0; extra == 'all'
Provides-Extra: anthropic
Requires-Dist: anthropic>=0.79.0; extra == 'anthropic'
Provides-Extra: context
Requires-Dist: smolagents<2.0,>=1.0; extra == 'context'
Provides-Extra: dev
Requires-Dist: mypy>=1.19.1; extra == 'dev'
Requires-Dist: pytest-asyncio>=1.3.0; extra == 'dev'
Requires-Dist: pytest-cov>=7.0.0; extra == 'dev'
Requires-Dist: pytest>=9.0.2; extra == 'dev'
Requires-Dist: respx>=0.22.0; extra == 'dev'
Requires-Dist: ruff>=0.15.0; extra == 'dev'
Provides-Extra: embeddings
Requires-Dist: google-genai>=1.62.0; extra == 'embeddings'
Requires-Dist: openai>=2.18.0; extra == 'embeddings'
Requires-Dist: sentence-transformers>=5.2.2; extra == 'embeddings'
Requires-Dist: tiktoken>=0.12.0; extra == 'embeddings'
Provides-Extra: google
Requires-Dist: google-genai>=1.62.0; extra == 'google'
Provides-Extra: llm
Requires-Dist: anthropic>=0.79.0; extra == 'llm'
Requires-Dist: google-genai>=1.62.0; extra == 'llm'
Requires-Dist: openai>=2.18.0; extra == 'llm'
Requires-Dist: tiktoken>=0.12.0; extra == 'llm'
Provides-Extra: local
Requires-Dist: sentence-transformers>=5.2.2; extra == 'local'
Provides-Extra: openai
Requires-Dist: openai>=2.18.0; extra == 'openai'
Requires-Dist: tiktoken>=0.12.0; extra == 'openai'
Description-Content-Type: text/markdown

# MemoryLayer.ai

**API-first memory infrastructure for LLM-powered agents.**

MemoryLayer provides cognitive memory capabilities for AI agents, including episodic, semantic, procedural, and working
memory with vector-based retrieval and graph-based associations.

## Features

- **Cognitive Memory Architecture**: Episodic, Semantic, Procedural, and Working memory types
- **Vector Search**: SQLite with sqlite-vec for efficient similarity search
- **Graph Associations**: 25+ relationship types for memory connections
- **MCP Integration**: Model Context Protocol server for Claude and other LLMs
- **REST API**: FastAPI-based HTTP server
- **Multiple Embedding Providers**: OpenAI, Qwen3-VL, vLLM, sentence-transformers

## Installation

```bash
# Basic installation
pip install memorylayer-server

# With OpenAI embeddings
pip install memorylayer-server[openai]

# With local embeddings (sentence-transformers)
pip install memorylayer-server[local]

# With multimodal support (Qwen3-VL)
pip install memorylayer-server[multimodal]

# All embedding providers
pip install memorylayer-server[embeddings]
```

## Quick Start

### HTTP Server

```bash
# Start the REST API server
memorylayer serve --port 8080
```

### MCP Server

```bash
# Start MCP server for Claude integration
memorylayer mcp
```

## API Usage

```python
from memorylayer import MemoryLayerClient

client = MemoryLayerClient(base_url="http://localhost:8080")

# Store a memory
memory = await client.remember(
    content="User prefers Python for backend development",
    type="semantic",
    importance=0.8,
    tags=["preferences", "programming"]
)

# Recall memories
results = await client.recall(
    query="What programming languages does the user like?",
    limit=5
)
```

## License

Apache 2.0 License - see [LICENSE](LICENSE) for details.
