Metadata-Version: 2.4
Name: agentmem-py
Version: 0.2.1
Summary: Memory API for AI agents — Postgres-native, graph memory included, no Neo4j
Project-URL: Homepage, https://agentmem-dashboard.vercel.app
Project-URL: Repository, https://github.com/rooney011/agentmem-sdk
Project-URL: Issues, https://github.com/rooney011/agentmem-sdk/issues
Author-email: rooney011 <bvsa2020@gmail.com>
License: Apache-2.0
Keywords: agents,ai,crewai,langchain,mem0,memory,postgres,vector
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software 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
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Requires-Dist: httpx>=0.24.0
Provides-Extra: async
Requires-Dist: httpx[http2]>=0.24.0; extra == 'async'
Provides-Extra: dev
Requires-Dist: pytest; extra == 'dev'
Requires-Dist: pytest-asyncio; extra == 'dev'
Requires-Dist: python-dotenv; extra == 'dev'
Description-Content-Type: text/markdown

# agentmem-py

Python SDK for [AgentMem](https://agentmem-dashboard.vercel.app) — the memory API for AI agents.

## Install

```bash
pip install agentmem-py
```

## Usage

```python
import os
from agentmem_py import MemoryStore

mem = MemoryStore(api_key=os.environ["AGENTMEM_API_KEY"])

mem.write(content="user prefers dark mode", agent_id="agent-1", scope="user")
hits = mem.search(query="theme preference", agent_id="agent-1", top_k=5)
for h in hits:
    print(h.score, h.content)
```

### Async

```python
import asyncio
from agentmem_py import AsyncMemoryStore

async def main():
    async with AsyncMemoryStore(api_key="...") as mem:
        await mem.write(content="hello", agent_id="agent-1")

asyncio.run(main())
```

## Self-hosting

Pass `base_url=` to point at your own deployment:

```python
mem = MemoryStore(api_key="...", base_url="https://your-host.example.com/functions/v1/api")
```

## License

[Apache-2.0](../LICENSE)
