Metadata-Version: 2.4
Name: velixar-langchain
Version: 0.1.0
Summary: Velixar AI memory retriever and memory module for LangChain
License: MIT
Project-URL: Homepage, https://velixarai.com
Project-URL: Documentation, https://docs.velixarai.com
Project-URL: Repository, https://github.com/velixar-ai/velixar-langchain
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: httpx>=0.24
Requires-Dist: langchain-core>=0.1

# velixar-langchain

Velixar AI memory integration for LangChain. Gives your LangChain agents persistent, cognitive memory that understands users across sessions.

## Install

```bash
pip install velixar-langchain
```

## Retriever

```python
from velixar_langchain import VelixarRetriever

retriever = VelixarRetriever(
    api_key="vx_...",
    workspace_id="ws_abc123",
)

# Use in a chain
docs = retriever.invoke("What are the user's preferences?")
```

## Memory

```python
from velixar_langchain import VelixarMemory

memory = VelixarMemory(
    api_key="vx_...",
    workspace_id="ws_abc123",
    user_id="user_1",
)

# Use with any LangChain chain
from langchain.chains import ConversationChain
chain = ConversationChain(llm=llm, memory=memory)
```

## Features

- 4-tier hierarchical memory (pinned, session, semantic, org)
- Automatic salience scoring and memory promotion
- Identity modeling and cognitive profiles
- Encrypted embeddings (AES-256-GCM)
- Cross-session persistence

## Links

- [Velixar AI](https://velixarai.com)
- [API Docs](https://docs.velixarai.com)
- [Dashboard](https://app.velixarai.com)
