Programmable Memory Layer

Integrate memory into agents, apps, and workflows using an MCP-compatible interface and a clean API surface.

MCP-Compatible Interface

Protocol

The memory layer is internally MCP-compatible, with a limited public MCP interface for read/write and retrieval. Advanced orchestration and behavioral enforcement remain internal.

MCP Read/Write

Public endpoints available

API Surface

Clean, consistent endpoints.

Authentication
Memory Add
Memory Search
Usage & account
Python SDK
JavaScript SDK

Quick start examples

python
from octamem import OctaMem

client = OctaMem(api_key="YOUR_API_KEY")

client.add(
    content="Launch date set for April 15. Beta opens March 20.",
    previous_context="Q1 product planning meeting",
)
View full documentation

Use Cases

Built for the next generation of AI apps.

Chatbots

Give chatbots long-term memory across sessions and model switches.

AI Agents

Agents retain behavioral context and preferences across tasks.

Copilots

Developer copilots that remember project structure and patterns.

RAG Pipelines

Augment retrieval with structured user memory for personalized results.

Ready to integrate?

Get your API key and start building with Python, JavaScript, or the REST API.

Get API Access