Patch OpenAI
Upgrade your existing OpenAI setup with Memobase memory.
Client-Side
Use our SDKs or APIs to connect your app to a Memobase backend.
Server-Side
Deploy your own Memobase backend. It’s easier than assembling IKEA furniture.
Memobase Client
Step 1: Get Prepped
Install the SDK
Install the SDK
Find Your Project URL and Token
Find Your Project URL and Token
You’ll get these when you set up your backend. Keep them handy.
Step 2: Connect to the Backend
Instantiate the Client
Instantiate the Client
Test the Connection (Ping!)
Test the Connection (Ping!)
Step 3: User Management
Create, read, update, and delete users.Create a User
Create a User
Get a User
Get a User
Step 4: Insert Message
Now that you have a user, let’s give them some memories.Insert Data (e.g. Chats)
Insert Data (e.g. Chats)
Step 5: Memory Operations
This is where the magic happens. Memobase extracts and stores memories for each user.flush: User data is held in a buffer. If the buffer gets too large or remains idle, it gets processed. You can also trigger this manually.
Flush (e.g., after a chat session ends)
Flush (e.g., after a chat session ends)
- Get Personalized Context:
context API
context API
- Pack the context into your system prompt:
Insert personalized contex
Insert personalized contex
Memobase Backend
We offer an open-source solution with a Docker backend to launch your own instance. You can usedocker-compose to launch the backend in one command.
Memobase Cloud
We also offer a hosted cloud service, with free tier and nice dashboard.Memobase Cloud Dashboard