Mem0 Cloud Memory

Mem0 Cloud Memory connects an agent to your Mem0 Cloud account, an external service specialised in memory. The agent can save important facts about each user there (their preferences, their context, what they have told you) and look them up when it needs them in later conversations.

This memory keeps individual, relevant facts, not the full thread of messages. Use it when what matters is that the agent gets to know each user over time.

When to use it

• A sales assistant must remember each prospect’s sector, size and interests across all their conversations.
• An internal HR assistant must remember each employee’s office and department without asking again.
• Your company already uses Mem0 Cloud and you want your agents to share that memory.

Configuration

Before you start you need a Mem0 Cloud account and a credential of the Mem0 API Key service with that account’s key. See Credentials.

Field	What it does
Credential (required)	The credential of the Mem0 API Key service. Pick one with Choose an option or create one with Add new credential.

Advanced options

Field	What it does
Session ID (required)	Identifies whom the memories belong to. Use a different value for each user or customer, for example their customer number, so their facts don’t mix.
Memory Retrieval Limit (required)	Default: 5. You normally don’t need to change it.
Host	The Mem0 Cloud address. Default: https://api.mem0.ai. Change it only if Mem0 gives you a different one.
Organization Name	Optional. The organisation of your Mem0 Cloud account where memories are stored.
Project Name	Optional. The Mem0 Cloud project where memories are stored, useful to keep different assistants apart.

Output

Memory is the configured memory. Connect it to the Memory input of an agent such as Agent, Simple Agent or Deep Agent. That input appears when you turn on Use memory in the agent’s Advanced tab.

With this memory connected, the agent gains the ability to save an important fact, search what it has saved and retrieve a specific fact. It decides when to do so based on the conversation.

It does not keep the conversation thread

With Mem0 Cloud Memory connected, the agent does not keep the literal messages of the conversation between runs, only the facts it decides to save. If you need it to follow the thread of each conversation, use Postgres Memory, Redis Memory or turn on Use memory without connecting any memory component.

Example

Consultoría Brezo has an assistant that serves its clients by chat:

1. Create a Mem0 API Key credential with the key of the consultancy’s Mem0 Cloud account.
2. Add Mem0 Cloud Memory, choose that credential and, in the Advanced tab, connect Session ID to the client’s identifier.
3. In the agent, turn on Use memory and connect Memory to the Memory input.
4. In the agent’s instructions, write: “Save each client’s sector and the services they are interested in”.

Weeks later, when the same client writes again, the agent remembers it is a logistics company interested in audits and doesn’t have to ask again.

Good practices

• Tell the agent in its instructions what it should and should not save, for example “never save bank details”.
• Don’t use the same Session ID for every user: they would share memories.

Related components

• Postgres Memory
• Redis Memory
• Agent
• Set Session ID