Mem0MemoryWriter

Write ChatMessage objects as memories to a Mem0 memory store, persisting conversation context for use in future pipeline runs.

Key Features

• Persists conversation messages to Mem0 memory storage so agents can recall past interactions.
• Supports scoping by user_id, run_id, agent_id, or app_id, allowing a single pipeline instance to serve multiple users or agents.
• The infer setting controls whether Mem0 extracts key facts from messages or stores message text verbatim.
• Returns a count of the memory items written, useful for logging and conditional branching.
• No API key is required when using a self-hosted Mem0 instance.

Configuration

1. Drag the Mem0MemoryWriter component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   • Configure the Mem0MemoryStore with your Mem0 API credentials.
   • Set infer to true to have Mem0 extract facts from messages, or false to store message text as-is.

Connections

Mem0MemoryWriter receives a list of ChatMessage objects, typically from the output of a chat generator or agent, along with optional scoping parameters such as user_id. It returns the count of written memory items through its memories_written output.

Source Code

To check this component's source code, open writer.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  Mem0MemoryWriter:
    type: haystack_integrations.components.writers.mem0.writer.Mem0MemoryWriter
    init_parameters:
      infer: true
      memory_store:
        type: haystack_integrations.memory_stores.mem0.memory_store.Mem0MemoryStore
        init_parameters:
          api_key: YOUR_MEM0_API_KEY

Using the Component in a Pipeline

# haystack-pipeline
components:
  Mem0MemoryWriter:
    type: haystack_integrations.components.writers.mem0.writer.Mem0MemoryWriter
    init_parameters:
      infer: true
      memory_store:
        type: haystack_integrations.memory_stores.mem0.memory_store.Mem0MemoryStore
        init_parameters:
          api_key: YOUR_MEM0_API_KEY

connections: []

max_runs_per_component: 100

metadata: {}

inputs:
  messages:
  - Mem0MemoryWriter.messages
  user_id:
  - Mem0MemoryWriter.user_id

outputs:
  memories_written: Mem0MemoryWriter.memories_written

Parameters

Inputs

Parameter	Type	Description
messages	List[ChatMessage]	List of ChatMessage objects to store as memories.
user_id	Optional[str]	User ID to scope the stored memories.
run_id	Optional[str]	Run ID to scope the stored memories.
agent_id	Optional[str]	Agent ID to scope the stored memories.
app_id	Optional[str]	App ID to scope the stored memories.

Outputs

Parameter	Type	Description
memories_written	int	Count of memory items stored in Mem0.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
memory_store	Mem0MemoryStore		An instance of Mem0MemoryStore to write memories to.
infer	bool	True	If True, Mem0 extracts key facts from messages. If False, Mem0 stores message text verbatim.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
messages	List[ChatMessage]		List of ChatMessage objects to store.
user_id	Optional[str]	None	User ID to scope the stored memories.
run_id	Optional[str]	None	Run ID to scope the stored memories.
agent_id	Optional[str]	None	Agent ID to scope the stored memories.
app_id	Optional[str]	None	App ID to scope the stored memories.

Related Information

• Mem0MemoryRetriever
• Pipeline Components