Memory

​

Framework support

​

How checkpointing works

• Conversation continuity: Maintain context between interactions
• Fault tolerance: Resume from the last successful step after a failure
• Thread isolation: Each session_id maps to a unique thread, keeping conversations separate
• Concurrent conversations: Multiple users can interact with the same agent simultaneously

​

Backend comparison

​

Quick configuration examples

• Manager UI
• Config file

1

Browse the backend catalog

Navigate to Memory Stores in the sidebar. The catalog shows backend cards: SQLite, PostgreSQL, In Memory, Vertex AI, and Database.

2

Add a backend

Click + on your backend and configure the connection details.

3

Attach to an agent

Attach the configuration to agents from the agent detail page.

• LangGraph
• ADK

Copy

Ask AI

agent:
  type: "LANGGRAPH"
  config:
    checkpointer:
      type: "postgres"
      db_url: "postgresql://user:pass@localhost:5432/dbname"

Copy

Ask AI

agent:
  type: "ADK"
  config:
    session_service:
      type: "in_memory"
    memory_service:
      type: "in_memory"

​

Best practices

• Use in-memory for development: No setup required, fastest iteration
• Use PostgreSQL or Database for production: Multi-process support, reliability, and crash recovery
• Configure thread isolation: Each conversation should have a unique session_id to prevent state leakage
• Monitor storage usage: Long-running conversations can accumulate significant state over time