Thread-scoped memory (short term)
Operates within the boundaries of a single conversation thread.
- It is automatically managed as part of the graph state, and persisted through thread-scoped checkpoints
- This memory type retains conversation history, uploaded files, retrieved documents, and other artifacts generated during the interaction
- Think of it as the working memory that maintains context within one specific conversation, allowing the agent to reference earlier messages or actions without starting from scratch each time
Across-thread memory (long term)
This long term memory extends beyond individual conversations, creating a persistent knowledge base spanning multiple sessions.
This memory is stored as JSON documents in a memory store, organized by namespaces (like folders) and distinct keys (like filenames).
Unlike thread-scoped memory, this information persists even after conversation end, enabling the system to recall user preferences, past decisions and accumulated knowledge.
This is what allows an agent to truly learn and adapt over time, rather than treating each interaction as isolated.