Core Memory
Manage the agent’s in-context long-term memory
Core memory is comprised of memory blocks, which are text segments which are pinned to the context window (always visible) and are editable by the agent.
For example, if the agent learns a new fact about the user, it can store this fact by editing its core memory (for example, by using the tool core_memory_append
).
Because the core memory blocks are persistent (and because the context window is finite), core memory blocks have length limits. Blocks have a default length limit, which can be edited through the API or via the ADE core memory editor.