new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

LangChain & LangGraph · all subjects

memory/writing

2 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

In-the-hot-path memory writing approach

Creating memories during runtime (in the hot path) allows for real-time updates, making new memories immediately available for subsequent interactions. It also enables transparency by notifying users when memories are created. However, this approach increases complexity by requiring a new tool to decide what to commit to memory, can impact agent latency due to reasoning about what to save, and forces the agent to multitask between memory creation and other responsibilities, potentially affecting memory quantity and quality.

Background memory writing approach

Creating memories as a separate background task offers several advantages: it eliminates latency in the primary application, separates application logic from memory management, and allows for more focused task completion. However, it requires determining the frequency of memory writing, as infrequent updates may leave other threads without new context. Common strategies for triggering memory formation include scheduling after a set time period with rescheduling if new events occur, using a cron schedule, or allowing manual triggers by users or application logic.

Give your agent this brain