Agents & tools · Glossary term

What is Agent Memory?

Information stored outside the model and selected for use in later agent steps, such as prior decisions, user preferences, task episodes, or verified facts.

Why does Agent Memory matter?

It gives an agent continuity beyond one context window without forcing every past event into every prompt.

Agent Memory in practice

Store a compact task outcome with provenance, retrieve it only when relevant, and let the user inspect or correct durable personal information.

What is the common confusion about Agent Memory?

Agent memory is not the same as agent state. State tracks the current run; memory preserves selected information for possible future runs.

Learn Agent Memory in the course

Lessons that name Agent Memory in a title or section

  • Agent Memory — Virtual Context and Memory Paging

    Context windows are finite. Conversations, documents, and tool traces are not. The fix is OS virtual memory restated — main context is RAM, external store is disk, the agent pages between them.

    Phase 14: Agent Engineering

Covered in Phase 14: Agent Engineering.

  • Agent StateThe explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets,…
  • Context EngineeringDesigning the full information environment supplied to a model at each step, including instructions, selected files, retrieved evidence,…
  • CheckpointA durable snapshot used to resume from a known boundary. In a workflow, it stores operational state and artifact references.
  • Semantic CacheA cache that reuses a previous result when a new request is judged sufficiently similar under a chosen representation and threshold.

Sources

More terms in Agents & tools

Open the Agents & tools list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.