Glossary · Agentic AI
What is Agent memory? Definition and meaning
Stores that let an agent recall facts, preferences and past work, from short-term context to long-term notes.
Definition
Agent memory: Stores that let an agent recall facts, preferences and past work, from short-term context to long-term notes.
In short: Information an agent keeps across steps and sessions.
When it is used
Continuity across conversations and across long tasks.
Where it fits
Agent memory belongs to Coding and computer agents in the Agentic AI topic. These are the other terms in the same group:
- Claude Code: A tool that works in a terminal, desktop or browser, reads a codebase, edits files, runs commands and tests, and keeps working over many steps.
- Computer use: The model sees the screen and clicks, types and scrolls to use applications.
- Browser agents: An agent drives a browser to read pages, fill forms and complete flows.
- Long-running tasks: Designs for agents that run unattended for long periods, with checkpoints, task lists and recovery.
- Skills: Folders of instructions, scripts and resources that an agent loads when a task needs them.
- Sub-agents: An agent spawns focused helpers whose work returns as a short result, which keeps the main context clean.
Learn more
The full guide to Agent memory explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: Agent identity and delegation · Next term: Agentic commerce