AI engineering glossary · Agents tools MCP
What is agent memory?
Agent memory: Any way an agent keeps information beyond a single model call, such as the running conversation, notes saved to a file or facts stored in a database. Memory lets the agent stay consistent over long tasks and across sessions.
Agent memory: an example
A shopping assistant remembers that the user prefers vegetarian restaurants under Rs 500 per person.
Related terms
More Agents tools MCP terms
- Agent observability
- Agent skills
- Agent trace
- Agent-to-agent protocol
- Agentic workflow
- AI agent
- Approval gate
- AutoGen
Where you learn it
Agent memory is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.