Agent Memory
Systems that allow AI agents to store, retrieve, and use information across interactions and sessions. Agent memory encompasses short-term context within a conversation and long-term persistence across separate sessions.
Agent memory is what transforms a stateless language model into a persistent assistant that learns and adapts over time. Short-term memory (conversation context) lets agents maintain coherence within a session. Long-term memory (vector stores, databases, or key-value stores) lets agents recall user preferences, past interactions, and accumulated knowledge across sessions.
For growth products powered by AI, memory is the foundation of personalization. An onboarding agent that remembers where a user left off, a support agent that knows a customer's history, or a sales agent that tracks deal context across touchpoints all depend on well-designed memory systems. The engineering challenge is deciding what to remember, how to retrieve it efficiently, and when to forget. Storing everything is expensive and can pollute context with irrelevant information. Implement memory with clear schemas, relevance scoring on retrieval, and periodic garbage collection of stale entries.
Related Terms
Model Context Protocol (MCP)
An open standard that defines how AI models connect to external tools, data sources, and services through a unified interface. MCP enables agents to dynamically discover and invoke capabilities without hardcoded integrations.
Tool Use
The ability of an AI model to invoke external functions, APIs, or services during a conversation to perform actions beyond text generation. Tool use transforms language models from passive responders into active problem solvers.
Function Calling
A model capability where the AI generates structured JSON arguments for predefined functions rather than free-form text. Function calling provides a reliable bridge between natural language understanding and programmatic execution.
Agentic Workflow
A multi-step process where an AI agent autonomously plans, executes, and iterates on tasks using tools, reasoning, and feedback loops. Agentic workflows go beyond single-turn interactions to accomplish complex goals.
ReAct Pattern
An agent architecture that interleaves Reasoning and Acting steps, where the model thinks about what to do next, takes an action, observes the result, and repeats. ReAct combines chain-of-thought reasoning with tool use in a unified loop.
Chain of Thought
A prompting technique that instructs the model to break down complex problems into sequential reasoning steps before producing a final answer. Chain of thought significantly improves accuracy on math, logic, and multi-step tasks.