Agent Memory
In one line
Agent memory is the storage and retrieval layer that lets an agent remember past conversations and task results, and reuse them in future steps.
Going deeper
By default an agent only knows what fits in its context window. To remember yesterday's request today, it needs a memory layer. The common split is short-term (current session), long-term (vector DB or distilled summaries) and episodic (a log of past tasks).
For marketing teams memory decides how much of the customer relationship the agent can actually use. Recommendations that remember preferences and history convert better — but they pull privacy and security questions in alongside.
Implementation-wise, the line between memory and RAG (retrieval-augmented generation) keeps blurring. Both 'fetch the right information and inject it into the LLM', so most real systems design them as one thing.
Related terms
AI Agent
An AI agent is an LLM-driven system that takes a goal, plans the steps, calls the tools it needs and runs the task end-to-end with limited human input.
LLMRAG
RAG (Retrieval-Augmented Generation) lets an LLM fetch external documents at answer time and ground its response in them — the technique behind ChatGPT Search, Perplexity and most AI search products.
LLMContext Window
The context window is the maximum number of tokens an LLM can take in at once — it defines how much content the model can consider in a single prompt.
AI AgentReAct
ReAct (Reasoning + Acting) is the classic agent pattern where an LLM loops through Thought, Action and Observation steps — reasoning out loud and calling tools as it goes.
LLMLLM
A large language model (LLM) is a neural network trained on massive text corpora to understand and generate human language — the engine behind ChatGPT, Claude, Gemini and similar products.
How does your brand show up in AI answers?
Villion measures how your brand appears across ChatGPT, Perplexity and AI Overviews, then automates the work that lifts citation rate and share of voice.
Get a free audit