AI Vocabulary · 05 Agents
What is Memory?
Notes an AI app saves and reloads so it can carry information from one conversation to the next.
Models don't remember anything between conversations. Each new chat starts empty. "Memory" in AI apps is a feature built around the model: the app saves facts, preferences or summaries and adds them to the context of later chats.
That can be very useful, because you don't have to explain your role or preferences every time. It can also be wrong or outdated, and it can surface things you didn't expect in an unrelated conversation.
Why it matters for you
Check what your AI tools remember about you and your work, and whether memory is shared across a team. Clear out what is wrong; outdated memories quietly shape answers.
Own it
Memory is data about you or your company, stored by someone. Know where it lives, whether you can view, export and delete it, and keep your most important context in documents you control.
Where it comes from
Researchers explored long-term memory for language models for years, for example in the 2023 MemGPT project, which borrowed ideas from how operating systems manage memory. For everyday users, memory arrived in February 2024, when OpenAI began testing a ChatGPT feature that remembers facts across chats, with controls to view and delete them (OpenAI).
Related
Your AI Learning Hub
Learn the whole AI Vocabulary, step by step, and build with it. Build it. Own it.