Personal memory (AI assistant)

Personal memory in AI assistants is the per-user persistent context — preferences, facts, history — that the assistant retains across sessions to personalise its behaviour and answers.

Personal memory turned consumer AI assistants from one-shot chatbots into ongoing relationships in 2024-2026. ChatGPT Memory, Claude Projects memory, Gemini Gems memory, and custom assistant frameworks all let users explicitly or implicitly add facts the assistant remembers across sessions. The UX problem: making memory visible (so users know what's stored), controllable (so they can edit or forget), and useful (so the assistant actually uses what it remembers). The technical pattern: store facts in a small DB, retrieve relevant ones into context per turn, write new facts back when the user provides them.

When to use personal memory (ai assistant)

• Consumer AI assistants.
• Per-user personalised experiences.

Common mistakes

• Storing PII without explicit consent.
• No editing UI — users can't correct wrong memories.

FAQ

Related terms

• Stateful agent — A stateful agent persists state — memory, learned facts, long-running context — across sessions, in contrast to stateless agents that start fresh on every conversation.
• Context distillation — Context distillation summarises an agent's growing conversation history into a compact representation, so each step's input stays small while preserving the relevant signal.
• Embedded bot (LLM) — An embedded bot is an LLM-powered assistant that lives inside a product's surface — a chat widget on a website, a sidebar in a SaaS app, a CLI helper — rather than as a standalone chat platform.

Last updated: 2026-06-01. Raw markdown: https://promtable.com/glossary/personal-memory.md.