All memory systems
Memory about youalso work & project memory

ChatGPT memory

ChatGPT's built-in memory: it learns about you from your chats and keeps that picture up to date.

by OpenAI · Built this? Edit this page on GitHub

Measured against human memory

each one, with its source ↓

built today

Head to head withClaude (app memory)

In short

ChatGPT remembers you in two ways. Saved memories are short notes, written when you say “remember this” or when ChatGPT decides something is useful. Chat history memory goes further: a background process OpenAI calls “dreaming” reads across your past chats and keeps a running picture of you up to date, so “you’re going to Singapore in July” becomes “you went to Singapore” once the trip is over. You can read that picture as a memory summary, correct it by typing, and see under each answer which memories shaped it.

Who it’s for

Everyone who uses ChatGPT, from Free to Pro and business plans. Nothing to install: it's managed in Settings, under Personalization and Memory.

What it remembers

Your preferences, goals, work, hobbies, plans and ongoing projects, drawn from saved memories, past chats and custom instructions, and on some plans your Library files, connected apps like Gmail, and (Pro and business plans on a Mac, opt-in) activity on your computer.

Memory lives
OpenAI's cloud
API keys
None: sign in to ChatGPT
Works with
ChatGPT on the web, iOS & Android apps, Mac & Windows apps
License
Closed sourceProprietary
Price
Free (limited memory); more on Go, Plus and Pro

Under the hood

Who writes memories
You, by asking it to remember; ChatGPT, when it judges something useful; and a background “dreaming” process that rewrites memory from many chats.
Where they're kept
On OpenAI's servers, as saved memories and a synthesised summary. The details aren't published.
How they're found
ChatGPT looks for relevant memories and past chats when they're likely to help, not on every reply. Sources show what it used.
Extra AI calls
Nothing extra to pay: dreaming runs in the background on OpenAI's side, within your plan.

How it works

  1. 1You chatOr ask it to remember something, which becomes a saved memory.
  2. 2It dreamsIn the background, it reads across your chats and updates its picture of you.
  3. 3Memory summaryA readable overview you can correct by typing, or tell what not to mention.
  4. 4Next answerWhen it helps, it pulls in memories and past chats, and shows them as Sources.
next chat: back to 1, you chat

What stands out

  • Memory that knows time passes: dreaming revises plans into past events, so old facts stop steering answers.
  • Sources under each answer show which memories and past chats shaped it, and let you fix, delete or mark them not relevant.
  • Friendly controls for everyone: edit the summary by typing, “don't mention this again”, temporary chats, and project-only memory that walls a project off from everything else.
  • Memory at huge scale: OpenAI cut the cost of dreaming about fivefold so Free users could have it too.

What it doesn’t do

  • It lives inside ChatGPT. There's no documented way to plug it into other AI tools, or to run it yourself.
  • The memory summary is a high-level view and, by OpenAI's own account, doesn't show everything that's remembered.
  • How memories are stored, linked or weighted isn't published, so much of what happens under the hood can't be checked.
  • Since Pulse was retired, nothing comes back on its own: reminders are scheduled tasks you ask for.
  • Deleting a chat doesn't delete a saved memory made from it. Each has to be removed separately.

Measured against human memory

4 built, 5 partly, 2 not known of the Field Guide’s 11 mechanisms

Encoding

Salience

Decides what's worth keeping, and how much, as a memory is written.

partly built

ChatGPT decides which details are worth keeping, and on Plus and Pro you can raise or lower a memory's priority, but there's no documented importance score set as it's written. source

Emotion

Gives memories written with feeling more weight.

not known

OpenAI doesn't say whether feelings in a conversation affect what's kept.

Storage

Forgetting

Lets unused memories fade over time on its own.

builtPlus & Pro

Automatic memory management moves less important saved memories to the background, judged by how recent they are and how often a topic comes up. source

Interference

When a new memory closely matches an old one, notices and lets the newer one win.

built

Dreaming keeps memory current: when things change, the newer fact replaces the old one, so a trip you were planning becomes a trip you took. source

Retrieval

Retrieval

Remembering something makes that memory stronger.

partly builtPlus & Pro

Topics you talk about often stay “top of mind”, but that follows the conversation, not recalling the memory itself. source

Association

Links memories, so recalling one brings its neighbours.

not known

Whether memories are linked to each other isn't documented. It finds related past chats by searching.

Prospective

Brings a memory back at the right time without being asked.

partly built

You can ask for reminders as scheduled tasks, and tell the memory summary what topics to bring up and when. Nothing surfaces purely on its own since Pulse was retired. source

Transformation

Consolidation

Reworks memories between sessions: strengthening, merging, reorganising.

built

Dreaming is a background process that learns from many conversations and rebuilds memory between chats. source

Reconsolidation

Corrects a memory when it's contradicted, and keeps what it used to say.

partly built

Memory is updated as things change or when you say something is outdated, and saved memories can keep a version history on some plans. Whether the summary keeps what it used to say isn't documented. source

Gist

Turns many specific moments into general knowledge.

built

Dreaming turns many chats into a general picture of you: your preferences, projects and constraints. source

Schemas

Forms beliefs about people and projects, and weighs new facts against them.

partly built

The memory summary is a picture of who you are that shapes answers, but how new facts are weighed against it isn't documented. source

Not every system is trying to be a human memory, so a hollow dot isn’t a flaw. It just says what the system doesn’t do. What the mechanisms are.

ChatGPT memory’s makers haven’t shared what they’re building next, so only today shows here. Makers can add their roadmap the same way they correct an entry.

Compare ChatGPT memory with the others, side by side

Questions

Who is ChatGPT memory for?

Everyone who uses ChatGPT, from Free to Pro and business plans. Nothing to install: it's managed in Settings, under Personalization and Memory.

Where does ChatGPT memory keep its memories?

OpenAI's cloud. On OpenAI's servers, as saved memories and a synthesised summary. The details aren't published.

Does ChatGPT memory forget?

Forgetting: built, basic (Plus & Pro). Automatic memory management moves less important saved memories to the background, judged by how recent they are and how often a topic comes up. source

Does ChatGPT memory correct a memory when it turns out to be wrong?

Reconsolidation: partly. Memory is updated as things change or when you say something is outdated, and saved memories can keep a version history on some plans. Whether the summary keeps what it used to say isn't documented. source

Is ChatGPT memory open source?

No, it's closed source. License: Proprietary.

Does ChatGPT memory need an API key?

API keys: None: sign in to ChatGPT.

How much does ChatGPT memory cost?

Price: Free (limited memory); more on Go, Plus and Pro.

Checked 2026-09-29. Stars and downloads as of 2026-10-13. Not yet confirmed by its makers. Sources: Memory in ChatGPT (help center), Dreaming: better memory for ChatGPT, ChatGPT release notes, Memory in projects, Scheduled tasks, Pricing.

Correct this page

Built ChatGPT memory? This page is yours to correct.

  1. This page is one small file in a public GitHub repo. Click Edit, fix what’s wrong or add what’s new, and GitHub opens a pull request for you. Rather not write YAML? Open an issue with links, and we’ll make the change.
  2. An automatic check tells you within a minute if anything is missing or mistyped.
  3. We read it against the sources you link. Every “built” or “partly built” grade needs a link that shows it, and every system is graded by the same written rules, ours included.
  4. Once it’s merged, the page updates a minute or two later. Changes from a system’s own team get a “Confirmed by its makers” mark.