Skip to content
induwara.lk
Premium
induwara.lkAI · Reference

AI Chatbot Memory Comparison — Which AI Assistants Remember You (2026)

Tick the memory features you need and instantly see which of the eight major AI assistants qualify. Every row — cross-session recall, free-tier access, delete and off controls — is sourced from the vendor's own help pages and dated.

By Induwara AshinsanaUpdated Jul 18, 2026
Compare AI assistant memory
8 assistants · verified 2026-07-18
Filter by capability
Presets
Find my assistant

8 of 8 assistants match

Tick a capability above to narrow the list.

Memory capability table

AssistantCross-sessionAuto-recallControllableFree tierCan disableMemory type
ChatGPT
OpenAI
YesYesYesYesYesSaved memories + reference chat historySource
Claude
Anthropic
YesPartialYesYesYesPreference/fact summary + (paid) past-chat searchSource
DeepSeek
DeepSeek
NoNoNoNoNoNone — stateless, session-onlySource
Gemini
Google
YesYesYesYesYesSaved info + past-chat personal contextSource
Grok
xAI
YesPartialYesYesYesExtracted facts + past-conversation recallSource
Meta AI
Meta
YesPartialYesYesYesSaved facts you share or it infersSource
Microsoft Copilot
Microsoft
YesPartialYesYesYesSaved facts & preferences (personalization)Source
Perplexity
Perplexity AI
YesYesYesNoYesStructured memories + search historySource
Yes — documented & availablePartial — limited or paid-onlyNo — not offered
Side-by-side
Capability
ChatGPT
Claude
Has persistent memory
Yes
Yes
Remembers across new chats
Yes
Yes
Auto-recalls full history
Yes
Partial
View / edit / delete
Yes
Yes
On the free plan
Yes
Yes
Can be turned off
Yes
Yes
May train on your data
Partial
No
ChatGPTSaved memories + reference chat history

Two parts: an editable list of saved memories plus implicit recall of past chats. Free users get short-term continuity; Plus/Pro get deeper long-term referencing. On the free tier, memories may inform ad personalization.

Manage it: Settings → Personalization → Memory

OpenAI Help — Memory FAQ
ClaudePreference/fact summary + (paid) past-chat search

Memory (a running summary of your preferences and facts) is free for all users since March 2026. Actively searching and referencing full past conversations stays on paid plans (Pro/Max/Team/Enterprise). Anthropic does not train on your chats by default.

Manage it: Settings → Memory

Claude Help — chat search & memory

Every row is sourced from the vendor's own help pages (linked in the table). Memory features change often — figures were last verified on 2026-07-18. Follow each “Source” link to re-check before you rely on a cell.

What this tells you

Most people want an AI assistant that remembers their context — their writing style, their project, their preferences — without re-explaining it every chat. Others want the opposite: to know exactly what is stored and how to switch it off. This tool answers both. It compares eight consumer assistants — ChatGPT, Claude, Gemini, Microsoft Copilot, Grok, Meta AI, Perplexity and DeepSeek — across six memory capabilities, using each vendor's documented behaviour.

How it works

This is a curated reference, not a calculator. The logic is careful data curation plus deterministic boolean filtering — no server call, no opinion, only what each vendor documents. Each assistant is one record with six capability fields, and every field is defined precisely so results are reproducible:

  • Cross-session — information from one chat is available in a different, new chat.
  • Auto-recall of history — the assistant can automatically reference the content of past chats, not just facts you explicitly saved.
  • View / edit / delete — there is a settings screen to see and remove individual memories.
  • Free tier — the memory feature works without a paid plan.
  • Can disable — there is a global switch to stop it remembering you.
  • Trains on your data — shown separately, because remembering you and training the underlying model are different things.

Each cell is one of three states: Yes (documented and available on the stated plan), Partial (limited — for example saved facts only, or the fuller version is paid) or No. When you tick filters, an assistant matches only if every ticked field is a full Yes — a Partial deliberately does not qualify, because a half-answer should not be sold as a full one. The match rule is a plain boolean AND: filters.every(f => assistant[f] === "yes"). With no filters ticked, every assistant matches and you see the full table.

The match count is computed two independent ways in the data module — once with Array.filter().length and once with a reduce accumulator — and both agree for every filter combination, a small guard against a logic slip. Because memory features change so often, the dataset carries a 2026-07-18 verification date and each row links to its primary vendor source for re-checking. The dataset covers consumer plans only; enterprise/team memory-admin controls and country-by-country availability are out of scope.

Worked examples

“Remembers me across new chats, on the free plan”

Filters: Cross-session + Free tier

  1. Match rule: an assistant qualifies only if BOTH fields are Yes.
  2. ChatGPT (Yes, Yes), Claude (Yes, Yes — free since Mar 2026), Gemini (Yes, Yes) → match
  3. Copilot (Yes, Yes), Grok (Yes, Yes), Meta AI (Yes, Yes) → match
  4. Perplexity: cross-session Yes, but memory is Pro/Max → free tier No → no match
  5. DeepSeek: no memory feature at all → no match
  6. Result: 6 of 8 assistants match.

“Let me delete memories AND turn memory off entirely”

Filters: View/edit/delete + Can disable

  1. ChatGPT, Claude, Gemini, Copilot, Grok, Meta AI, Perplexity all expose a delete UI and an off switch → 7 match
  2. DeepSeek stores nothing, so there is nothing to delete or disable → no match
  3. Result: 7 of 8 match — the privacy controls are near-universal once memory exists.

Edge case — the strictest possible filter (all five ticked)

Filters: Cross-session + Auto-recall + Delete + Free + Can disable

  1. ChatGPT (all five Yes) → match
  2. Gemini (all five Yes) → match
  3. Claude: full past-chat search is paid → auto-recall Partial → no match
  4. Copilot, Grok, Meta AI: keep extracted facts, not full history → auto-recall Partial → no match
  5. Perplexity: free tier No; DeepSeek: all No → no match
  6. Result: only 2 of 8 match — ChatGPT and Gemini clear every bar.

Frequently asked questions

Sources & references

One primary vendor page per assistant. Each row in the tool links to the same source so you can re-check a single cell.

Last cross-checked against these sources on 2026-07-18. Memory features ship and change often; this page is reviewed on a rolling basis and whenever a vendor announces a change.

Related tools

Rate this tool
Be the first to rate

Comments & feedback

Spotted a bug or want an improvement? Tell us — our team reviews every comment, and good ideas get built. Comments are public and anonymous.

Spotted a memory feature that changed, or an assistant we should add?

Email me at [email protected] — most fixes ship within 24 hours.