One person’s memory across 21+ AI tools.
A governed memory you can share and audit.
MemoryPlugin syncs your chats from ChatGPT, Claude, Gemini, Grok, DeepSeek and TypingMind, plus Claude Code, Codex and Cursor, into one searchable history you can recall in any AI over MCP. Kemory captures chats across six AIs too, and adds sharing across organisations, consent and a hash-chained audit trail.
Last verified 7 November 2026 against primary sources
Two good answers.
Different jobs.
- You are one person who wants every past chat, coding-agent sessions included, searchable and recallable from Claude or Cursor.
- You want a mature archive with full-conversation recall, file Q&A, Ask with citations and an iPhone app.
- You prefer simple individual pricing, with annual, monthly or lifetime options.
- You need to share memory with people in other organisations, with accept-to-receive, credited contributions and an audit entry for every cross-organisation read.
- You want a deny-by-default Gatekeeper, just-in-time consent and a hash-chained audit log on every plan, including free.
- You want Counsel, Continue a chat in another AI, or data kept in India or Switzerland.
See each one
doing its job.
Screenshots taken 7 November 2026. MemoryPlugin is a trademark of its owner, shown here to identify the product.
At a glance
The same rows on every comparison, so you can read one page against another.
*89.6% end-to-end answer accuracy on LongMemEval-S, open-weight Llama-3.3-70B reader, six runs. See the benchmarks or the full method on docs.sekondbrain.ai. A dash means not documented, not proven absent.
The same job,
done two ways.
MemoryPlugin covers more sources than most products in the category, Kemory included: 21+ AI tools in the extension, background sync for six web assistants and transcript sync for Claude Code, Codex and Cursor. Full-conversation recall and export over MCP, file Q&A and a native iPhone app make it a strong personal archive, and its Trust page explains plainly what it stores and where.
The numbers,
and how each was run.
These rows use different datasets, splits, readers and retrieval budgets, so they cannot be compared directly. We publish the method, every run including the lower ones, and use an open-weight reader rather than a frontier model.
| Product | Benchmark | Score | What it measures | Setup | Reader model | Runs |
|---|---|---|---|---|---|---|
| Kemory | LongMemEval‑S | 89.6% | End-to-end answer accuracy | 500 questions, oracle split | Llama-3.3-70B (open-weight) | Six, with variance |
| MemoryPlugin | None published | — | — | — | — | — |
What changed at MemoryPlugin
Products move quickly. These are the dated changes this comparison has been checked against.
- 8 July 2026MemoryPlugin Sync for macOS launched: Claude Code, Codex and Cursor chats synced into history (Pro).
- July 2026MCP server open-sourced and listed in the official MCP Registry; Trust page published.
- August 2026Native iPhone app in beta on TestFlight; ChatGPT Project chats now sync; Sync 2.2.0.
- By 7 November 2026Core at $89 a year and Pro at $180 a year, with monthly and lifetime options.
Specialists do one job well.
Kemory holds the thread across them all.
Every year brings better models and you will keep trying them. Kemory sits above the models rather than inside any one of them, so what you have worked out goes with you.
Tell one AI something once, and every AI you use just knows it. Start a thought in one and carry on in another, mid-sentence.
Every memory is permissioned and every change is provable. We do not train on your data. Delete anything, and prove it is gone.
Compaction runs on an open-weight model, so the frontier model only ever sees the compacted version — not the pile.
Already using MemoryPlugin? You do not have to replace it to try Kemory. Kemory connects to the AIs you use over MCP and Kora for Chrome.
Choosing MemoryPlugin instead?
Good — it fits you better right now.
Come back to Kemory when cross-AI, governed memory is what you need.
Five questions,
Kemory vs MemoryPlugin.
- What is the difference between Kemory and MemoryPlugin?
- MemoryPlugin gives one person a memory and a searchable chat archive across 21+ AI tools, recalled over MCP. Kemory captures chats across six AIs and adds governed sharing across organisations, consent, a hash-chained audit log, Counsel and Continue in another AI.
- Does MemoryPlugin capture my chats automatically?
- Yes, once you switch on Background Sync for each platform; the extension then syncs new conversations once an hour from ChatGPT, Claude, Gemini, Grok, DeepSeek and TypingMind. Kemory’s Kora captures chats in the background on ChatGPT, Claude, Gemini, Perplexity, Manus and Grok.
- Can MemoryPlugin share memories with a colleague?
- Yes, on Pro. A bucket owner invites people by email as Viewer, Contributor or Editor; they accept, each memory shows who added it, and access can be changed or revoked. Kemory’s sharing also works across organisations, credits contributions and audits every cross-organisation read.
- How are MemoryPlugin and Kemory priced?
- MemoryPlugin Core is $89 a year ($15 monthly, $200 lifetime) and Pro is $180 a year ($25 monthly, $400 lifetime), with a seven-day trial and a 14-day refund; there is no free plan. Kemory is free for 2,000 memories and two AIs, with Pro at $19.99 a month, Team at $30 a seat and Business at $55 a seat (10-seat minimum).
- Where is my data kept?
- MemoryPlugin says it runs on US-based infrastructure, encrypted in transit and at rest but not end to end, with administrative access logged. Kemory keeps data in India for Indian users and in Switzerland otherwise, encrypts each user’s data at rest and deletes by crypto-shredding.
More comparisons
Credit where it’s due. The real difference, either way.