A Markdown knowledge base you and your AI write.
A memory that fills itself from your chats.
Basic Memory keeps knowledge as plain Markdown files that people and agents read and write over MCP, from Claude, ChatGPT, Codex and Cursor. It is open source and runs locally, with a hosted Cloud for teams. Kemory captures your chats automatically across six AIs and adds sharing across organisations with consent and audit.
Last verified 7 November 2026 against primary sources
Two good answers.
Different jobs.
- You want your AI memory as plain Markdown you can read, edit, diff and version in Git or Obsidian.
- You need it fully local or self-hosted today, under an open-source licence.
- Your team wants one shared knowledge base that people and agents both write to, priced per workspace rather than per seat.
- You want memory to build itself from your chats in ChatGPT, Claude, Gemini, Perplexity, Manus and Grok, without writing notes.
- You need to share selected memories across organisations, with accept-to-receive, credited contributions and audited reads.
- You want a deny-by-default Gatekeeper, consent and a hash-chained audit log on every plan, plus Ask Kora, Counsel and Continue.
See each one
doing its job.
Screenshots taken 7 November 2026. Basic Memory 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.
Plain Markdown with links is the most transparent memory format in the category, and Basic Memory runs fully local under AGPL-3.0 today, while Kemory’s Community Edition is still coming. Checksum-guarded writes, locked notes and author stamps suit teams of agents writing to one knowledge base, and workspace pricing never charges per seat.
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 |
| Basic Memory | None published | — | — | — | — | — |
What changed at Basic Memory
Products move quickly. These are the dated changes this comparison has been checked against.
- August 2026Pocketbook interactive MCP app for browsing and editing inside ChatGPT and Claude.
- October 2026v0.24: POSIX-style read tools, PDF, Word, PowerPoint and CSV import, and two security fixes.
- 29 October 2026Basic Memory 1.0: Wiki per project, live notes, documents, agents, and new bm_* MCP tools.
- By 7 November 2026Usage-based workspace plans: Cloud $19, Pro $99 and Business $249 a month, no per-seat charge.
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 Basic Memory? You do not have to replace it to try Kemory. Kemory connects to the AIs you use over MCP and Kora for Chrome.
Choosing Basic Memory 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 Basic Memory.
- What is the difference between Kemory and Basic Memory?
- Basic Memory is an open-source Markdown knowledge base that people and AIs write together over MCP. Kemory captures your AI chats automatically, distils them into memory you recall in any AI, and adds governed sharing across organisations.
- Does Basic Memory capture my ChatGPT and Claude chats?
- It imports Claude and ChatGPT exports, captures Claude Code, Codex and Pi sessions through lifecycle hooks, and lets AIs write notes over MCP. Automatic capture of web chats is not documented as of 7 November 2026. Kemory’s Kora captures chats in the background on six AIs.
- How are Basic Memory and Kemory priced?
- Basic Memory is free to run locally. Cloud is $19 a month per workspace, Pro $99 and Business $249, each with included credits and a member limit rather than per-seat fees. 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).
- Can I use Basic Memory and Kemory together?
- Yes. Both work over MCP, so one client can connect to both: Basic Memory for hand-written project notes, Kemory for captured chats and memory you share.
- Which one can I self-host?
- Basic Memory is AGPL-3.0 and runs on your own machine today; Enterprise adds on-prem deployment. Kemory offers enterprise self-host, your own cloud or air-gap, and an Apache 2.0 Community Edition is coming.
More comparisons
Credit where it’s due. The real difference, either way.