A fast memory API.
A governed memory across your AIs.
Supermemory is a memory and context engine for developers, with user profiles, hybrid search, connectors and plugins for coding agents. Kemory captures supported AI chats in the background, lets you continue a conversation in another AI and makes permissions and audit the default on every plan.
Last verified 7 November 2026 against primary sources
Two good answers.
Different jobs.
- You are building an agent or app and want a well-documented memory API with profiles, hybrid search and connectors.
- You live in Claude Code, Cursor or Codex and want a ready-made open-source plugin.
- You want to prototype on a local binary and move to the hosted platform by changing the base URL.
- You want chats on ChatGPT, Claude, Gemini, Perplexity, Manus and Grok captured in the background, with history import.
- You need permissions, consent and an audit trail on every plan rather than on a top tier.
- You want to continue a conversation in another AI, use Counsel, or share memory across organisations.
See each one
doing its job.
Screenshots taken 7 November 2026. Supermemory 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.
Supermemory's developer experience is strong: clear docs, SDKs, a large plugin catalogue and a local binary on the same API. Its connectors cover Drive, Gmail, Notion, OneDrive and GitHub, and SOC 2 Type II and a HIPAA BAA are documented for eligible plans.
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 |
| Supermemory | LongMemEval-S | 97% | Recall@20 with aggregation (retrieval), self-reported | Not stated | GPT-4o judge | Not stated |
| Supermemory | LongMemEval-S (README) | 95% | Recall@15 (retrieval), self-reported | Not stated | Not stated | Not stated |
What changed at Supermemory
Products move quickly. These are the dated changes this comparison has been checked against.
- 9 September 2026Consumer app Nova and the company-brain product discontinued, with refunds; focus moves to the memory API. MCP and plugins continue.
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 Supermemory? You do not have to replace it to try Kemory. Kemory connects to the AIs you use over MCP and Kora for Chrome.
Choosing Supermemory 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 Supermemory.
- What is the difference between Kemory and Supermemory?
- Supermemory is a memory API, MCP server and plugins for agents you build or use. Kemory adds background capture of your AI chats, continuation in another AI and permissioned sharing between people, with governance on every plan.
- Does Supermemory still offer Nova or a Chrome extension?
- Supermemory discontinued Nova and its company-brain product on 9 September 2026, and its Chrome extension served Nova. Its MCP server and plugins continue.
- Can I self-host Supermemory?
- Yes, as a local binary or Docker image, free within a 10,000-document lite licence; dedicated and air-gapped deployments are on Enterprise. Kemory offers enterprise self-host, your own cloud or air-gap, and an Apache 2.0 Community Edition is coming.
- How is Supermemory priced compared with Kemory?
- Supermemory is free with $5 of credits, then Pro at $19 a month, Max at $100 and Scale at $399 with unlimited seats, all on usage-based credits; Enterprise is custom. 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.
- Is Supermemory's 97% higher than Kemory's 89.6%?
- They measure different things. Supermemory's 97% is Recall@20 on LongMemEval-S: whether the evidence was retrieved. Kemory's 89.6% is end-to-end answer accuracy, whether the final answer was right, on the LongMemEval-S oracle split with a Llama-3.3-70B reader across six runs.
More comparisons
Credit where it’s due. The real difference, either way.