Two products: Vity for people, Synap for agents.
One governed memory for both, shared with audit.
Maximem’s Vity extension carries your context between ChatGPT, Claude, Gemini and Perplexity, and its Synap engine gives production agents memory through SDKs, a hosted MCP endpoint and adapters for 23 frameworks. Kemory covers both jobs in one memory, and adds sharing across organisations with consent and a hash-chained audit trail.
Last verified 7 November 2026 against primary sources
Two good answers.
Different jobs.
- You are building agents and want drop-in adapters for the framework you already use, with memory fetched before the agent asks.
- You want a vendor that publishes every LongMemEval answer and an open harness to rerun it.
- You want credit-based developer pricing with a free trial and an audit trail on every tier.
- You want to share memory with people in other organisations, with accept-to-receive, credited contributions and audited reads.
- You want a deny-by-default Gatekeeper, just-in-time consent and a hash-chained audit log, for people and agents alike.
- You want data kept in India or Switzerland today, plus Ask Kora, Counsel and Continue in another AI.
See each one
doing its job.
Screenshots taken 7 November 2026. Maximem 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.
Synap ships adapters for 23 agent frameworks and publishes every LongMemEval answer, retrieved memory and judge verdict with an open harness, which makes its numbers checkable. Every developer plan, the free trial included, keeps an audit trail, and Maximem offers on-premise and air-gapped deployment for customers who need it.
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 |
| Maximem | LongMemEval_S | 95.6% | Answer accuracy, self-reported | All 500 questions, October 2026 | gemini-3.8-flash (judge gpt-4o) | Not stated |
| Maximem | LoCoMo | 93.2% | Answer accuracy, self-reported | Categories 1–4, adversarial excluded | gpt-5-mini (judge gpt-5-mini) | Not stated |
What changed at Maximem
Products move quickly. These are the dated changes this comparison has been checked against.
- 20 June 2026LoCoMo run published (93.2%, categories 1–4).
- October 2026LongMemEval run published (95.6% on all 500 questions), with every answer released.
- 5 November 2026Synap SDK 0.8.0 on PyPI and Vity extension v1.9.6.
- By 7 November 2026Synap Starter at a $19 launch price (list $49); Pro $249, Scale $999.
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 Maximem? You do not have to replace it to try Kemory. Kemory connects to the AIs you use over MCP and Kora for Chrome.
Choosing Maximem 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 Maximem.
- What is the difference between Kemory and Maximem?
- Maximem sells two products: Vity, which carries your context between consumer AIs, and Synap, a memory engine for agents you build. Kemory is one memory for people, teams and agents, captured from six AIs, recalled over MCP, REST, CLI and SDKs, and shared across organisations with consent and audit.
- How are Maximem and Kemory priced?
- Synap is credit-based: a free trial with 12,500 credits a month and one agent, Starter at $19 a month (launch price, list $49), Pro at $249 and Scale at $999. Vity is free to start, with a paid tier listed as coming soon. 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).
- Is Synap’s 95.6% better than Kemory’s 89.6%?
- The numbers cannot be compared directly. Synap reports all 500 LongMemEval_S questions with a Gemini answer model and a GPT-4o judge. Kemory reports end-to-end answer accuracy on the LongMemEval-S oracle split with an open-weight Llama-3.3-70B reader, across six runs. Different split, reader and judge.
- Can I self-host Maximem or Kemory?
- Maximem’s SDKs and eval harnesses are open source and it says the full stack can be self-hosted with its support, including on-premise and air-gapped, though not out of the box. Kemory offers enterprise self-host, your own cloud or air-gap, and an Apache 2.0 Community Edition is coming.
- Can I share memory with another person?
- Synap shares organisational knowledge across an application’s users and tenants; sharing between people in Vity is not documented as of 7 November 2026. Kemory shares namespaces or chosen items across organisations, with accept-to-receive, credited contributions, revocation and an audit entry for every cross-organisation read.
More comparisons
Credit where it’s due. The real difference, either way.