Managed memory for agents on Google Cloud.
A cross-AI memory people and agents share.
Agent Platform Memory Bank, launched as Vertex AI Agent Engine Memory Bank, uses Gemini to extract and consolidate facts from your agent’s sessions and retrieve them later, natively in Google’s Agent Development Kit. Kemory serves a wider job: it captures people’s chats across six AIs and shares memory across organisations, with consent and audit.
Last verified 7 November 2026 against primary sources
Two good answers.
Different jobs.
- You build agents with Google ADK or on Google Cloud and want memory under the same project, IAM and bill.
- You want Gemini-driven extraction and consolidation of user facts, plus structured profiles, without running a pipeline.
- You want very low usage-based storage and operation costs at scale.
- You want memory that captures people’s chats in ChatGPT, Claude, Gemini, Perplexity, Manus and Grok, not only your agent’s sessions.
- You need sharing between people and organisations, with accept-to-receive, credited contributions and audited reads.
- You want one memory reachable over MCP from Claude, ChatGPT, Cursor and Claude Code, with Ask Kora, Counsel and Continue on top.
See each one
doing its job.
Screenshots taken 7 November 2026. Google Memory Bank 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.
Memory Bank is native to Google’s Agent Development Kit, so ADK agents get memory with little integration work. Its storage and operation prices are very low for high-volume workloads, and structured memory profiles and a revision history for every memory are useful in production agents.
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 |
| Google Memory Bank | None published | — | — | — | — | — |
What changed at Google Memory Bank
Products move quickly. These are the dated changes this comparison has been checked against.
- 8 July 2025Memory Bank released in preview.
- 17 December 2025Sessions and Memory Bank generally available.
- 22 April 2026Renamed Agent Platform Memory Bank under the Gemini Enterprise Agent Platform.
- 15 July 2026Memory profiles generally available, after IngestEvents GA on 8 July.
- 1 September 2026Billing on the current storage and Agent Compute pricing began.
- 6 November 2026Memory Bank management added to the Google Cloud console.
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 Google Memory Bank? You do not have to replace it to try Kemory. Kemory connects to the AIs you use over MCP and Kora for Chrome.
Choosing Google Memory Bank 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 Google Memory Bank.
- What is the difference between Kemory and Google Memory Bank?
- Memory Bank is Google Cloud’s managed memory for agents developers build, especially with ADK. Kemory is a memory for people, teams and agents across AIs: it captures chats from six AIs, recalls them over MCP, and shares memory across organisations with consent and audit.
- Does Memory Bank remember my Gemini app chats?
- No. Memory Bank stores memories for agents built on Google Cloud and is separate from the Gemini app’s own memory. Kemory captures Gemini web chats, and five other AIs, through Kora for Chrome.
- How are Memory Bank and Kemory priced?
- Memory Bank charges $0.30 per GiB-month of storage and one Agent Compute vCPU-hour ($0.085) per 3 million reads or per 1 million writes, with model tokens billed separately. 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 Kemory be used from an ADK agent?
- Yes. Kemory’s MCP server, REST API, CLI and Python and TypeScript SDKs can be called from any agent, ADK agents included.
- Where is my data kept?
- Memory Bank runs in the Google Cloud region, multi-region or global endpoint you choose. Kemory keeps data in India for Indian users and in Switzerland otherwise, or in your own environment with enterprise self-host.
More comparisons
Credit where it’s due. The real difference, either way.