Memanto Cloud launches Nov 20. What should we get right?
Hi everyone,
We first launched Memanto here five months ago: an open-source memory agent that gives AI agents long-term memory, and works with Claude Code, Cursor, Windsurf and more.
Since then, one request has come up in our user survey more than any other: make it easier to start. Until now, using Memanto meant installing it on your machine and connecting it to Moorcheh with an API key, or running Moorcheh on-prem in Docker. That's real work before your agent remembers anything.
On November 20 we launch Memanto Cloud:
A one-line install.
We run the backend, so there's no Moorcheh API key or server to set up.
An agent can create its own Memanto account and provision its own long-term memory, without waiting for a human.
The open-source version and the on-prem path stay available.
Before launch day, we'd like your help getting it right:
If your agent could sign itself up, what's the first thing you'd want it to remember?
What would you need to see before trusting a hosted memory with your agent's history?
What would stop you from trying it on day one?
I'll come back to this thread before launch with what we changed because of it.


p/runevr
p/producthunt
p/google-cloud-platform
p/operum
p/murror
p/tabstack
p/dino-kids
p/any-video-to-text
p/seldon
p/rithub
p/jot-2-0
p/okapi-2
p/gatrends
p/appxiom
p/flamigo
p/dots-7
p/kodlo
p/replay-11
Replies
Be the first to reply
Have a question or a thought to share? Add a comment above to start the conversation.