Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

How do OpenClaw and Remember coordinate their memory retrieval and writing processes? #2

Closed Answered by liang9886703
liang9886703 asked this question in Q&A
Discussion options

I installed remember using the standard procedure outlined in the documentation, like this:

openclaw plugins install @remember-md/remember
openclaw gateway restart

Afterwards, I communicated with Openclaw, telling it:

/remember:init
Created in the default path
Serves the current project
/remember:process

At this point, I'm unsure if this conversation will automatically write to and retrieve contents under ~/remember (my workspace is obviously not there).

You must be logged in to vote

I found that relying solely on prompt words wasn't stable enough, so I switched to using cron as a backup: a scheduled task called remember:process has been created to run automatically once a day at 5:00 AM. It seems to be working well so far.

Replies: 4 comments 2 replies

Comment options

Hello, so the extraction process is not fully automated in terms of running after each session unit, so you need to run the /remember:process command. This can of course be configured as a cron inside OpenClaw.
Let me know if it works.

You must be logged in to vote
1 reply
Comment options

I saw the /remember skill, and I added the following to AGENTS:

  • If you think it's appropriate to use the remember skill, simply record the information and notify that it has been recorded. Execute it directly without prompting.

This should replace running the /remember:process command.

Now, I'm unsure if the ~/remember workspace will be retrieved by Openclaw as a memory.

Comment options

I found that relying solely on prompt words wasn't stable enough, so I switched to using cron as a backup: a scheduled task called remember:process has been created to run automatically once a day at 5:00 AM. It seems to be working well so far.

You must be logged in to vote
0 replies
Answer selected by codezz
Comment options

Great. Thanks for sharing.

You must be logged in to vote
0 replies
Comment options

Love this, but anyone here know at some point any openclaw wrapper that has persistent memory? setting up stuff to openclaw has been very tiring recently:)

You must be logged in to vote
1 reply
Comment options

One thing I found recently is that you can add extra paths where openclaw can search other that it's default memory. You can add the second brain path there
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /