Agent memory
plori agents keep notes about you and your projects. How memory works, private vs account scope, and how to manage it.
plori agent memory is a set of short notes the agent keeps across sessions and reads at the start of every turn. Memory is separate from the Workspace files: the files hold the agent's work, memory holds what it has learned about you and your projects.
How does agent memory work?
Each note is a short piece of text ("deploys go through the staging cluster first", "the user prefers TypeScript"). Before every turn, the agent's visible notes are handed to it alongside your message, so it acts on them without being asked. The amount of note text per turn has a limit, so keep each note short. Notes are deliberately small; memory is for durable facts and preferences, not documents. Put documents in the Workspace files.
The agent writes its own notes as it works, and you can write notes for it yourself.
Who can see a note?
Every note has one of two scopes:
- Private: visible only to the one agent that owns it. Notes the agent writes for itself are always private.
- Account: visible to all agents on your account. Use this for facts every agent should know, like house style or standing constraints.
An agent can never share a note on its own. Promoting a note to account scope is a human action in Settings → Memory in the Workspace conversation. A confirmation shows the exact text you are about to share.
How do I manage notes?
In a Workspace conversation, open Settings, then select the Memory tab. It shows the Workspace agent’s private notes and notes shared across your account. As the account owner, you can:
- Create and edit notes by hand.
- Promote a private note to account scope, or demote it back.
- Duplicate a shared note into a private copy for one agent to evolve.
- Quarantine a note to stop the agent from seeing it without deleting it, and restore it later. Useful when you suspect a note is steering the agent wrong.
- Delete notes permanently.
What memory is not
Memory is not a transcript. Conversations are stored with the agent as threads you can reopen, but the agent does not reread old threads on every turn. If something from a past conversation matters durably, it belongs in a note, and a well-behaved agent will put it there itself.
Related
- Disk and files: where the agent's actual work lives.
- Getting started: start free and run your first task.