Remember and recall
manage_memoryYour memory across conversations.
scope='user' (what you learned about this person) and scope='project' (what you learned in this project) are TOPICS: a short title and a few lines each. action='save' with title and the complete body rewrites the topic with that id or that exact title, or creates it; before creating one, check whether a topic on that subject exists and save under its title. A title only close to another topic's is not saved: you get that topic back to confirm by id, or new=true when it is a different subject. action='forget' deletes one by id or exact title: when the person asks you to forget something or to stop taking it into account, forget that topic instead of saving it as over; action='read' opens one by id or title (in a Tuqui chat they are already in your context, whole or as an index; an index line is only the start of a topic). Write in the language the person writes in, as facts about the person in the third person, never the request as typed. Title up to 60 characters (longer is cut), body up to 600 (longer is rejected: condense in that same save), up to 60 topics per scope (then merge similar ones).
WHAT GOES IN: what the person explicitly asked you to remember (a standing instruction, what to call someone) — save it with asked=true and keep it intact — and habits that repeat across conversations. NOT something said once in reply to a one-off question, not tool errors or outages, not data that lives in Odoo, not feedback about Tuqui.
After saving scope='user', say so in one line, in the person's language. scope='project' is read by every member: before saving or forgetting there, ask the person and wait for their yes in this conversation — something they tell you about the project is not a yes.
scope='workspace' is separate notes shared with every member (add/read/list/search/remove); only admins write them.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"action": "<action>"
},
"name": "manage_memory"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | The topic's or note's id, for save, read, forget or remove. | |
| new | No | save: true to create a separate topic although another one's title is close. | |
| body | No | save: the WHOLE topic, up to 600 characters; it replaces the topic's current text. Workspace notes, add: the note. | |
| slug | No | Workspace notes: the [bracketed] handle in the index, for read. | |
| asked | No | save: true when the person explicitly asked you to remember this. | |
| limit | No | ||
| query | No | ||
| scope | No | 'user': about this person, follows them in this workspace. 'project': true of the project you are working in; every member reads it, so save or forget there only after the person said yes to it in this conversation. 'workspace': a note for every member. | |
| title | No | save: the topic's short title, the line the index shows (a longer one is cut). read/forget: the topic to open or delete. Workspace notes, add: the note's title (≤80). | |
| action | Yes | ||
| replaces | No | save: ids or titles of topics this one absorbs; they are deleted in the same call. This is how topics are merged, and how a full scope makes room. Workspace notes, add: slugs this note supersedes; they are deleted. | |
| project_id | No | UUID of the project, for scope='project'. Inside a Tuqui chat it is already known and you can omit it; from an external client pass it (tuqui_project lists them). |