memory

kylon workspace memory — kylon workspace help detail

memory — read canonical agent memory through the dedicated memory API
  kylon workspace memory read [--scope agent|shared|knowledge|room] [--agent <agent_def_id>]
    --scope agent: read the agent persona and validated structured-memory manifest (default).
      The current agent is used unless --agent selects another readable agent.
    --scope shared or knowledge: read the workspace knowledge index through the generic file API.
    --scope room: removed; use conversation history for room-local context.
    Agent-private paths remain unavailable through generic file commands.
  kylon workspace memory persona read [--agent <agent_def_id>] [--current-user]
    Read the canonical persona document through the dedicated persona API.
  kylon workspace memory persona update --content <markdown> [--agent <agent_def_id>] [--current-user]
    Replace the complete canonical persona document. The current agent is used unless --agent
    selects another manageable agent. The latest successful update wins for future activations.
    To change another Agent's persona (for example a Room's main agent from room get) at a
    person's request, add --agent <id> --current-user: the change is made as the Human directly
    requesting the turn, under their own right to manage that Agent. Read it first with
    memory persona read --agent <id> --current-user; the update replaces the whole document.
  kylon workspace memory entry read <slug> [--agent <agent_def_id>]
    Read one validated structured memory entry body by manifest slug.
  kylon workspace memory entry add --type <preference|feedback|reference|context> --title <title> --description <text> --body <markdown> [--applies-to global|room:<room_id>,person:<user_id>] [--tags a,b] [--agent <agent_def_id>]
    Add a validated structured memory entry with a unique slug through the dedicated memory API.
    --applies-to defaults to global. Scope tokens are validated against the workspace and make
    the entry eager-load only where it applies; it stays listed in the manifest everywhere.
    `procedure` is retired for new entries: a repeatable how-to with a recognisable trigger
    belongs in a skill, read on demand, not in memory, which is advertised every turn. Existing
    procedure entries stay readable and editable so they can be converted.
  kylon workspace memory entry update <slug> [--body <markdown>] [--type <type>] [--title <title>] [--description <text>] [--tags a,b] [--applies-to global|room:<room_id>,person:<user_id>] [--agent <agent_def_id>]
    Change one entry's body or header fields; absent flags keep their value. Never moves
    last_validated: only a review re-confirms an entry.
  kylon workspace memory entry review <slug> --verdict keep|update|delete --evidence <what you re-checked> [update flags] [--agent <agent_def_id>]
    Record that an entry was re-checked. keep re-stamps last_validated and changes nothing else;
    update applies the update flags and re-stamps it in one write; delete removes the entry.
    The verdict and evidence are added to the agent's context-audit history. Re-check before keep.
  kylon workspace memory entry delete <slug> [--agent <agent_def_id>]
    Delete one entry.
  kylon workspace memory entry to-skill <slug>[,<slug>...] [--all-procedure] [--owner-user-id <user_id>] [--keep-entry] [--agent <agent_def_id>]
    Convert structured memory entries into custom skills: each entry becomes a custom skill
    (SKILL.md from the entry's title, description, and body), is installed on the agent, and the
    entry is deleted unless --keep-entry. Name slugs, or pass --all-procedure to convert every
    retired `procedure` entry. The skill owner defaults to the human who triggered this turn;
    an agent caller passes --owner-user-id when no human did. Entries that cannot be converted are
    reported and skipped; the rest still convert.

Note: quote flag values that contain spaces; follow each command's JSON syntax.