OpenClawDocs
On this page

On this page

View as MarkdownView this page as plain textOpen in ChatGPTAsk questions about this pageOpen in ClaudeAsk questions about this page

Plugin guides

Knowledge scribes

A scribe is a conversation you own that Knowledge starts for you. It follows a skill that ships with Knowledge, once or on a schedule, and saves what it finds to the viewed agent's store. Part of the Knowledge plugin guide.

Open Knowledge in the Control UI and select the Scribes tab. Scribes that are starting, on, paused, failing, or need reauthorization are listed under On. The rest are under Available, including a once scribe that is done, which can be started again.

The scribes

Scribe Runs Options Skill
Review unlinked claims Ongoing None knowledge-unlinked-claims
Learn from conversations Once or ongoing Active only, or active and archived; starting 30 days, 90 days, all, or today knowledge-ingest
Learn from Memory Once MEMORY.md, daily notes, and the Dreaming diary (DREAMS.md) knowledge-ingest
  • Review unlinked claims files claims that maintenance left unlinked, creates pages for subjects that deserve one, and records outcomes in page State.
  • Learn from conversations saves the decisions, preferences, commitments, and lessons in your conversations. Ongoing runs check for newly finished conversations daily at 4:00 AM in your time zone. Conversations already learned from are skipped. Defaults are active conversations from the last 30 days.
  • Learn from Memory brings memory-core notes into Knowledge once. Memory itself is not changed.

Start a scribe

Select Set up…, Import…, or Turn on…, choose options, and start. Starting needs a connection with write access (operator.write).

  1. Knowledge creates a conversation titled Scribe · <title> for the viewed agent, or reuses the scribe's existing conversation (restoring it if it was archived).
  2. It sends that conversation a fixed setup message: the skill to follow and the options you chose as JSON. No vault content is included.
  3. An ongoing scribe creates one automation for itself and reports on. The Scribes tab then runs that automation once as its first run; the setup turn never runs it. If the page is closed when setup finishes, the first run starts the next time the Scribes tab loads. A once scribe does its work and reports back. Nothing is scheduled.

Scribes run as you, with your private access to the store, and use the agent's default model. Read everything a scribe did by opening its conversation. Ongoing scribes also appear on the Automations page.

States

State Meaning
Available No scribe conversation, a conversation that never received its setup, or an ongoing scribe that was turned off.
Starting The conversation received its setup but has not reported its result yet.
On Its automation is enabled and the last run did not fail.
Paused Its automation is disabled.
Failing The last run failed, the scheduler disabled it after repeated failures, setup reported a failure, or the setup turn stopped without a result.
Done A once scribe finished.
Needs reauthorization The automation exists but its conversation was archived or deleted.

Each scribe turn ends its reply with one SCRIBE_RESULT line. The Scribes tab reads the latest one for the result summary.

Controls

Open a scribe for its schedule, next and last run, model, options, failure alert, and recent runs.

Control Effect
Run now Runs the automation immediately. If a run is already in progress, it does not start another.
Pause / Resume Disables or enables the automation.
Turn off… Removes the automation. The conversation is kept.
Open conversation Opens the scribe's conversation.
Repair Restores an archived conversation, or creates one, and asks it to re-check and recreate its automation.
Retry For a failed once scribe: sends its setup message again, as a new attempt, in the same conversation.

Controls need write access. Pause, resume, and turn off are rejected if the automation changed since the page read it; the page shows the error, and reopening the scribe shows its current state.

Limits

  • The Scribes tab rereads scribe state about every 30 seconds while it is visible, so a setup result or a finished run can take that long to appear.
  • Conversation counts and the MEMORY.md size come from Gateway reads. A count the Gateway cannot provide is left out rather than estimated.
  • Repair and Retry reuse the options of the latest setup message the page can still read in the conversation (its last 100 messages); otherwise it uses the defaults.
  • The page finds a scribe's conversation by its Scribe · <title> name and, for an ongoing scribe, picks the one its automation targets. Renaming the conversation hides it from the tab: a once scribe starts a new conversation next time, and an ongoing one shows Needs reauthorization.
Was this useful?