openclaw wiki CLI Reference

`openclaw wiki`

The memory-wiki vault can be inspected and maintained through this command group. It ships as part of the optional memory-wiki plugin, which is bundled by default. Activate it before running any of the commands:

openclaw plugins enable memory-wiki
openclaw gateway restart

For more context, see Memory Wiki plugin, Memory Overview, and CLI: memory.

Common commands

openclaw wiki status
openclaw wiki doctor
openclaw wiki init
openclaw wiki ingest ./notes/alpha.md
openclaw wiki okf import ./knowledge-catalog/okf/bundles/ga4
openclaw wiki compile
openclaw wiki lint
openclaw wiki search "alpha"
openclaw wiki search "who should I ask about Teams?" --mode route-question
openclaw wiki get entity.alpha --from 1 --lines 80

openclaw wiki apply synthesis "Alpha Summary" \
  --body "Short synthesis body" \
  --source-id source.alpha

openclaw wiki apply metadata entity.alpha \
  --source-id source.alpha \
  --status review \
  --question "Still active?"

openclaw wiki bridge import
openclaw wiki unsafe-local import
openclaw wiki chatgpt import --export ./chatgpt-export --dry-run
openclaw wiki chatgpt rollback <run-id>

openclaw wiki obsidian status
openclaw wiki obsidian search "alpha"
openclaw wiki obsidian open syntheses/alpha-summary.md
openclaw wiki obsidian command workspace:quick-switcher
openclaw wiki obsidian daily

Agent selection

When the plugins.entries.memory-wiki.config.vault.scope setting is agent, the vault is chosen through the --agent <id> option on the command:

openclaw wiki status --agent support
openclaw wiki search "refund policy" --agent support
openclaw wiki ingest ./campaign-notes.md --agent marketing

If --agent is not provided, the CLI falls back to the configured default agent, just like other agent-scoped CLI families. To target a different agent, supply the flag explicitly. An agent id that is not recognized causes the vault operation to fail before it starts. When no default agent can be determined, the error message instructs you to either pass --agent <id> or set up an agent. This option has no effect on the resolved path when vault.scope is global.

Gateway clients must stay explicit: in an agent-scoped multi-agent deployment, vault-backed wiki.* requests need agentId to be included. Omitting it, or using an unknown id, results in an error. Agent turns, wiki tools, memory corpus supplements, and compiled prompt digests already include the active runtime agent context.

Commands

`wiki status`

This command displays the vault mode and scope, the resolved agent, health status, and whether the Obsidian CLI is available. Run it first to verify that the intended vault is initialized, that bridge mode is functioning correctly, or that Obsidian integration is present.

When bridge mode is turned on and set to read memory artifacts, this command contacts the running Gateway so the active memory plugin context matches what agent and runtime memory see.

`wiki doctor`

Health checks for the wiki are executed here, along with actionable remediation steps. A non-zero exit code signals an unhealthy state.

In bridge mode that reads memory artifacts, the Gateway is queried before the report is assembled. Bridge imports that are disabled, or bridge configs that do not read memory artifacts, remain fully local and offline.

Common problems include:

bridge mode enabled but no public memory artifacts exist
vault layout is invalid or absent
external Obsidian CLI is missing when Obsidian mode is expected

`wiki init`

The wiki vault layout and starter pages are created here, which includes top-level indexes and cache directories.

`wiki ingest <path>`

A local markdown or text file can be brought into the wiki sources/ folder as a source page via import. The <path> argument must point to a local file path; URL ingestion is not supported at this time. Binary files are rejected outright.

Source pages that are imported carry provenance frontmatter with sourceType: local-file, sourcePath, and ingestedAt. After every ingest, the vault is recompiled automatically.

The --title <title> flag lets you override the source title, which otherwise defaults to the filename.

`wiki okf import <path>`

An unpacked Open Knowledge Format bundle can be imported, with each entry becoming a wiki concept page.

Every non-reserved .md concept document inside the OKF directory tree is read by the importer. A non-empty type field is mandatory, and unknown OKF type values are handled as generic concepts. Reserved OKF index.md and log.md files are skipped as concepts.

Imported pages land flattened under concepts/, so existing wiki compile, search, get, digest, and dashboard flows pick them up right away. The page frontmatter keeps the original OKF concept ID, type, resource, tags, timestamp, source path, and the full frontmatter. Internal OKF markdown links get rewritten to point at the generated wiki pages; broken or external links stay untouched. The vault is always recompiled after an import.

Here are some examples:

openclaw wiki okf import ./bundles/ga4
openclaw wiki okf import ./bundles/ga4 --json
openclaw wiki search "BigQuery Table" --mode source-evidence --json
openclaw wiki get <path-from-json-result>

`wiki compile`

Indexes, related blocks, dashboards, and the compiled query and prompt snapshot are all rebuilt here. That snapshot lives in OpenClaw's shared SQLite plugin state and is held in memory for synchronous prompt projection; no cache files are written into the vault.

Report pages are also refreshed during compile when render.createDashboards is enabled.

`wiki lint`

Linting the vault produces a report that covers:

structural problems, such as broken links, missing or duplicate ids, absent page type or title, and invalid frontmatter
provenance gaps, including missing source ids and missing import provenance
contradictions, both flagged ones and conflicting claims
open questions
pages and claims with low confidence
stale pages and claims

Run this after any meaningful wiki changes.

`wiki search <query>`

Content within the wiki can be searched, with behavior driven by configuration:

search.backend: shared or local
search.corpus: wiki, memory, or all
--mode: auto, find-person, route-question, source-evidence, or raw-claim

Use wiki search for wiki-specific ranking and provenance. For one broad shared recall pass, prefer openclaw memory search when the active memory plugin exposes shared search.

Search modes:

find-person: aliases, handles, socials, canonical IDs, and person pages
route-question: ask-for/best-used-for hints and relationship context
source-evidence: source pages and structured evidence fields
raw-claim: structured claim text with claim/evidence metadata

Examples:

openclaw wiki search "bgroux" --mode find-person
openclaw wiki search "who knows Teams rollout?" --mode route-question
openclaw wiki search "maintainer-whois" --mode source-evidence
openclaw wiki search "strong route Teams" --mode raw-claim --json

Text output includes Claim: and Evidence: lines when a result matches a structured claim. JSON output additionally exposes matchedClaimId, matchedClaimStatus, matchedClaimConfidence, evidenceKinds, and evidenceSourceIds for agent-side drilldown.

`wiki get <lookup>`

Read a wiki page by id or relative path.

openclaw wiki get entity.alpha
openclaw wiki get syntheses/alpha-summary.md --from 1 --lines 80

`wiki apply`

Apply narrow mutations without freeform page surgery:

apply synthesis <title>: create or refresh a synthesis page with a managed summary body
apply metadata <lookup>: update metadata on an existing page

Both accept --source-id, --contradiction, --question (each repeatable), --confidence <n> (0-1), and --status <status>. apply metadata also accepts --clear-confidence to remove a stored confidence value. This is the supported way to evolve wiki pages so managed generated blocks stay intact.

`wiki bridge import`

Import public memory artifacts from the active memory plugin into bridge-backed source pages. Use this in bridge mode to pull the latest exported memory artifacts into the wiki vault.

For active bridge artifact reads, the CLI routes the import through Gateway RPC so it uses the runtime memory plugin context. If bridge imports are disabled or artifact reads are off, the command keeps the local/offline zero-import behavior. Index refresh after import is gated by ingest.autoCompile.

`wiki unsafe-local import`

Import from explicitly configured local paths (unsafeLocal.paths) in unsafe-local mode. Intentionally experimental and same-machine only. Index refresh after import is gated by ingest.autoCompile.

`wiki chatgpt import`

Import a ChatGPT export into draft wiki source pages.

openclaw wiki chatgpt import --export ./chatgpt-export
openclaw wiki chatgpt import --export ./conversations.json --dry-run

Flag	Default	Description
`--export <path>`	(required)	ChatGPT export directory or `conversations.json` path.
`--dry-run`	`false`	Preview created/updated/skipped counts without writing pages.

A non-dry-run import that changes any page records an import run id, printed in the summary, needed for rollback.

`wiki chatgpt rollback <run-id>`

Roll back a previously applied ChatGPT import run, removing pages it created and restoring pages it overwrote. Pages changed after import are moved under the run's .openclaw-wiki/import-runs/<run-id>/recovered/ directory instead of being deleted. Recovery paths remain in the command result on retries and later alreadyRolledBack responses. Interrupted runs remain rolling_back while target recovery or derived-artifact compilation is incomplete. A persisted process-restart fence separates those phases: after it, retries rebuild indexes and compiled caches without rewriting source pages or moving later pathname writes. A later normal compile may refresh machine-managed Related blocks. This covers in-process failure and process restart after ordinary filesystem calls return, not kernel or host power-loss ordering.

`wiki obsidian ...`

Obsidian helper commands for vaults running in Obsidian-friendly mode: status, search, open, command, daily. These require the official obsidian CLI on PATH when obsidian.useOfficialCli is enabled.

Configuration validation rejects obsidian.useOfficialCli: true when vault.scope is agent because obsidian.vaultName is one global setting, not a per-agent mapping. Obsidian-friendly Markdown rendering remains available.

Practical usage guidance

Reach for wiki search and wiki get when tracking origin and page identity is essential.
Prefer wiki apply over manually altering managed generated sections.
Turn to wiki lint before relying on conflicting or low-confidence material.
Apply wiki compile right after bulk imports or source modifications if you need refreshed dashboards and compiled digests without delay.
Choose wiki okf import when a data catalog, documentation export, or agent enrichment pipeline already outputs OKF markdown bundles.
Select wiki bridge import when bridge mode depends on memory artifacts that were recently exported.

Configuration tie-ins

The behavior of openclaw wiki is determined by:

plugins.entries.memory-wiki.config.vaultMode
plugins.entries.memory-wiki.config.vault.scope
plugins.entries.memory-wiki.config.vault.path
plugins.entries.memory-wiki.config.search.backend
plugins.entries.memory-wiki.config.search.corpus
plugins.entries.memory-wiki.config.bridge.*
plugins.entries.memory-wiki.config.obsidian.*
plugins.entries.memory-wiki.config.ingest.autoCompile
plugins.entries.memory-wiki.config.render.*
plugins.entries.memory-wiki.config.context.includeCompiledDigestPrompt

For the complete configuration model, check the Memory Wiki plugin.