Skip to main content
memory-wiki is a bundled plugin that compiles durable knowledge into a navigable wiki: deterministic pages, structured claims with evidence, provenance, dashboards, and machine-readable digests. It does not replace the active memory plugin. Recall, promotion, indexing, and dreaming stay owned by whichever memory backend is configured (memory-core, QMD, Honcho, etc.). memory-wiki sits beside it and compiles knowledge into a maintained wiki layer. Practical rule:
  • memory_search for one broad recall pass across whatever corpora are configured
  • wiki_search / wiki_get when you want wiki-specific ranking, provenance, or page-level belief structure
  • memory_search corpus=all to span both layers in one call, when the active memory plugin supports corpus selection
A common local-first setup: QMD as the active memory backend for recall, and memory-wiki in bridge mode for durable synthesized pages. See the QMD + bridge mode example under Configuration. If bridge mode reports zero exported artifacts, the active memory plugin is not currently exposing public bridge inputs. Run openclaw wiki doctor first, then confirm the active memory plugin supports public artifacts.

​
Vault modes

  • isolated (default): own vault, own sources, no dependency on the active memory plugin. Use this for a self-contained curated knowledge store.
  • bridge: reads public memory artifacts and event logs from the active memory plugin through public plugin SDK seams. Use this to compile the memory plugin’s exported artifacts without reaching into private plugin internals.
  • unsafe-local: explicit same-machine escape hatch for local private paths. Intentionally experimental and non-portable; use only when you understand the trust boundary and specifically need local filesystem access bridge mode cannot provide.
Vault mode and vault scope are separate choices:
  • vaultMode chooses where wiki inputs come from.
  • vault.scope chooses whether all agents use one vault or each agent gets a child vault.
vault.scope: "global" is the default and preserves the existing single-vault behavior. Use vault.scope: "agent" with isolated or bridge mode when agents must not share wiki pages, compiled digests, search results, or writes. Agent scope cannot be combined with unsafe-local mode because those configured private paths are not agent-owned inputs. Configuration validation rejects this combination. Bridge mode can index, per bridge.* config toggle:
  • exported memory artifacts (indexMemoryRoot)
  • daily notes (indexDailyNotes)
  • dream reports (indexDreamReports)
  • memory event logs (followMemoryEvents)
When bridge mode is active and bridge.readMemoryArtifacts is enabled, openclaw wiki status, openclaw wiki doctor, and openclaw wiki bridge import route through the running Gateway so they see the same active memory plugin context as agent/runtime memory. If bridge is disabled or artifact reads are off, those commands keep local/offline behavior.

​
Vault layout

Managed content stays inside generated blocks; human note blocks are preserved across regeneration.
  • sources/: imported raw material and bridge/unsafe-local-backed pages
  • entities/: durable things, people, systems, projects, objects
  • concepts/: ideas, abstractions, patterns, policies (also the landing spot for OKF imports)
  • syntheses/: compiled summaries and maintained rollups
  • reports/: generated dashboards

​
Open Knowledge Format imports

Import an unpacked Open Knowledge Format bundle into wiki concept pages. Good fit when a data catalog, documentation crawler, or enrichment agent already produces OKF: keep OKF as the portable exchange artifact, let memory-wiki turn it into OpenClaw-native concept pages and compiled digests.
  • non-reserved .md files are concept documents
  • each imported concept requires a non-empty type frontmatter field; missing type produces a missing-type warning and the file is skipped
  • unknown type values are accepted as generic concepts
  • index.md and log.md are reserved and never imported as concepts
  • broken or external markdown links are left unchanged
Imported pages flatten under concepts/ so existing compile, search, get, and dashboard flows see them without a second wiki tree. Each page keeps the original OKF concept ID, source path, type, resource, tags, timestamp, and full producer frontmatter. Internal OKF links rewrite to the generated wiki concept pages and also emit structured relationships entries with kind: okf-link.

​
Structured claims and evidence

Pages carry structured claims frontmatter, not just freeform text. Each claim can include id, text, status, confidence, evidence[], and updatedAt. Each evidence entry can include kind, sourceId, path, lines, weight, confidence, privacyTier, note, and updatedAt. This makes the wiki behave like a belief layer, not a passive note dump. Claims can be tracked, scored, contested, and resolved back to sources.

​
Agent-facing entity metadata

Entity pages carry generic routing metadata usable for people, teams, systems, projects, or any other entity type:
  • entityType: for example person, team, system, project
  • canonicalId: stable identity key across aliases and imports
  • aliases: names, handles, or labels that resolve to the same page
  • privacyTier: free-form string; public is treated as no-review, any other value (for example local-private, sensitive, confirm-before-use) is flagged in reports/privacy-review.md
  • bestUsedFor / notEnoughFor: compact routing hints
  • lastRefreshedAt: source-refresh timestamp, separate from page edit time
  • personCard: optional person-specific routing card (handles, socials, emails, timezone, lane, ask-for, avoid-asking-for, confidence, privacy tier)
  • relationships: typed edges to related pages (target, kind, weight, confidence, evidence kind, privacy tier, note)
For a people wiki, start with reports/person-agent-directory.md, then open the person page with wiki_get before using contact details or inferred facts.

​
Compile pipeline

Compile reads wiki pages, normalizes summaries, and emits stable machine-facing artifacts under:
  • .openclaw-wiki/cache/agent-digest.json
  • .openclaw-wiki/cache/claims.jsonl
Agents and runtime code read these digests instead of scraping Markdown. Compiled output also powers first-pass wiki indexing for search/get, claim-id lookup back to owning pages, compact prompt supplements, and report generation.

​
Dashboards and health reports

When render.createDashboards is enabled, compile maintains dashboards under reports/:

​
Search and retrieval

Two search backends:
  • shared: use the shared memory search flow when available
  • local: search the wiki locally
Three corpora: wiki, memory, all.
  • wiki_search / wiki_get use compiled digests as a first pass when possible
  • claim ids resolve back to the owning page
  • contested/stale/fresh claims influence ranking
  • provenance labels survive into results
Search modes (--mode / tool mode param): When a result matches a structured claim, wiki_search returns matchedClaimId, matchedClaimStatus, matchedClaimConfidence, evidenceKinds, and evidenceSourceIds in its details payload. Text output includes compact Claim: and Evidence: lines when available.

​
Agent tools

The plugin also registers a non-exclusive memory corpus supplement, so shared memory_search and memory_get can reach the wiki when the active memory plugin supports corpus selection.

​
Prompt and context behavior

When context.includeCompiledDigestPrompt is enabled, memory prompt sections append a compact compiled snapshot from agent-digest.json: top pages only, top claims only, contradiction count, question count, confidence/freshness qualifiers. This is opt-in because it changes prompt shape; it mainly matters for context engines or prompt assembly that explicitly consume memory supplements.

​
Configuration

Put config under plugins.entries.memory-wiki.config:
Key toggles:

​
Per-agent vaults

Set vault.scope to agent to give every configured agent a separate wiki. In this scope, vault.path is a parent directory and OpenClaw appends the normalized agent id:
This resolves to ~/.openclaw/wiki/support and ~/.openclaw/wiki/marketing. If vault.path is omitted in agent scope, the parent defaults to ~/.openclaw/wiki. The default main agent therefore keeps the existing ~/.openclaw/wiki/main path. Agent tools, compiled prompt digests, and the wiki supplement exposed through memory_search / memory_get resolve the vault from the active agent context. For CLI and Gateway calls in a setup with multiple configured agents, provide the agent explicitly with openclaw wiki --agent <agentId> ... or the Gateway request’s agentId. A single configured agent remains the default when no id is provided. In bridge mode, agent-scoped imports accept a public memory artifact only when its agentIds includes the selected agent. Artifacts owned by another agent, without ownership metadata, or with an unknown owner are skipped. Global scope keeps the existing shared-artifact behavior.
Changing vault.scope does not copy or split an existing vault. In agent scope, an explicitly configured vault.path becomes a parent directory, so move or import existing pages deliberately before switching production agents. Back up the vault first.Per-agent vaults are a same-process knowledge boundary, not an operating-system security boundary. Plugins and unsandboxed tools with host filesystem access can still read another agent’s directory. Use sandboxing or separate Gateway profiles when agents do not trust each other.

​
Example: QMD + bridge mode

Use this when you want QMD for recall and memory-wiki for a maintained knowledge layer. Each layer stays focused: QMD keeps raw notes, session exports, and extra collections searchable, while memory-wiki compiles stable entities, claims, dashboards, and source pages.
This keeps QMD in charge of active memory recall, memory-wiki focused on compiled pages and dashboards, and prompt shape unchanged until you intentionally enable compiled digest prompts.

​
CLI

See CLI: wiki for the full command reference, including wiki okf import, wiki apply metadata, wiki unsafe-local import, wiki chatgpt import / wiki chatgpt rollback, and the full wiki obsidian subcommand set.

​
Obsidian support

When vault.renderMode is obsidian, the plugin writes Obsidian-friendly Markdown and can optionally use the official obsidian CLI for status probing, vault search, opening a page, invoking a command, and jumping to the daily note. This is optional; the wiki still works in native mode without Obsidian. Agent-scoped vaults can still use Obsidian-friendly Markdown, but configuration validation rejects obsidian.useOfficialCli: true with vault.scope: "agent". The current obsidian.vaultName setting is global and cannot select a distinct Obsidian vault for each agent. Use the wiki tools and CLI operations instead, or keep an Obsidian-operated wiki in global scope.
1

Keep the active memory plugin for recall

Recall, promotion, and dreaming stay owned by the configured memory backend.
2

Enable memory-wiki

Start with isolated mode unless you explicitly want bridge mode.
3

Use wiki_search / wiki_get when provenance matters

Prefer these over memory_search when you want wiki-specific ranking or page-level belief structure.
4

Use wiki_apply for narrow syntheses or metadata updates

Avoid hand-editing managed generated blocks.
5

Run wiki_lint after meaningful changes

Catches contradictions, open questions, and provenance gaps.
6

Turn on dashboards for stale/contradiction visibility

Set render.createDashboards: true (default).