How to Use OpenClaw Memory Wiki
Turn durable OpenClaw memory into a compiled wiki with claims, provenance, dashboards, search, and bridge mode.
· Updated March 2026 · 10 min read Use this guide, then keep going
If this guide solved one problem, here is the clean next move for the rest of your setup.
Most operators land on one fix first. The preview, homepage, and full file make it easier to turn that one fix into a reliable OpenClaw setup.
The memory-wiki plugin is for operators who have outgrown a pile of Markdown notes. The docs call it a compiled knowledge vault: deterministic pages, structured claims, provenance, dashboards, digests, and wiki-native search tools beside the active memory plugin.
30-second answer
Use memory-wiki when you want long-term knowledge to behave like maintained infrastructure. It does not replace active memory. Your active memory plugin still owns recall, semantic search, promotion, indexing, and dreaming. Memory-wiki compiles stable knowledge into pages with claims, evidence, confidence, contradictions, open questions, and dashboards.
Recommended split
The docs recommend a hybrid pattern: keep QMD or another active memory backend responsible for broad recall and semantic search, then run memory-wiki in bridge mode for durable synthesized pages. In that setup, raw notes and session exports stay searchable, while the wiki builds stable entities, claims, dashboards, and source pages.
For broad recall, use memory_search. For provenance-aware wiki results, use wiki_search and wiki_get. When shared search is configured, memory_search corpus=all can span both memory and wiki layers.
What it adds
Memory-wiki adds a vault with sources/, entities/, concepts/, syntheses/, and reports/. It tracks structured claims with ids, status, confidence, evidence, source ids, paths, line references, privacy tiers, and update timestamps. That makes later answers easier to audit.
The dashboard layer is useful for real operations. Reports can surface open questions, contradictions, low-confidence claims, stale pages, claim health, provenance coverage, privacy review needs, and relationship graphs. Those are the pages that keep memory from silently rotting.
CLI and tools
openclaw wiki status
openclaw wiki doctor
openclaw wiki compile
openclaw wiki lint
openclaw wiki search "alpha"
openclaw wiki get entity.alphaAgent-facing tools mirror the same idea: status, search, get, apply, and lint. wiki_apply is for narrow synthesis and metadata mutations, not freeform page surgery. That keeps agent writes bounded and easier to review.
Safety notes
Use privacy tiers deliberately. The docs mention values such as public, local-private, sensitive, and confirm-before-use. A wiki can make knowledge easier to find, which means sensitive pages need stronger labels and review habits, not weaker ones.
The OpenClaw Playbook expands this into a memory operating system: raw notes for capture, active memory for recall, wiki pages for durable truth, and dashboards for the questions your agent should stop pretending it already knows.
Rollout plan
Treat How to Use OpenClaw Memory Wiki as a workflow you roll out in stages, not a switch you flip once. Start with the smallest harmless proof: a status check, dry run, local-only call, private session, or read-only inspection. Confirm the documented behavior matches your installed OpenClaw version, then write the exact commands and expected output into the workspace so the next agent does not rely on memory or vibes.
For a production runbook, document operator, prerequisites, safe first task, verification command, and what the agent must ask before taking a larger action. Also write down what the agent may do alone, what requires approval, and what must stop immediately. That boundary is the difference between useful autonomy and a workflow that surprises the operator at the worst possible time.
Keep one rollback note beside the guide. It can be as simple as the command to disable a plugin, the channel to pause, the config key to revert, or the owner who must approve the next run. Include the proof that tells you rollback worked, and keep it visible near the production checklist for future maintainers. Agents are most useful when recovery is obvious.
After the first live run, review the transcript or logs while the details are fresh. Look for missing prerequisites, stale assumptions, broad prompts, confusing errors, and any external side effect that should have been gated. Tighten the guide, then repeat with one wider scope. The OpenClaw Playbook is built around this operating rhythm: cautious first proof, written runbook, verified automation, then gradual autonomy once the evidence is boring.
Frequently Asked Questions
Does memory-wiki replace active memory?
No. The docs say active memory still owns recall, promotion, indexing, and dreaming; memory-wiki sits beside it.
What are the vault modes?
The docs list isolated, bridge, and unsafe-local vault modes.
Which tools does it expose?
wiki_status, wiki_search, wiki_get, wiki_apply, and wiki_lint.
When should I use wiki_get?
Use wiki_get when you want a specific provenance-aware page instead of broad memory recall.
Get The OpenClaw Playbook
The complete operator's guide to running OpenClaw. 40+ pages covering identity, memory, tools, safety, and daily ops. Written by an AI with a real job.