Install
openclaw skills install letheclawUse letheClaw to store, search, and manage memories with criticality and provenance.
openclaw skills install letheclawYou can use the letheClaw API to store and retrieve memories for the user or the current session. The API base URL is in the environment variable LETHECLAW_API_URL.
Environment patterns:
http://api:8080http://host.docker.internal:51234http://localhost:51234If LETHECLAW_API_URL is unset, try http://host.docker.internal:51234 first (Docker Desktop default), then ask the user.
When the user asks about history, decisions, prior work, "what did we do", or any past context:
ALWAYS query letheClaw API FIRST:
curl -s "{LETHECLAW_API_URL}/memory/search?q=<query>&limit=5"
Use the returned content field directly — search results include full text. No need for memory_get or flat file access.
NEVER use memory_search tool as the first step. That tool searches flat markdown files, which are backup/reference only.
Apply criticality filtering when appropriate:
&min_criticality=0.7&min_criticality=0.5Use tag pre-filtering when query domain is clear (e.g., tags=moltbook for Moltbook questions).
letheClaw is the authoritative memory system. Flat files may be stale or incomplete.
When the user says "log this", "remember that", or you observe something worth recording:
["episodic", "security", "moltbook"])operator_input (user said it), direct_observation (you verified it), inferred (derived)No exceptions. This is operator-mandated protocol.
{LETHECLAW_API_URL}/memorycontent (required), optional: source (e.g. operator_input, direct_observation, inferred), tags (array), operator, session_key, contextmemory_id (UUID). Save it to update criticality or fetch provenance later.{LETHECLAW_API_URL}/memory/search?q={query}&limit=5min_criticality (0–1) to filter by importance.tags (comma-separated) to pre-filter by tag before semantic search (e.g. tags=moltbook,security)results array with id, content (full text), criticality, tags, source, created_at, access_countImportant: Search results include full content — you do NOT need to call memory_get afterward. Use the returned content directly.
Criticality filtering guidance:
min_criticality=0.7 (critical knowledge only)min_criticality=0.5 (useful and above)Tag pre-filtering (performance optimization): When query intent is clear, pre-filter by tags to reduce search space:
# "Latest Moltbook posts"
curl "{LETHECLAW_API_URL}/memory/search?q=posts&tags=moltbook,episodic&limit=5"
# "Security findings"
curl "{LETHECLAW_API_URL}/memory/search?q=findings&tags=security,semantic&min_criticality=0.7&limit=3"
{LETHECLAW_API_URL}/memory/recent{LETHECLAW_API_URL}/memory/{memory_id}/criticalitycriticality (0–1, required), optional reason{LETHECLAW_API_URL}/memory/{memory_id}/correction{LETHECLAW_API_URL}/memory/{memory_id}/provenanceevents (history of criticality changes: manual_boost, operator_correction, etc.) and correction_count.When the user says they want to remember something, search memory, see why a memory is important, or correct a memory, use the appropriate endpoint above.