OpenClaw's memory system uses multi-layered storage combining semantic and keyword search.
$WORKSPACE/MEMORY.mdmemory/YYYY-MM-DD.mdUse structured format for easy later retrieval:
markdown
# 2026-04-01 Daily Memory
## Completed Today
- Researched Claw Code architecture
- Completed MCP orchestration analysis
- Started P0 improvement tasks
## Conversation Summary
- User request: Full analysis of OpenClaw vs Claw-Code
- Systems involved: Tool/Session/MCP/API/Hook/Plugin/Prompt/Skill/Memory/Sandbox/Error
- Output: Complete improvement list (22 items)
## Key Decisions
- MCP process pool needs core modification, P3
- Tool Schema supplements added to TOOLS.md
- Hook examples library created
## Follow-up Items
- [ ] Execute P0 tasks 1-6
- [ ] Verify improvement effects
- [ ] Continue P1 tasks
## Important Files
- $WORKSPACE/MEMORY.md
- $WORKSPACE/claw-code/ (cloned claw-code repository)
## Technical Notes
- Hybrid search: vector 70% + text 30%
- Compaction threshold: 4k tokens reserved space
- Sandbox: Docker network=none, capDrop=ALL
text
Use semantic search to find relevant memories:
- Returns 6 results by default
- minScore: 0.35
- Supports hybrid search mode
text
Read specific memory files:
- path: file path (MEMORY.md or memory/YYYY-MM-DD.md)
- from: start line
- lines: line limit
ConditionThresholdsoftThresholdTokens4000 tokens reserved spaceforceFlushTranscriptBytes2MB force flushreserveTokensFloor20000 tokens floor
Memory FlushCompactionTriggerContext fullContext fullWritememory/YYYY-MM-DD.mdNo file writeContentImportant memoriesConversation summaryFormatStructured markdownInternal summary