Two memory systems, each with different strengths. Use both.
| Question Type | Tool | Example |
|---|---|---|
| -------------- | ------ | --------- |
| Document content | memory_search | "What's in GOALS.md?" |
| Curated notes | memory_search | "What are our project guidelines?" |
| Temporal facts | Graphiti | "When did we set up Slack?" |
| Conversations | Graphiti | "What did the user say last Tuesday?" |
| Entity tracking | Graphiti | "What projects involve Alice?" |
Semantic search over markdown files (MEMORY.md, memory/*/.md).
memory_search query="your question"
Then use memory_get to read specific lines if needed.
Search for facts with time awareness:
graphiti-search.sh "your question" GROUP_ID 10
Log important facts:
graphiti-log.sh GROUP_ID user "Name" "Fact to remember"
Common group IDs:
main-agent — Primary agentuser-personal — User's personal contextWhen answering questions about past context:
memory_searchAdd to your AGENTS.md:
### Memory Recall (Hybrid)
**Temporal questions** ("when?", "what changed?", "last Tuesday"):
graphiti-search.sh "query" main-agent 10
**Document questions** ("what's in X?", "find notes about Y"):
memory_search query="your query"
When answering past context: check Graphiti for temporal, memory_search for docs.
Full setup guide: https://github.com/clawdbrunner/openclaw-graphiti-memory
Part 1: OpenClaw Memory — Configure embedding provider (Gemini recommended)
Part 2: Graphiti — Deploy Docker stack, install sync daemons
共 1 个版本