Hybrid Memory System

Two memory systems, each with different strengths. Use both.

When to Use Which

Question Type	Tool	Example
Document content	INLINECODE0	"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?" |

Quick Reference

memory_search (Built-in)

Semantic search over markdown files (MEMORY.md, memory/**/*.md).

CODEBLOCK0

Then use memory_get to read specific lines if needed.

Graphiti (Temporal)

Search for facts with time awareness:

CODEBLOCK1

Log important facts:

CODEBLOCK2

Common group IDs:

• - main-agent — Primary agent
• INLINECODE6 — User's personal context

Recall Pattern

When answering questions about past context:

1. 1. Temporal questions → Check Graphiti first
2. Document questions → Use INLINECODE7
3. Uncertain → Try both, combine results
4. Low confidence → Say you checked but aren't sure

AGENTS.md Template

Add to your AGENTS.md:

CODEBLOCK3bash
graphiti-search.sh "query" main-agent 10

**Document questions** ("what's in X?", "find notes about Y"):

memory_search query="your query"
CODEBLOCK5

Setup

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