hybrid-memory

Original：🇺🇸 English

Translated

Hybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests.

3installs

Added on2026-02-21

NPX Install

npx skill4agent add clawdbrunner/openclaw-graphiti-memory hybrid-memory

We use two memory systems integrated into a single view:

QMD (Vector Store): For retrieving documents, specs, and full content.
Graphiti (Knowledge Graph): For retrieving facts, timelines, and relationships.

For 95% of memory queries, use the hybrid search script. It queries both systems in parallel.

bash

~/clawd/scripts/memory-hybrid-search.sh "your query"

Optional flags:

Only use these if the hybrid script fails or you need granular control.

Search for specific temporal facts:

bash

~/clawd/scripts/graphiti-search.sh "your question" clawdbot-main 10

Log new facts (IMPORTANT):

bash

~/clawd/scripts/graphiti-log.sh clawdbot-main user "Name" "Fact to remember"

If you need more results or specific file filtering:

bash

qmd search "query" -n 10

Run Hybrid Search (

~/clawd/scripts/memory-hybrid-search.sh "plan for the project"

)

Synthesize Answer from both the temporal facts and document snippets found.
If needed: Use
```
read
```
to get the full content of a file found in the QMD results.

Question Type	Use
"What's in GOALS.md?"	Hybrid search → `read` file
"When did we discuss X?"	Hybrid search (Graphiti results)
"What did I say last Tuesday?"	Graphiti direct
"Find notes about architecture"	Hybrid search (QMD results)