mcpField
H
hybrid-memory

hybrid-memory

github.com/clawdbrunnerAgent workflows10360 installsUpdated 14w ago
Repository

About hybrid-memory

hybrid-memory is a memory skill that combines QMD document search with Graphiti knowledge-graph retrieval. It is intended for agents that need to recall document content alongside facts, timelines, and relationships.

Key features

  1. 01Parallel search across QMD and Graphiti
  2. 02Optional agent group selection
  3. 03JSON output option
  4. 04Direct Graphiti search and fact logging
  5. 05QMD search with result and file filtering

Use cases

  1. 01Finding project plans and reading referenced files
  2. 02Recalling when a topic was discussed
  3. 03Searching architecture notes

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/clawdbrunner/openclaw-graphiti-memory --skill hybrid-memory

After installing, type/hybrid-memoryin Claude Code to confirm it loaded.

Details

From the project README

Hybrid Memory System

We use two memory systems integrated into a single view:

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

Primary Tool

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

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

Optional flags:

  • [group_id] — Specify agent group (default: openclaw-main)
  • --json — Output JSON for programmatic use

Specific Tools (Advanced)

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

Graphiti Only (Temporal/Facts)

Search for specific temporal facts:

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

Log new facts (IMPORTANT):

~/.openclaw/scripts/graphiti-log.sh openclaw-main user "Name" "Fact to remember"
QMD Only (Deep Document Search)

If you need more results or specific file filtering:

qmd search "query" -n 10

Recall Pattern

  1. User asks question ("What was the plan for the project?")
  2. Run Hybrid Search (~/.openclaw/scripts/memory-hybrid-search.sh "plan for the project")
  3. Synthesize Answer from both the temporal facts and document snippets found.
  4. If needed: Use read to get the full content of a file found in the QMD results.

When to Use Which

Question TypeUse
"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)

Comments

Markdown supported