How do I install the Hybrid Memory skill?

Run npx skillmds@latest add tomevault-io/hybrid-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hybrid Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hybrid Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hybrid Memory free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hybrid Memory?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hybrid Memory by tomevault-io — Agent Skill

Name: Hybrid Memory
Author: tomevault-io

Hybrid Memory

Recalls past conversations, retrieves stored facts, and searches documents using OpenClaw QMD vector memory and Graphiti temporal knowledge graph. Use when the user asks to remember something, recall a previous discussion, look up what was said before, find prior context, check conversation history, or retrieve a stored fact or document. Use when this capability is needed.

tomevault-io 41224d7 2 files · 3.8 KB Updated Sep 17, 2026

File contents

Hybrid Memory System

Combines two memory backends into a single recall layer:

QMD (Vector Store): Retrieves documents, specs, and full-text content by semantic similarity.
Graphiti (Knowledge Graph): Retrieves temporal facts, entity relationships, and cross-agent knowledge.

Primary Tool

For most memory queries, use the hybrid search script. It queries both systems in parallel and merges results.

~/.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)

Use these when the hybrid script returns no results, or when you need granular control over a single backend.

Graphiti Only (Temporal/Facts)

Search for specific temporal facts:

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

Log new facts (IMPORTANT — do this after key conversations or decisions):

~/.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

User asks question ("What was the plan for the project?")
Run Hybrid Search (~/.openclaw/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.
If no results: Retry with broader terms, try Graphiti direct (graphiti-search.sh), or widen QMD search (qmd search "query" -n 20).

Proactive Logging

Keep the knowledge graph current by logging important facts after they occur:

After the user shares a preference, decision, or key fact
After completing a task with outcomes worth remembering
After learning new entity relationships (people, projects, systems)

~/clawd/scripts/graphiti-log.sh clawdbot-main user "UserName" "User decided to use PostgreSQL for the new service"

When to Use Which

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)
"Remember that I prefer dark mode"	`graphiti-log.sh` to store the fact

Source: clawdbrunner/openclaw-graphiti-memory — distributed by TomeVault.

---name: hybrid-memorydescription: Recalls past conversations, retrieves stored facts, and searches documents using OpenClaw QMD vector memory and Graphiti temporal knowledge graph. Use when the user asks to remember something, recall a previous discussion, look up what was said before, find prior context, check conversation history, or retrieve a stored fact or document. Use when this capability is needed.---# Hybrid Memory SystemCombines two memory backends into a single recall layer:1. **QMD (Vector Store):** Retrieves documents, specs, and full-text content by semantic similarity.2. **Graphiti (Knowledge Graph):** Retrieves temporal facts, entity relationships, and cross-agent knowledge.## Primary ToolFor most memory queries, use the hybrid search script. It queries both systems in parallel and merges results.```bash~/.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)Use these when the hybrid script returns no results, or when you need granular control over a single backend.### Graphiti Only (Temporal/Facts)Search for specific temporal facts:```bash~/.openclaw/scripts/graphiti-search.sh "your question" openclaw-main 10```Log new facts (IMPORTANT — do this after key conversations or decisions):```bash~/.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:```bashqmd search "query" -n 10```## Recall Pattern1. **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.5. **If no results:** Retry with broader terms, try Graphiti direct (`graphiti-search.sh`), or widen QMD search (`qmd search "query" -n 20`).## Proactive LoggingKeep the knowledge graph current by logging important facts after they occur:- After the user shares a preference, decision, or key fact- After completing a task with outcomes worth remembering- After learning new entity relationships (people, projects, systems)```bash~/clawd/scripts/graphiti-log.sh clawdbot-main user "UserName" "User decided to use PostgreSQL for the new service"```## When to Use Which| 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) || "Remember that I prefer dark mode" | `graphiti-log.sh` to store the fact |---> Source: [clawdbrunner/openclaw-graphiti-memory](https://github.com/clawdbrunner/openclaw-graphiti-memory) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions