ClawVault
Agent memory system with memory graph, context profiles, checkpoint/recover, structured storage, semantic search, observational memory, task tracking, canvas...
Agent memory system with memory graph, context profiles, checkpoint/recover, structured storage, semantic search, observational memory, task tracking, canvas...
Real data. Real impact.
Emerging
Developers
Per week
Open source
Skills give you superpowers. Install in 30 seconds.
An elephant never forgets. Structured memory for OpenClaw agents.
Built for OpenClaw. Canonical install: npm CLI + hook install + hook enable.
What this skill does:
CLAWVAULT_PATH or auto-discovered)repair-session reads and modifies OpenClaw session transcripts (~/.openclaw/agents/) ā creates backups before writinghooks/clawvault/handler.js) with lifecycle events (gateway:startup, gateway:heartbeat, command:new, session:start, compaction:memoryFlush, cron.weekly). Hook is opt-in and must be installed/enabled.observe --compress makes LLM API calls (Gemini Flash by default) to compress session transcripts into observationsEnvironment variables used:
CLAWVAULT_PATH ā vault location (optional, auto-discovered if not set)OPENCLAW_HOME / OPENCLAW_STATE_DIR ā used by repair-session to find session transcriptsGEMINI_API_KEY ā used by observe for LLM compression (optional, only if using observe features)No cloud sync ā all data stays local. No network calls except LLM API for observe compression.
This is a full CLI tool, not instruction-only. It writes files, registers hooks, and runs code.
Auditability: the published ClawHub skill bundle includes
SKILL.md, HOOK.md, and hooks/clawvault/handler.js so users can inspect hook behavior before enabling it.
npm install -g clawvault openclaw hooks install clawvault openclaw hooks enable clawvaultVerify and reload
openclaw hooks list --verbose openclaw hooks info clawvault openclaw hooks check
restart gateway process
clawhub install clawvault can install skill guidance, but does not replace explicit hook pack installation.
# 1) Review package metadata before install npm view clawvault version dist.integrity dist.tarball repository.url2) Install CLI + qmd dependency
npm install -g clawvault@latest npm install -g github:tobi/qmd
3) Install hook pack, but DO NOT enable yet
openclaw hooks install clawvault
4) Review hook source locally before enabling
node -e "const fs=require('fs');const p='hooks/clawvault/handler.js';console.log(fs.existsSync(p)?p:'hook file not found in current directory')" openclaw hooks info clawvault
5) Enable only after review
openclaw hooks enable clawvault openclaw hooks check
# Initialize vault (creates folder structure + templates) clawvault init ~/my-vaultOr set env var to use existing vault
export CLAWVAULT_PATH=/path/to/memory
Optional: shell integration (aliases + CLAWVAULT_PATH)
clawvault shell-init >> ~/.bashrc
# Start your session (recover + recap + summary) clawvault wakeCapture and checkpoint during work
clawvault capture "TODO: Review PR tomorrow" clawvault checkpoint --working-on "PR review" --focus "type guards"
End your session with a handoff
clawvault sleep "PR review + type guards" --next "respond to CI" --blocked "waiting for CI"
Health check when something feels off
clawvault doctor
# Verify runtime compatibility with current OpenClaw setup clawvault compatVerify qmd is available
qmd --version
Verify OpenClaw CLI is installed in this shell
openclaw --version
ClawVault currently depends on
qmd for core vault/query flows.
ClawVault builds a typed knowledge graph from wiki-links, tags, and frontmatter:
# View graph summary clawvault graphRefresh graph index
clawvault graph --refresh
Graph is stored at
.clawvault/graph-index.json ā schema versioned, incremental rebuild.
# Default context (semantic + graph neighbors) clawvault context "database decision"With a profile preset
clawvault context --profile planning "Q1 roadmap" clawvault context --profile incident "production outage" clawvault context --profile handoff "session end"
Auto profile (used by OpenClaw hook)
clawvault context --profile auto "current task"
| Profile | Purpose |
|---|---|
| Balanced retrieval |
| Broader strategic context |
| Recent events, blockers, urgent items |
| Session transition context |
| Hook-selected profile based on session intent |
# Check hook wiring, event routing, handler safety clawvault compatStrict mode for CI
clawvault compat --strict
clawvault wake clawvault sleep "what I was working on" --next "ship v1" --blocked "waiting for API key"
# Types: fact, feeling, decision, lesson, commitment, preference, relationship, project clawvault remember decision "Use Postgres over SQLite" --content "Need concurrent writes for multi-agent setup" clawvault remember lesson "Context death is survivable" --content "Checkpoint before heavy work" clawvault remember relationship "Justin Dukes" --content "Client contact at Hale Pet Door"
clawvault capture "TODO: Review PR tomorrow"
# Keyword search (fast) clawvault search "client contacts"Semantic search (slower, more accurate)
clawvault vsearch "what did we decide about the database"
clawvault wake
clawvault sleep "what I was working on" --next "finish docs" --blocked "waiting for review"
clawvault checkpoint --working-on "PR review" --focus "type guards" --blocked "waiting for CI"
clawvault recover --clear # Shows: death time, last checkpoint, recent handoff
clawvault handoff \ --working-on "ClawVault improvements" \ --blocked "npm token" \ --next "publish to npm, create skill" \ --feeling "productive"
clawvault recap # Shows: recent handoffs, active projects, pending commitments, lessons
Wiki-link entity mentions in markdown files:
# Link all files clawvault link --allLink single file
clawvault link memory/2024-01-15.md
vault/ āāā .clawvault/ # Internal state ā āāā last-checkpoint.json ā āāā dirty-death.flag āāā decisions/ # Key choices with reasoning āāā lessons/ # Insights and patterns āāā people/ # One file per person āāā projects/ # Active work tracking āāā handoffs/ # Session continuity āāā inbox/ # Quick captures āāā templates/ # Document templates
clawvault wake restores contextclawvault sleep captures next steps[[person-name]] builds your knowledge graph## Memory Checklist - [ ] Run `clawvault wake` at session start - [ ] Checkpoint during heavy work - [ ] Capture key decisions/lessons with `clawvault remember` - [ ] Use wiki-links like `[[person-name]]` - [ ] End with `clawvault sleep "..." --next "..." --blocked "..."` - [ ] Run `clawvault doctor` when something feels off
Append this checklist to existing memory instructions. Do not replace your full AGENTS.md behavior unless you intend to.
When the Anthropic API rejects with "unexpected tool_use_id found in tool_result blocks", use:
# See what's wrong (dry-run) clawvault repair-session --dry-runFix it
clawvault repair-session
Repair a specific session
clawvault repair-session --session <id> --agent <agent-id>
List available sessions
clawvault repair-session --list
What it fixes:
tool_result blocks referencing non-existent tool_use IDsBackups are created automatically (use
--no-backup to skip).
qmd --versionclawvault init or set CLAWVAULT_PATHclawvault shell-init and add to shell rcclawvault link --orphansclawvault repair-sessionclawvault compatopenclaw hooks install clawvault, then openclaw hooks enable clawvault, restart gateway, and verify via openclaw hooks list --verboseclawvault graph --refreshclawvault context --profile incident or --profile planningnpm run typecheck)449/449)clawvault compat --strict (requires local openclaw binary for full runtime validation)ClawVault uses qmd for search:
# Install qmd bun install -g github:tobi/qmdAlternative
npm install -g github:tobi/qmd
Add vault as collection
qmd collection add /path/to/vault --name my-memory --mask "**/*.md"
Update index
qmd update && qmd embed
CLAWVAULT_PATH ā Default vault path (skips auto-discovery)OPENCLAW_HOME ā OpenClaw home directory (used by repair-session)OPENCLAW_STATE_DIR ā OpenClaw state directory (used by repair-session)GEMINI_API_KEY ā Used by observe for LLM-powered compression (optional)No automatic installation available. Please visit the source repository for installation instructions.
View Installation Instructions1,500+ AI skills, agents & workflows. Install in 30 seconds. Part of the Torly.ai family.
Ā© 2026 Torly.ai. All rights reserved.