2026 02 10 Clawhub Clawvault 1.5.1
by @pin-alt
Structured memory system for OpenClaw agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, local semantic search, and session transcript repair.
clawhub install 2026-02-10-clawhub-clawvault-1-5-1π About This Skill
name: clawvault version: 1.5.1 description: Structured memory system for OpenClaw agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, local semantic search, and session transcript repair. author: Versatly repository: https://github.com/Versatly/clawvault
ClawVault π
An elephant never forgets. Structured memory for OpenClaw agents.
> Built for OpenClaw β install via clawhub install clawvault
Install
npm install -g clawvault
Setup
# Initialize vault (creates folder structure + templates)
clawvault init ~/my-vaultOr set env var to use existing vault
export CLAWVAULT_PATH=/path/to/memoryOptional: shell integration (aliases + CLAWVAULT_PATH)
clawvault shell-init >> ~/.bashrc
Quick Start for New Agents
# 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
Core Commands
Wake + Sleep (primary)
clawvault wake
clawvault sleep "what I was working on" --next "ship v1" --blocked "waiting for API key"
Store memories by type
# 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"
Quick capture to inbox
clawvault capture "TODO: Review PR tomorrow"
Search (requires qmd installed)
# Keyword search (fast)
clawvault search "client contacts"Semantic search (slower, more accurate)
clawvault vsearch "what did we decide about the database"
Context Death Resilience
Wake (start of session)
clawvault wake
Sleep (end of session)
clawvault sleep "what I was working on" --next "finish docs" --blocked "waiting for review"
Checkpoint (save state frequently)
clawvault checkpoint --working-on "PR review" --focus "type guards" --blocked "waiting for CI"
Recover (manual check)
clawvault recover --clear
Shows: death time, last checkpoint, recent handoff
Handoff (manual session end)
clawvault handoff \
--working-on "ClawVault improvements" \
--blocked "npm token" \
--next "publish to npm, create skill" \
--feeling "productive"
Recap (bootstrap new session)
clawvault recap
Shows: recent handoffs, active projects, pending commitments, lessons
Auto-linking
Wiki-link entity mentions in markdown files:
# Link all files
clawvault link --allLink single file
clawvault link memory/2024-01-15.md
Folder Structure
vault/
βββ .clawvault/ # Internal state
β βββ last-checkpoint.json
β βββ dirty-death.flag
βββ decisions/ # Key choices with reasoning
βββ lessons/ # Insights and patterns
βββ people/ # One file per person
βββ projects/ # Active work tracking
βββ handoffs/ # Session continuity
βββ inbox/ # Quick captures
βββ templates/ # Document templates
Best Practices
1. Wake at session start β clawvault wake restores context
2. Checkpoint every 10-15 min during heavy work
3. Sleep before session end β clawvault sleep captures next steps
4. Use types β knowing WHAT you're storing helps WHERE to put it
5. Wiki-link liberally β [[person-name]] builds your knowledge graph
Checklist for AGENTS.md
## 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
Session Transcript Repair (v1.5.0+)
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-sessionRepair a specific session
clawvault repair-session --session --agent 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).
Troubleshooting
bun install -g github:tobi/qmd or npm install -g qmdclawvault init or set CLAWVAULT_PATHclawvault shell-init and add to shell rcclawvault link --orphansclawvault repair-sessionIntegration with qmd
ClawVault uses qmd for search:
# Install qmd
bun install -g github:tobi/qmdAdd vault as collection
qmd collection add /path/to/vault --name my-memory --mask "**/*.md"Update index
qmd update && qmd embed
Environment Variables
CLAWVAULT_PATH β Default vault path (skips auto-discovery)Links
βοΈ Configuration
# Initialize vault (creates folder structure + templates)
clawvault init ~/my-vaultOr set env var to use existing vault
export CLAWVAULT_PATH=/path/to/memoryOptional: shell integration (aliases + CLAWVAULT_PATH)
clawvault shell-init >> ~/.bashrc
π Tips & Best Practices
1. Wake at session start β clawvault wake restores context
2. Checkpoint every 10-15 min during heavy work
3. Sleep before session end β clawvault sleep captures next steps
4. Use types β knowing WHAT you're storing helps WHERE to put it
5. Wiki-link liberally β [[person-name]] builds your knowledge graph