Get the FREE Ultimate OpenClaw Setup Guide ā†’
p

2026 02 10 Clawhub Clawvault 1.5.1

Scanned

@pin-alt

npx machina-cli add skill @pin-alt/2026-02-10-clawhub-clawvault-1-5-1 --openclaw
Files (1)
SKILL.md
5.9 KB

ClawVault šŸ˜

An elephant never forgets. Structured memory for OpenClaw agents.

Built for OpenClaw ā€” install via clawhub install clawvault

Install

npm install -g clawvault

Setup

# Initialize vault (creates folder structure + templates)
clawvault init ~/my-vault

# Or set env var to use existing vault
export CLAWVAULT_PATH=/path/to/memory

# Optional: shell integration (aliases + CLAWVAULT_PATH)
clawvault shell-init >> ~/.bashrc

Quick Start for New Agents

# Start your session (recover + recap + summary)
clawvault wake

# Capture 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 --all

# Link single file
clawvault link memory/2024-01-15.md

Folder Structure

vault/
ā”œā”€ā”€ .clawvault/           # Internal state
ā”‚   ā”œā”€ā”€ last-checkpoint.json
ā”‚   ā””ā”€ā”€ dirty-death.flag
ā”œā”€ā”€ decisions/            # Key choices with reasoning
ā”œā”€ā”€ lessons/              # Insights and patterns
ā”œā”€ā”€ people/               # One file per person
ā”œā”€ā”€ projects/             # Active work tracking
ā”œā”€ā”€ handoffs/             # Session continuity
ā”œā”€ā”€ inbox/                # Quick captures
ā””ā”€ā”€ templates/            # Document templates

Best Practices

  1. Wake at session start ā€” clawvault wake restores context
  2. Checkpoint every 10-15 min during heavy work
  3. Sleep before session end ā€” clawvault sleep captures next steps
  4. Use types ā€” knowing WHAT you're storing helps WHERE to put it
  5. Wiki-link liberally ā€” [[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-run

# Fix 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:

  • Orphaned tool_result blocks referencing non-existent tool_use IDs
  • Aborted tool calls with partial JSON
  • Broken parent chain references

Backups are created automatically (use --no-backup to skip).

Troubleshooting

  • qmd not installed ā€” run bun install -g github:tobi/qmd or npm install -g qmd
  • No ClawVault found ā€” run clawvault init or set CLAWVAULT_PATH
  • CLAWVAULT_PATH missing ā€” run clawvault shell-init and add to shell rc
  • Too many orphan links ā€” run clawvault link --orphans
  • Inbox backlog warning ā€” process or archive inbox items
  • "unexpected tool_use_id" error ā€” run clawvault repair-session

Integration with qmd

ClawVault uses qmd for search:

# Install qmd
bun 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

Environment Variables

  • CLAWVAULT_PATH ā€” Default vault path (skips auto-discovery)

Links

Source

git clone https://clawhub.ai/pin-alt/2026-02-10-clawhub-clawvault-1-5-1View on GitHub

Overview

ClawVault provides a structured memory system for OpenClaw agents, enabling persistent context across sessions. It offers context death resilience through checkpoint and recover, structured storage, Obsidian-compatible Markdown, local semantic search, and session transcript repair to keep agent work coherent over time.

How This Skill Works

Install and initialize a vault folder, then capture memories by type (fact, decision, lesson, etc.) and save progress with checkpoints. Sessions start with wake and end with sleep, optionally handing off next steps; a folder structure plus wiki-style linking enables fast recall and transcript repair.

When to Use It

  • Starting a new OpenClaw session and restoring prior context (wake).
  • Building resilience against context death with frequent checkpoints and recover.
  • Organizing memories by type (fact, decision, lesson, relationship, project) for easy retrieval.
  • Coordinating work across handoffs and next actions with a clear transfer of responsibility.
  • Enabling fast local search and notes through Obsidian-compatible Markdown and auto-linking.

Quick Start

  1. Step 1: Initialize vault with clawvault init ~/my-vault or set CLAWVAULT_PATH to an existing vault.
  2. Step 2: Start a session with clawvault wake, then capture notes and checkpoint as you work, and end with clawvault sleep.
  3. Step 3: Optional health check with clawvault doctor to verify the vault and indexing.

Best Practices

  • Wake at session start to restore context as a baseline.
  • Checkpoint every 10-15 minutes during heavy work to guard progress.
  • Sleep at session end to capture next steps and handoffs.
  • Use the designated memory types to organize data effectively.
  • Wiki-link liberally to grow a knowledge graph of people and concepts.

Example Use Cases

  • Recover a crashed session by waking and reviewing the last checkpoint and handoff.
  • Record a key decision and the reasoning in the decisions and lessons folders.
  • Link a client contact in people and reference it in a project to surface context.
  • Semantically search for past discussions to recall the database decision.
  • Handoff a completed PR review with next steps and status to CI.

Frequently Asked Questions

Add this skill to your agents
Sponsor this space

Reach thousands of developers ā†—