clawvault

Persist markdown-native memory graphs and context profiles across AI agent sessions.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Versatly/clawvault --skill clawvault-versatly
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clawvault
Source: https://github.com/Versatly/clawvault/tree/main
Command: npx skills add https://github.com/Versatly/clawvault --skill clawvault-versatly

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

AI agents often lose context between sessions. ClawVault provides a structured, markdown-native memory layer that persists across sessions, enabling durable recall and graph-based context.

Core Features & Use Cases

  • Memory graph with wiki-links and typed entities for knowledge graph navigation
  • Context profiles and checkpoint/recover primitives for session resilience
  • Markdown-native storage compatible with Obsidian workflows and local-first memory
  • Observational memory extraction from sessions for durable, auditable memory

Quick Start

Start a new session with clawvault wake to load memory context and begin capturing memories.

Frequently Asked Questions about clawvault

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add persistent memory to AI agents across sessions?

You can provide persistent memory by using a markdown-native memory layer that captures context across sessions. This approach supports a memory graph and observational memory extraction for durable recall.

What's the best way to store AI agent memory in markdown format?

Storing AI agent memory in markdown is best handled by writing to a local vault using wiki-links and typed entities. This builds a navigable knowledge graph compatible with local-first markdown workflows.

Can I use clawvault memory with Obsidian workflows?

Yes, clawvault memory integrates directly with Obsidian workflows using markdown-native local vaults. It stores context profiles and memory graphs as standard markdown files, ensuring seamless compatibility.

How do I recover context after an AI agent session crashes?

Recovering context after a session crash requires using checkpoint and recover primitives. These mechanisms save session state and observational memory, enabling the agent to resume operations seamlessly.

How does a memory graph improve context-aware reasoning for AI agents?

A memory graph improves AI reasoning by mapping typed entities and wiki-links to navigate relationships. This structure lets agents retrieve connected context profiles and historical observations for planning.

Do I need OpenClaw compatibility to use local memory checkpoints?

OpenClaw compatibility checks are supported but not strictly required for basic local memory checkpoints. The system provides an open plugin surface and CLI commands for memory operations independently.