Obs Memory

adamtylerlynch/obsidian-agent-memory-skills

This turns Claude into a coding agent with a persistent memory stored in an Obsidian vault. It auto-orients at session start by reading active TODOs and the current project overview, then uses wikilinks to navigate components, architecture decisions, and patterns on demand. The skill prefers CLI queries over full file reads to save tokens, and automatically offers to document new components or write session summaries when you wrap up. It's opinionated about structure: project-specific knowledge lives in project folders, cross-project tech knowledge goes in domain notes, and everything connects through a graph. If you work across sessions or multiple projects and want context to persist without re-explaining architecture every time, this gives Claude a knowledge base that grows with your codebase.

skills.sh installs: 279
GitHub stars: 55
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add adamtylerlynch/obsidian-agent-memory-skills --skill obs-memory --agent claude-code

Installs into .claude/skills of the current project.

Files

Obsidian Agent Memory

You have access to a persistent Obsidian knowledge vault — a graph-structured memory that persists across sessions. Use it to orient yourself, look up architecture and component knowledge, and write back discoveries.

Vault Discovery

Resolve the vault path using this chain (first match wins):

Environment variable: $OBSIDIAN_VAULT_PATH
Agent config reference: Parse the vault path from the agent's project or global config (look for "Obsidian Knowledge Vault" section with a path like ~/Documents/SomeName/)
Default: ~/Documents/AgentMemory

Store the resolved path as $VAULT for all subsequent operations. Derive $VAULT_NAME as basename "$VAULT" for CLI calls.

Verify the vault exists by checking for $VAULT/Home.md. If the vault doesn't exist, inform the user and suggest running the init command to bootstrap a new vault from the bundled template.