Vault PKM

Give Claude persistent, structured memory across conversations using your Obsidian vault. Read, write, search, and navigate your knowledge base — all from within Claude Code.

Under the hood, this Claude Code plugin provides 20 MCP (Model Context Protocol) tools for note creation, semantic search, graph traversal, metadata queries, and session memory — plus agents, hooks, and skills for seamless workflow integration. Published on npm as obsidian-pkm.

If you find this useful, please star the repo — it helps others discover the plugin.

Watch the demo video

Why

Claude Code has built-in memory, but it's flat text files scoped to individual projects — no structure, no search beyond exact matches, no connections between notes, and no way to query across projects. As knowledge grows, it doesn't scale. This server replaces that with a proper PKM layer: structured notes with enforced metadata, semantic search, a navigable knowledge graph, and cross-project access through a single Obsidian vault.

• Structured session memory — Every tool call is logged with timestamps and session IDs, so Claude can recall exactly what was read, written, and searched in previous conversations — not just what was saved to a text file.
• Structured knowledge creation — ADRs, research notes, devlogs, and tasks are created from enforced templates with validated frontmatter — not freeform text dumps. Your vault stays consistent and queryable.
• Semantic discovery — "Find my notes about caching strategies" works even if you never used the word "caching." Conceptual search surfaces relevant knowledge that keyword search misses.
• Graph-aware connections — Claude explores your knowledge graph by following wikilinks, discovering related notes by proximity rather than just content. Link suggestions help weave new notes into your existing web of knowledge.
• Knowledge capture — Decisions, tasks, and research findings are captured by specialized agents in the background without interrupting your coding flow.

Without this, knowledge stays fragmented across per-project memory files and chat logs. With it, your AI assistant maintains a unified knowledge base that compounds over time.

How It Compares

	Vault PKM	remember	Claude built-in memory
Knowledge base	Your Obsidian vault (markdown files you own)	Compressed conversation logs (.remember/ dir)	CLAUDE.md + auto-memory files
Scope	Cross-project (one vault for everything)	Per-project	Per-project (git-repo scoped)
Semantic search	OpenAI embeddings	—	—
Graph traversal	Wikilink BFS, link health audits	—	—
Structured notes	13 templates with validated frontmatter	Plain markdown	Plain markdown
Metadata queries	Filter by type, status, tags, dates, custom fields	—	—
Session memory	Activity log (every tool call with timestamps)	Tiered daily summaries (Haiku-compressed)	Manual (user writes CLAUDE.md)
Setup effort	Medium (vault path + optional OpenAI key)	Low (auto hooks, no config)	None (built-in)
MCP tools	20	0 (hooks-based)	0
Agents	3 (explorer, capture, auditor)	0	0

remember is great for lightweight session continuity with minimal setup. Vault PKM is for developers who want a structured, searchable, interconnected knowledge base that grows with every project.

Features

Knowledge Creation & Editing

Tool	Description
vault_write	Create notes from templates with enforced frontmatter (ADRs, research, devlogs, tasks, etc.)
vault_append	Add content to notes, with positional insert (after/before heading, end of section)
vault_edit	Surgical string replacement for precise edits
vault_update_frontmatter	Atomic YAML frontmatter updates (set, create, remove fields; validates enums by note type)

Discovery & Search

Tool	Description
vault_search	Full-text keyword search across markdown files
vault_semantic_search	Conceptual similarity search via OpenAI embeddings — finds related notes even with different wording
vault_query	Query by YAML frontmatter (type, status, tags, dates, custom fields) with sorting
vault_tags	Discover all tags with per-note counts; folder scoping, glob filters, inline tag parsing
vault_suggest_links	Suggest relevant notes to link based on content similarity

Graph & Connections

Tool	Description
vault_links	Wikilink analysis (incoming and outgoing links for a note)
vault_neighborhood	Graph exploration via BFS wikilink traversal — discover related notes by proximity
vault_add_links	Add annotated wikilinks to a note's section with deduplication
vault_link_health	Audit link quality — find orphans, broken links, weak connections, ambiguous links

Reading & Navigation

Tool	Description
vault_read	Read note contents (pagination by heading, tail, chunk, line range; auto-redirects large files)
vault_peek	Inspect file metadata and structure without reading full content
vault_list	List files and folders
vault_recent	Recently modified files

Organization & Maintenance

Tool	Description
vault_move	Move/rename files with automatic wikilink updating across the vault
vault_trash	Soft-delete to .trash/ (Obsidian convention), warns about broken incoming links

Session Memory

Tool	Description
vault_activity	Cross-conversation memory — logs every tool call with timestamps and session IDs

Agents, Skills & Commands

Agents (3) run autonomously in foreground or background:

Agent	Purpose
vault-explorer	Research existing knowledge before creating notes
pkm-capture	Devlog entries + knowledge capture after commits and work blocks
link-auditor	Audit vault link health after bulk note changes

Skills (6) are guided workflows triggered by slash commands:

Skill	Purpose
pkm-write	Duplicate checking, link discovery, and annotations when creating notes
pkm-explore	Graph + semantic exploration to map existing knowledge on a topic
pkm-session-end	Session wrap-up: devlog, undocumented work capture, link health audit
add-task	Fast task capture from a title with duplicate detection, priority shorthands, and due date
triage-tasks	Surface open tasks as a numbered list with git completion hints; batch-update via shorthand (e.g. 1,3 done | 2 active)
tackle-task	Work a task end-to-end: read, explore vault context, route to the right workflow tier, close when done

Commands (2) for setup and configuration:

Command	Purpose
/vault-pkm:setup	Configure vault path, API keys, and permissions
/vault-pkm:init-project	Connect a code repository to a vault project folder

Prerequisites

• Node.js >= 20 (Node 18 is EOL; uses native fetch and ES modules)
• An MCP-compatible client such as Claude Code

Prebuilt native binaries are included for Node 20/22 on Linux x64, macOS (x64/arm64), and Windows x64. Most users need nothing else. If the prebuilt fails, you'll need C++ build tools — see Troubleshooting.

Quick Start

1. Install the Plugin

claude plugin marketplace add anthropics/claude-plugins-community
claude plugin install vault-pkm@claude-community

2. Configure

Run the setup skill in Claude Code:

/vault-pkm:setup

The setup skill walks you through vault path, API keys, tool permissions, and verification. Hooks are registered automatically by the plugin system.

Important: Restart your Claude Code session after setup completes so the MCP server picks up the new configuration.

3. Scaffold Your Vault (optional)

If you need templates and the PARA folder structure, run the vault scaffolding wizard:

npx obsidian-pkm init

This is separate from the plugin install above — it only sets up your vault's directory structure (PARA folders, note templates). Nothing is written until you confirm each step.

Note: The first npx run downloads and compiles native dependencies, which may take 30-60 seconds. Subsequent runs are instant.

Step 1 — Vault path. Point to an existing Obsidian vault or create a new one. The wizard resolves ~, $HOME, and relative paths automatically. Safety checks prevent using system directories (/, /home, etc.) as a vault. For existing non-empty directories you can use it as-is, create a subfolder inside it, or wipe it (with triple confirmation). You'll be offered an optional backup before any changes.

Step 2 — Note templates. Copies template files into <vault>/05-Templates/. Three options:

• Full set — all 13 templates (adr, daily-note, devlog, fleeting-note, literature-note, meeting-notes, moc, note, permanent-note, project-index, research-note, task, troubleshooting-log)
• Minimal — just note.md (a single generic template)
• Skip — for users with their own templates

Existing templates are never overwritten.

Step 3 — PARA folder structure. Creates 7 top-level folders with _index.md stubs:

Folder	Purpose
00-Inbox/	Quick captures and unsorted notes
01-Projects/	Active project folders
02-Areas/	Ongoing areas of responsibility
03-Resources/	Reference material and reusable knowledge
04-Archive/	Completed or inactive items
05-Templates/	Note templates
06-System/	System configuration and metadata

Each _index.md has type: moc frontmatter. Existing folders and index files are skipped.

4. Verify It Works

Open Claude Code and try:

List the folders in my vault

Claude should call vault_list and show your vault's directory structure. If it works, the server is connected and ready.

5. Enable Semantic Search (optional)

Add your OpenAI API key to ~/.claude/settings.json under the env block:

{
  "env": {
    "VAULT_PATH": "/path/to/vault",
    "VAULT_PKM_OPENAI_KEY": "sk-your-key-here"
  }
}

Use VAULT_PKM_OPENAI_KEY (preferred) to avoid conflicts with project-level OpenAI keys.