Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By onebrain-ai
Supercharge Obsidian vaults with AI: capture stream-of-consciousness braindumps and classify into tasks/ideas/projects/notes, extract action items, research web topics into structured Markdown summaries, review session logs for insights and patterns, import files/PDFs, suggest wikilinks to build knowledge graphs, generate dashboards like TASKS.md and MOC.md, and run vault health diagnostics.
npx claudepluginhub onebrain-ai/onebrain --plugin onebrainClassifies an inbox note and recommends target folder, subfolder, filename, and wikilinks for /consolidate
Scans vault for unlinked notes and suggests wikilink connections between related content
After a new note is written, scans the vault for related notes and automatically adds up to 3 wikilinks under a ## Related section
Scans vault tags and suggests up to 3 to add to a new note's frontmatter
Scans a braindump note for action items and extracts them as vault tasks
Quick URL bookmark capture : paste a link, AI generates name and description, suggests category, saves to Bookmarks.md in awesome-list format. Invoke when user wants to save a URL for later — bare URL with no other context defaults to this. Do NOT use for: deeply processing or summarizing the URL content now (use summarize), saving a note that is not a URL (use capture), or researching a topic from scratch (use research).
Capture a stream of raw thoughts : classify them and file to inbox with action items extracted. Use when the user signals a free-form, stream-of-consciousness dump with multiple unrelated threads — 'let me dump everything on my mind'. Do NOT use for: a single titled idea (use capture), saving a URL (use bookmark), or anything structured and focused.
Quick note capture with automatic wikilink suggestions to related existing notes. Use when the user wants to save a single, specific, titled idea, insight, or piece of information to the vault. Do NOT use for: unstructured multi-thread thought dumps (use braindump), saving a URL for later (use bookmark), deeply summarizing an article or URL (use summarize), processing a book (use reading-notes), or teaching the agent a preference (use learn).
Clone your agent's portable context (agent folder including MEMORY.md) to a folder for transfer to another vault. Use only when the user explicitly wants to migrate or copy agent memory to a new vault. Do NOT use for: backing up the whole vault, updating OneBrain (use update), or reviewing memory (use memory-review).
Find connections between notes and suggest wikilinks to strengthen the knowledge graph. Use when the user wants to discover how existing notes relate to each other — 'find connections', 'what links to this note', 'strengthen my graph'. Do NOT use for: creating new notes (use capture), processing inbox (use consolidate), or searching for specific content (search directly).
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Plugin-first second brain package for AI agents and humans.
Automatic Claude Code -> Obsidian second brain: zero-config session capture, hybrid search, autonomous recall, daily/lessons/preferences.
Personal knowledge management with brain CLI - capture notes, manage todos, auto-sync, and search your second brain
Set up or upgrade an AI-powered Obsidian vault with journaling, knowledge graphs, pattern recognition, and meeting workflows. Includes skills for daily journaling, weekly insights, graphify knowledge graphs, humanizer, and more.
The bridge between Claude's working memory and Basic Memory's durable knowledge graph — session briefings, pre-compaction checkpoints, and capture reflexes
Extended Second Brain that learns as you work in Claude Code
Your AI forgets everything when the session ends.
Your notes, your AI, and your tools live in separate silos.
OneBrain fixes both — giving you a thinking partner that remembers everything.
Your personal AI OS — persistent memory, 24+ skills, and a full local stack
(Claude Code + Obsidian + tmux + Telegram), entirely on your own machine.
Get Started → · View Commands →
OneBrain is an AI operating system layer built on top of Obsidian. It gives your AI agent persistent memory, a structured knowledge vault, and 24+ pre-built skills — so every session picks up exactly where the last one left off.
Unlike chat-based AI tools, OneBrain lives in plain Markdown files you own forever. No cloud sync required. No proprietary format. Just your agent, your vault, your data.
Most tools ask you to query an AI. OneBrain co-evolves with you — every preference you teach sharpens the agent, every link it surfaces sharpens you.
The bidirectional flow:
Harness-agnostic — Claude Code · Gemini CLI · OpenAI Codex · Qwen · or BYO LLM via API key. See the architecture ↓
OneBrain doesn't compete with Claude Code, Gemini CLI, or any other AI harness — it extends them. Whichever harness you drive, OneBrain adds the persistent memory, skill surface, and personal calibration that harnesses don't ship with. Same harness; suddenly it remembers who you are, what you're working on, and how you like to work — all while your Obsidian vault stays the durable source of truth underneath.
| # | Layer | Role | What lives here |
|---|---|---|---|
| 01 | OneBrain | OS layer (plugin + CLI) | 24+ skills · lifecycle hooks · vault sync · indexing · checkpoints · harness routing |
| 02 | Harness | Agentic runtime | Bring your own — Claude Code · Gemini CLI · Codex · Qwen · ... |
| 03 | LLM | Intelligence source | Local (mlx, ollama) · cloud (claude, gemini, gpt) · raw API |
| 04 | Obsidian Vault | Source of truth | Plain Markdown — notes, memory, decisions, knowledge graph |
The Harness layer is where most AI tools pick a fight with each other. We don't — pick whichever harness you love. By familiarity, by task, or by cost. Your vault stays the same.