obsidian-second-brain

<p align="center"> <a href="https://github.com/eugeniughelbur/obsidian-second-brain"> <img src="media/banner.png" alt="obsidian-second-brain: one brain, eight platforms, 47 commands. A cross-platform skill for Obsidian that runs on Claude Code, Codex, Gemini, OpenCode, Antigravity, Hermes, Pi, and Grok Bot." width="100%" /> </a> </p> <p align="center"> <a href="#install"><img src="https://img.shields.io/badge/Claude_Code-D97757?style=for-the-badge&logo=anthropic&logoColor=white" alt="Claude Code" /></a> <a href="#grok-bot"><img src="https://img.shields.io/badge/Grok_Bot-000000?style=for-the-badge&logo=x&logoColor=white" alt="Grok Bot" /></a> <a href="#codex-cli--gemini-cli--opencode"><img src="https://img.shields.io/badge/Codex_CLI-412991?style=for-the-badge&logo=openai&logoColor=white" alt="Codex CLI" /></a> <a href="#codex-cli--gemini-cli--opencode"><img src="https://img.shields.io/badge/Gemini_CLI-4285F4?style=for-the-badge&logo=googlegemini&logoColor=white" alt="Gemini CLI" /></a> <a href="#codex-cli--gemini-cli--opencode"><img src="https://img.shields.io/badge/OpenCode-181818?style=for-the-badge&logo=opensourceinitiative&logoColor=white" alt="OpenCode" /></a> </p> <p align="center"> <strong>Your vault is the memory. Claude, Grok Bot, Codex - same brain.</strong> <br /> <em>Your vault outlives whichever CLI you switch to.</em> </p> <p align="center"> <img src="https://img.shields.io/badge/Obsidian-Vault-7C3AED?style=for-the-badge&logo=obsidian&logoColor=white" alt="Obsidian Vault" /> <img src="https://img.shields.io/github/v/release/eugeniughelbur/obsidian-second-brain?style=for-the-badge&color=green" alt="Release" /> <img src="https://img.shields.io/badge/license-MIT-blue?style=for-the-badge" alt="License: MIT" /> <img src="https://img.shields.io/github/stars/eugeniughelbur/obsidian-second-brain?style=for-the-badge&color=yellow" alt="Stars" /> <a href="https://github.com/sponsors/eugeniughelbur"><img src="https://img.shields.io/badge/Sponsor-EA4AAA?style=for-the-badge&logo=github-sponsors&logoColor=white" alt="Sponsor" /></a> </p> <h1 align="center">obsidian-second-brain: AI second brain for Obsidian - persistent memory for Claude Code and Grok Bot</h1> <p align="center"> <strong>An evolution of <a href="https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f">Karpathy's LLM Wiki pattern</a>: a vault that rewrites itself.</strong> <br /><br /> <em>Every source updates existing pages instead of just appending new ones. Contradictions reconcile automatically. Your vault compounds while you sleep.</em> <br /><br /> <strong>Powered by <a href="references/freshness-policy.md">OKM - Open Knowledge Metabolism</a>:</strong> <em>every stored fact is timeless, dated, or a pointer - so your knowledge base never fills with facts that used to be true.</em> <br /><br /> <strong>Built for</strong> <em>developers &middot; founders and operators &middot; writers &middot; researchers - <a href="#choose-your-preset">pick a preset at setup</a></em> <br /><br /> <strong>Start with three:</strong> <em><code>/obsidian-init</code> to set up, <code>/obsidian-save</code> to capture, <code>/obsidian-find</code> to recall. The other 42 are there when you need them.</em> <br /><br /> <em>auto-synthesis &middot; thinking tools that argue with you</em> <br /><br /> <em>live research from X, the web, and YouTube &middot; 4 scheduled agents &middot; 4 role presets</em> <br /><br /> <em>write-time AI-first validator &middot; <code>/create-command</code> interview flow &middot; multilingual trigger schema</em> <br /><br /> <a href="#install"><strong>Install &rarr;</strong></a> &middot; <a href="DEMOS.md">Demos</a> &middot; <a href="#what-happens-when-you-install-this">See it in action</a> &middot; <a href="#45-commands">All commands</a> &middot; <a href="#choose-your-preset">Presets</a> &middot; <a href="#the-vault-is-alive">OKM</a> &middot; <a href="https://github.com/eugeniughelbur/obsidian-second-brain/discussions">Discussions</a> </p> <p align="center"> <a href="DEMOS.md"> <img src="media/obsidian-save.gif" alt="One /obsidian-save command turns a conversation into five cross-linked AI-first notes: a person, a project with the decision, a task, a board card, and the daily note." width="100%" /> </a> <br /> <em>One <code>/obsidian-save</code> - five cross-linked notes. Real footage, synthetic vault. <a href="DEMOS.md">More demos &rarr;</a></em> <br /><br /> <em>If this looks useful, <a href="https://github.com/eugeniughelbur/obsidian-second-brain">star the repo</a>. It is how other people find it.</em> </p> <p align="center"> <strong>v0.15 - The Port (September 2026):</strong> the plugin now runs on Windows the way it runs on macOS and Linux, fixed end to end by a contributor across two PRs.<br/> <em>Windows paths, CRLF and BOM notes, UTF-8 everywhere, a USERPROFILE-aware config home; plus Gemini-first /podcast with a free Whisper fallback, tag syntax and taxonomy checks, Simplified Chinese triggers, /obsidian-reindex, an Obsidian lint plugin, platform ownership, AI-FIRST.md, a reproducible retrieval benchmark, a generated docs site, typed edges, and the callout preamble. 763-test CI wall.</em> <a href="CHANGELOG.md">See the changelog &rarr;</a> </p>

---

The Problem

You use Claude every day. Every session starts from scratch. You re-explain everything. The conversation ends. Everything disappears. Claude Code has no persistent memory across sessions - and neither does Grok Bot, Codex, Gemini, or any of the others.

You take notes in Obsidian. Hundreds of files. They just sit there. You make the same decision twice because you forgot you made it six months ago. Ideas rot in daily notes. Nobody connects the dots.

Two powerful tools. Completely disconnected. You already have the long-term memory. The thing doing the thinking cannot reach it.

---

How this extends Karpathy's LLM Wiki

Karpathy's pattern is brilliant. Drop sources, LLM creates wiki pages, ask questions. This skill takes it further:

| | Karpathy's LLM Wiki | obsidian-second-brain | |---|---|---| | New sources | Append new pages, cross-reference | Rewrite existing pages. People get updated, claims revised, stale facts replaced. | | Contradictions | Flagged, you resolve manually | /obsidian-reconcile resolves them automatically | | Patterns | Surface when you ask | /obsidian-synthesize finds unnamed patterns and writes synthesis pages on its own | | When it runs | On demand, when you prompt | 4 scheduled agents: morning brief, nightly consolidation, weekly review, vault-health check | | Note format | Human-readable wiki pages | AI-first: ## For future agent preamble + frontmatter for LLM retrieval, not human review |

If Karpathy's wiki is a knowledge base you maintain with an LLM, this is a knowledge base that maintains itself.

---

What Happens When You Install This

After a meeting: /obsidian-save Claude pulls out every decision, person, task, and idea and saves each one to the right note. You do nothing.

You recorded a voice memo: /obsidian-ingest meeting.m4a Claude transcribes it with a local Whisper install, attributes speakers where the transcript makes them identifiable, extracts every promise and action item, and distributes across entity pages, task boards, and the daily note.

You screenshot a whiteboard: /obsidian-ingest photo.png Claude reads the image, extracts text and structure, creates concept notes, links to related projects. A photo becomes knowledge.

You find a great video: /obsidian-ingest https://youtube.com/... Claude doesn't summarize into one note. It REWRITES your existing pages. People get updated. Contradictions get resolved. Patterns trigger new synthesis pages. One URL in. The vault is smarter.

Before a big decision: /obsidian-challenge Claude searches your vault for past failures and reversed decisions on the same topic. Pushes back with your own words. Your vault holds you accountable.

You want to see the big picture: /obsidian-visualize Claude generates a visual canvas of your entire vault. Hub nodes centered, color-coded by type, orphans highlighted. Open it in Obsidian and see the shape of your knowledge.

You go to sleep: The nightly agent runs 5 phases: closes the day, reconciles contradictions, synthesizes cross-source patterns, heals orphan notes, and rebuilds the index. You wake up to a smarter vault.

You start a new day: /obsidian-daily Claude pulls your calendar events, overdue tasks, and overnight changes into today's note. Your morning starts informed.

Someone shares an X post: /x-read https://x.com/... Grok with live X access fetches the post, the thread, and the replies. Returns verbatim text + TL;DR + key claims + reply sentiment + voices to watch. No more screenshots.

You're planning today's content: /x-pulse "AI automation" Grok scans X for what's trending in your topic right now. Returns 3-5 emerging themes (with rep posts + key voices), gaps nobody is filling, hook formats that are working, and 3 specific post ideas you could write today.

You need real research: /research "AI memory tools" Perplexity Sonar Pro pulls a deep dossier with citations: summary, key facts (every claim with a recency marker and source domain), timeline, key players, contrarian views, recommended further reading, open questions. Saved to your vault, auto-opens in Obsidian.

You want vault-first deep research: /research-deep "AI memory tools" Scans your vault for what you already know. Identifies gaps. Spawns 3-5 targeted searches via Perplexity (web) and Grok (X discourse). Synthesizes a delta report: what's new, what's confirmed, contradictions to resolve, recommended vault updates. Vault baseline doesn't get re-researched. Only gaps get filled.

You hit a great YouTube video: /youtube https://youtu.be/... Free transcript via youtube-transcript-api. Optional metadata + top comments via YouTube Data API v3. Gemini (free tier, Grok fallback) summarizes into TL;DR, Key Points, Notable Quotes (verbatim), Themes, Comment Sentiment, and Worth Following Up On. Saved as an AI-first note in your vault. Add --visual to also watch it: scene-change frame extraction (ffmpeg) that Claude reads with its own vision to capture on-screen text, code, diagrams, and demos the transcript misses.

You never open Obsidian. Everything happens through Claude.

---

Before & After

| | Without this skill | With this skill | |---|---|---| | Saving decisions | Copy-paste or lose them | Auto-saved to the right project note | | Daily notes | Write it yourself, forget half the time | Created automatically | | Finding patterns | Re-read dozens of notes | /obsidian-emerge finds them for you | | Challenging yourself | Nobody pushes back | /obsidian-challenge uses your own history against you | | Session continuity | Re-explain every time | /obsidian-world loads full context in 10 seconds | | Ingesting content | Read it, forget it | /obsidian-ingest rewrites 5-15 vault pages from 1 source (URLs, PDFs, audio, screenshots) | | Contradictions | You don't know they exist | /obsidian-reconcile resolves them automatically | | Synthesis | You connect dots manually | /obsidian-synthesize finds patterns across sources on its own | | Sharing vault data | Only Claude can read it | /obsidian-export gives any AI tool a clean snapshot | | Facts change over time | Old info gets overwritten | Bi-temporal facts track when it was true AND when the vault learned it | | Starting a new session | Re-explain who you are | CRITICAL_FACTS.md loads your identity in ~120 tokens | | Reading an X thread | Open X, scroll, screenshot, paste | /x-read [url] returns post + thread + sentiment + voices | | Knowing what to post | Guess what's trending | /x-pulse scans X and returns hot themes + gaps + hoo