Skip to content

eliransu/digital-brain

Repository files navigation

digital-brain

License: MIT Claude Code

Claude + Obsidian knowledge companion. A running notetaker that builds and maintains a persistent, compounding wiki vault. Every source you add gets integrated. Every question you ask pulls from everything that has been read. Knowledge compounds like interest.

Based on Andrej Karpathy's LLM Wiki pattern. Markdown only — no build step, no compiled code, no runtime dependencies.

This repo is a derivative of AgriciDaniel/claude-obsidian by Agrici Daniel (AI Marketing Hub), MIT-licensed. The skill engine, vault scaffold, and DragonScale extension all originate from that project. See ATTRIBUTION.md for the full credit list. Go star the upstream first.


What It Does

You drop sources. Claude reads them, extracts entities and concepts, updates cross-references, and files everything into a structured Obsidian vault. The wiki gets richer with every ingest.

You ask questions. Claude reads the hot cache (recent context), scans the index, drills into relevant pages, and synthesizes an answer. It cites specific wiki pages, not training data.

You lint. Claude finds orphans, dead links, stale claims, and missing cross-references. Your wiki stays healthy without manual cleanup.

At the end of every session, Claude updates a hot cache. The next session starts with full recent context, no recap needed.


Why digital-brain?

Most Obsidian AI plugins are chat interfaces — they answer questions about your existing notes. digital-brain is a knowledge engine — it creates, organizes, maintains, and evolves your notes autonomously.

Capability digital-brain
Auto-organize notes Creates entities, concepts, cross-references
Contradiction flagging [!contradiction] callouts with sources
Session memory Hot cache persists between conversations
Vault maintenance 8-category lint (orphans, dead links, gaps)
Autonomous research 3-round web research with gap-filling
Multi-model support Claude, Gemini, Codex, Cursor, Windsurf
Visual canvas Image / PDF / text cards with auto-layout zones
Query with citations Cites specific wiki pages
Batch ingestion Parallel agents for multiple sources
Open source MIT

Quick Start

  1. Move this folder to wherever you want your vault to live. Common choices: ~/brain/, ~/notes/, ~/digital-brain/.

  2. Run the setup script once before opening Obsidian. It writes graph/appearance configs and pulls down the Excalidraw plugin binary.

    bash bin/setup-vault.sh
  3. Open the folder in Obsidian: Manage Vaults → Open folder as vault → select this folder.

  4. Open Claude Code in the same folder. Then in any session:

    /wiki
    

    That bootstraps your vault — walks you through filling in wiki/meta/User.md, edits VOICE.md, and sets the Linear team key in wiki/daily/_config.json.

  5. Read TEMPLATE.md for the placeholder checklist.


Commands

You say Claude does
/wiki Setup check, scaffold, or continue where you left off
ingest [file] Read source, create 8–15 wiki pages, update index and log
ingest all of these Batch process multiple sources, then cross-reference
what do you know about X? Read index → relevant pages → synthesize answer
/save File the current conversation as a wiki note
/save [name] Save with a specific title (skips the naming question)
/autoresearch [topic] Run the autonomous research loop: search, fetch, synthesize, file
/canvas Open or create the visual canvas, list zones and nodes
/canvas add image [path] Add an image to the canvas with auto-layout
/canvas add text [content] Add a markdown text card to the canvas
/canvas add pdf [path] Add a PDF document as a rendered preview node
/canvas add note [page] Pin a wiki page as a linked card on the canvas
/canvas zone [name] Add a new labeled zone to organize visual content
lint the wiki Health check: orphans, dead links, gaps, suggestions
update hot cache Refresh hot.md with latest context summary

Cross-Project Power Move

Point any Claude Code project at this vault. Add to that project's CLAUDE.md:

## Wiki Knowledge Base

Path: ~/path/to/vault

When you need context not already in this project:

1. Read wiki/hot.md first (recent context cache)
2. If not enough, read wiki/index.md
3. If you need domain details, read the relevant domain sub-index
4. Only then drill into specific wiki pages

Do NOT read the wiki for general coding questions or tasks unrelated to [domain].

Your executive assistant, coding projects, and content workflows all draw from the same knowledge base.


Six Wiki Modes

Mode Use when
A: Website Sitemap, content audit, SEO wiki
B: GitHub Codebase map, architecture wiki
C: Business Project wiki, competitive intelligence
D: Personal Second brain, goals, journal synthesis
E: Research Papers, concepts, thesis
F: Book/Course Chapter tracker, course notes

Modes can be combined.


What Gets Created

A typical scaffold creates:

  • Folder structure for your chosen mode
  • wiki/index.md: master catalog
  • wiki/log.md: append-only operation log
  • wiki/hot.md: recent context cache
  • wiki/meta/dashboard.base: Bases dashboard (primary, native Obsidian)
  • _templates/: Obsidian Templater templates for each note type
  • .obsidian/snippets/vault-colors.css: color-coded file explorer
  • Vault CLAUDE.md: auto-loaded project instructions

MCP Setup (Optional)

MCP lets Claude read and write vault notes directly without copy-paste.

Option A (REST API based):

  1. Install the Local REST API plugin in Obsidian

  2. Copy your API key

  3. Run:

    claude mcp add-json obsidian-vault '{
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-obsidian"],
      "env": {
        "OBSIDIAN_API_KEY": "your-key",
        "OBSIDIAN_HOST": "127.0.0.1",
        "OBSIDIAN_PORT": "27124",
        "NODE_TLS_REJECT_UNAUTHORIZED": "0"
      }
    }' --scope user

Option B (filesystem based, no plugin needed):

claude mcp add-json obsidian-vault '{
  "type": "stdio",
  "command": "npx",
  "args": ["-y", "@bitbonsai/mcpvault@latest", "/path/to/your/vault"]
}' --scope user

Plugins

Core Plugins (built into Obsidian)

Plugin Purpose
Bases Powers wiki/meta/dashboard.base: native database views. Available since Obsidian v1.9.10.
Properties Visual frontmatter editor
Backlinks, Outline, Graph view Standard navigation

Pre-installed Community Plugins (ship with this vault)

Enable in Settings → Community Plugins → enable:

Plugin Purpose
Calendar Right-sidebar calendar with word count + task dots
Thino Quick memo capture panel
Excalidraw Freehand drawing canvas, annotate images
Banners Notion-style header image via banner: frontmatter

Excalidraw main.js (8 MB) is downloaded automatically by setup-vault.sh. It is not tracked in git.

Also install from Community Plugins (not pre-installed)

Plugin Purpose
Templater Auto-fills frontmatter from _templates/
Obsidian Git Auto-commits vault every 15 minutes
Dataview (optional) Only needed for the legacy wiki/meta/dashboard.md queries

CSS Snippets (auto-enabled by setup-vault.sh)

Snippet Effect
vault-colors Color-codes wiki/ folders by type in the file explorer
ITS-Dataview-Cards Turns Dataview TABLE queries into visual card grids
ITS-Image-Adjustments Fine-grained image sizing — append |100 to any image embed

File Structure

digital-brain/
├── .claude-plugin/         # plugin + marketplace manifest
├── skills/                 # all skills (wiki, ingest, query, lint, save, autoresearch, canvas, ...)
├── agents/                 # parallel ingestion + lint agents
├── commands/               # slash commands (/wiki, /save, /sync, /sup, /note, /task, /ppl, ...)
├── hooks/                  # SessionStart + Stop hot-cache hooks
├── _templates/             # Obsidian Templater templates
├── wiki/                   # the vault itself (empty in this template)
│   ├── index.md
│   ├── hot.md
│   ├── log.md
│   ├── meta/               # User.md, Voice.md
│   ├── concepts/
│   ├── entities/people/
│   ├── sources/
│   ├── synthesis/
│   ├── notes/
│   ├── domains/
│   └── daily/_config.json
├── .raw/                   # source documents (hidden in Obsidian)
├── .obsidian/              # vault config + CSS snippets
├── WIKI.md                 # full schema reference
├── VOICE.md                # short drafting rules for /write
├── TEMPLATE.md             # what to edit before first use
└── README.md               # this file

AutoResearch: program.md

The /autoresearch command is configurable. Edit skills/autoresearch/references/program.md to control:

  • What sources to prefer (academic, official docs, news)
  • Confidence scoring rules
  • Max rounds and max pages per session
  • Domain-specific constraints

The default program works for general research. Override it for your domain.


Credits

Full details in ATTRIBUTION.md.

License

MIT. See LICENSE. The copyright notice retains Agrici Daniel (AI Marketing Hub) per the upstream license.

About

Claude + Obsidian knowledge companion. A persistent, compounding wiki vault based on Karpathy's LLM Wiki pattern — drop sources, ask questions, knowledge compounds.

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages