Stop renting your memory

Claude forgets you. Your notes don't.

Stop paying a subscription to teach the same model the same things every week. Move your memory into a vault you own — local, searchable, yours. Ask Claude in plain English; it finds what you wrote and answers from it.

16 slides · ~6 min read Claude Desktop + Ollama + Obsidian macOS · Windows · Linux
What you get

Three pieces, one workflow.

Each piece does one thing. They wire together with MCP — Claude's plugin protocol — so Claude Desktop can read your notes and run local models without any of it leaving your machine.

Obsidian

Your notes. Markdown files in a folder you own. Add color-coded folders and a clean theme via community plugins.

Claude Desktop

The brain interface. Talks to your vault through MCP. Asks the smart questions; you read the smart answers.

Ollama

Local models. Embeds your notes into a vector database so Claude can find them by meaning, not keywords.

The vault

A dialed-in starter folder with `🏠 Welcome`, `Tools/`, `Projects/`, and the conventions Claude reads.

Two ways in

One-click installer, or do it yourself.

Both end at the same place. Pick the one that matches how you like to learn.

Path A · Step 01

Pick your platform.

The installer ships as one file per OS. Click your platform — the next slide will show the right download.

Linux note
Claude Desktop has no official Linux build yet. The Linux installer still wires everything for Claude Code (CLI), which reads the same MCP config.
Path A · Step 02

Download. Double-click.

Grab the installer file from the GitHub repo. It expects to live next to the vault-template/ folder.

macOS
curl -L -O https://raw.githubusercontent.com/Coherence-Daddy/use-ollama-to-enhance-claude/main/install.command
chmod +x install.command
open install.command
Gatekeeper
First run: right-click the file → Open → confirm in the dialog. After that, double-click works.
Windows · PowerShell
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/Coherence-Daddy/use-ollama-to-enhance-claude/main/install.bat" -OutFile install.bat
.\install.bat
Heads up
install.bat is a tiny launcher; the work happens in install.ps1 (also in the repo).
Linux
curl -L -O https://raw.githubusercontent.com/Coherence-Daddy/use-ollama-to-enhance-claude/main/install.sh
chmod +x install.sh
./install.sh

A terminal window will open with a coral banner and step-by-step progress. Total time: 3–8 minutes (most of it pulling the local models).

Terminal — install.command
━━━ Step 1 · Checking dependencies ━━━ Homebrew is installed Claude Desktop is installed Obsidian is installed Ollama is installed ━━━ Step 2 · Starting Ollama and pulling models ━━━ Ollama is running Pulling model 'llama3.1' (this can take a few minutes)… Model 'nomic-embed-text' already pulled ━━━ Step 3 · Creating your vault ━━━ ? Where should your Brain vault live? [~/Documents/Obsidian Vault/Brain] Vault created at /Users/you/Documents/Obsidian Vault/Brain
Path A · Step 03

What the installer does (so you trust it).

  1. Checks dependencies. Installs Homebrew (mac) / uses winget (Windows) / detects apt-dnf-pacman (Linux). Adds Claude Desktop, Obsidian, and Ollama if missing.
  2. Pulls local models. llama3.1 for chat, nomic-embed-text for embeddings. ~5 GB combined; cached after this.
  3. Asks where to put the vault. Defaults to ~/Documents/Obsidian Vault/Brain/. Confirms before overwriting.
  4. Copies the vault template. 🏠 Welcome.md, Tools/, Projects/, _Claude_Ollama_Human/, plus pre-configured plugins and the coral-dark CSS snippet.
  5. Wires Claude Desktop. Writes claude_desktop_config.json with the MCP filesystem server pointed at your vault. Backs up any existing config first.
  6. Opens Obsidian and Claude Desktop. Both apps launch on the new vault. Done.
Safe to re-run
The installer is idempotent. Re-running asks before overwriting the vault and always backs up your Claude config.
Path A · Step 04

First open: try it in 30 seconds.

  1. Obsidian opens on your new vault.You'll land on 🏠 Welcome.
  2. Click into Tools/🔍 Ask Brain.Follow the one-line instruction at the top.
  3. Switch to Claude Desktop.Ask: "What's in my Brain vault?"
  4. Watch Claude list your folders and files.If it does, MCP is wired correctly. You're done with Path A — skip to slide 14.
If Claude says it can't see the vault
Quit Claude Desktop fully (Cmd+Q / Ctrl+Q), then reopen. MCP servers only load on cold start.
Obsidian — Brain
🏠 Welcome.md
📁 Projects
Ollama Engine
Sample Project
📁 Tools
🔍 Ask Brain.md
📂 Import Project.md
📥 Intake Project.md
🔄 Sync Brain.md
📁 _Claude_Ollama_Human

Welcome

This vault gives Obsidian a memory and lets Claude search it for you in plain English.

Write notes the way you always have. Ask Claude later — it actually finds the right ones and answers from them.

→ Open Tools/🔍 Ask Brain to try it.

Path B · Step 01

Install three apps.

If you already have one or two of these, skip those.

Claude Desktop

Native client that supports MCP servers.

claude.ai/download

Obsidian

Your notes editor. Free for personal use.

obsidian.md/download

Ollama

Runs local models. Tiny installer.

ollama.com

Optional · Claude Code

CLI that reads the same MCP config — useful if you want terminal access too.

npm i -g @anthropic-ai/claude-code
Path B · Step 02

Pick your model strategy — Cloud (recommended) or Local.

Same Ollama tooling, two ways to run the actual brains. Ollama Cloud runs much higher-quality models on Ollama's hardware (free tier — Gemma, GLM, Kimi, Qwen3-Coder). Local keeps everything on your laptop. Most people should start with Cloud and only flip to Local if total privacy matters more than answer quality.

☁️ Ollama Cloud (recommended) 🔒 Local
Models gemma4:31b-cloud, glm-5.1:cloud, kimi-k2.6:cloud, qwen3-coder-next llama3.1 (chat), nomic-embed-text (embeddings)
Quality Frontier-tier — these punch alongside GPT-4-class models Solid for everyday lookup; weaker on hard reasoning
Cost Free tier on a personal Ollama account Free; uses your CPU/GPU
Privacy Notes summaries leave for inference; Ollama logs minimal Nothing leaves your machine. Air-gap-grade.
Disk + RAM ~0 (models live in the cloud) ~5 GB download, 8 GB RAM at runtime
Cloud setup (recommended)
Sign up at ollama.com · generate a free API key · then pull all four cloud models so the picker can offer them:
ollama pull gemma4:31b-cloud
ollama pull glm-5.1:cloud
ollama pull kimi-k2.6:cloud
ollama pull qwen3-coder-next
See the companion tutorial → Save 90% on Claude Code with Ollama Cloud for the full router setup.
Local setup (privacy fallback)
ollama pull llama3.1            # chat / reasoning (~4.7 GB)
ollama pull nomic-embed-text    # embeddings (~274 MB)
Pick this if you want total privacy, work offline, or have a beefy machine you'd rather use than a free cloud tier.

Verify either path with ollama list. The 🤖 Models button in your vault flips between them on the fly — no reinstall needed.

Path B · Step 03

Create the vault structure.

A clean starter shape that scales. Every folder has one job.

📁 Brain/ 🏠 Welcome.md # start here 📁 Projects/ # one folder per project (the brain holds the *map*, not the code) 📁 Tools/ # actions Claude can take 🔍 Ask Brain.md 📂 Import Project.md 📥 Intake Project.md 🔄 Sync Brain.md 📋 Open Dashboard.md 🤖 Models.md 📁 _Claude_Ollama_Human/ # conventions Claude reads (sinks to bottom of file list)
Shortcut
The repo includes a vault-template/ directory with this exact shape pre-built. Copy it to ~/Documents/Obsidian Vault/Brain/ and open it as a vault.
Path B · Step 04

Install community plugins.

Settings → Community plugins → Browse. Search and install each:

File Color
Right-click a folder → set a color. Coral / blue / purple at a glance.
Iconize
Per-folder icons from Lucide. Reads better than emoji prefixes.
Iconic
Modern icon system; pairs with Iconize for full coverage.
Hider
Hides UI chrome you don't need (status bar, scrollbars).
Style Settings
Exposes CSS knobs for themes and the coral-dark snippet.
Minimal Theme
Clean lightweight base. Settings → Appearance → Themes.
Dataview
Live tables of recent notes on the Welcome page.
Excalidraw
Whiteboard sketches alongside Mermaid diagrams.
Quit Obsidian fully before editing plugin configs
If Obsidian is running and you edit .obsidian/plugins/*/data.json by hand, it'll overwrite your changes on close. Cmd-Q first.
Path B · Step 05

Wire Claude Desktop to your vault.

Edit claude_desktop_config.json — Claude looks for it in a per-OS location.

macOS path
~/Library/Application Support/Claude/claude_desktop_config.json
Windows path
%APPDATA%\Claude\claude_desktop_config.json
Linux path
~/.config/Claude/claude_desktop_config.json
contents
{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/absolute/path/to/your/Brain"
      ]
    }
  }
}
One MCP server, two superpowers
The filesystem server lets Claude read AND write inside the vault path you give it. Ollama is reached via its local HTTP API at localhost:11434 — no MCP entry needed unless you want Claude to call models directly.
Path B · Step 06

Restart and verify.

  1. Quit Claude Desktop fully.Cmd+Q on mac, Alt+F4 on Windows. MCP servers only load at cold start.
  2. Reopen Claude Desktop.Watch the bottom-right for an MCP indicator (a small plug icon when servers connect).
  3. Ask: "What's in my Brain vault?"Claude should list the top-level folders.
  4. Ask: "Read 🏠 Welcome.md and summarize it."If you get a real summary, MCP filesystem is wired.
If Claude can't see anything
Most common cause: invalid JSON in claude_desktop_config.json. Paste it into jsonlint.com to catch a stray comma. Also check the path is absolute and exists.
Claude Desktop — connected to Brain
You
What's in my Brain vault?
Claude
Your vault has three top-level areas:
· Projects/ — your active projects (3 folders)
· Tools/ — the action notes I can run (Ask, Import, Intake, Sync, Dashboard, Models)
· _Claude_Ollama_Human/ — the conventions I read to behave consistently
There's also a 🏠 Welcome.md at the root that points new users to Ask Brain. filesystem
You
Read 🏠 Welcome.md and summarize it.
Claude
It's a single-page intro: "This vault gives Obsidian a memory and lets Claude search it for you in plain English." It lists three prerequisites, gives a 30-second "try it now" path through Ask Brain, and explains what the vault is not — not a code store, not cloud-based. Under the hood it shows the MCP wiring between Claude, Ollama, and Qdrant. 🏠 Welcome.md
Use it

The daily loop.

Don't change how you write notes. The brain works better the more you use Obsidian normally.

  1. Capture.New note in Obsidian. Frontmatter is optional. Don't pre-organize.
  2. Sync.Run /sync from Tools (or let it auto-run periodically). This re-embeds new notes into the local Qdrant vector store.
  3. Ask.Open Claude Desktop. Ask in plain English. "What did I figure out about the auth migration?" Claude searches by meaning, not keywords.
  4. Refine.Claude's answer cites the notes it pulled from. Click through, edit, re-sync.
Use it

Importing a project: source stays where it lives.

When you import a repo, the brain reads it and writes a summary. Code never moves into Obsidian.

What gets written

  • Projects/<name>/README.md — purpose, owners, status
  • .brain.yml — paths, services, models
  • architecture.mmd.md — Mermaid map
  • decisions.md — running log

What never gets written

  • Source code
  • Build artifacts, node_modules
  • Secrets, .env
  • Large binaries
Why this matters
The vault stays small and searchable. Qdrant embeds the meaningful parts. When Claude needs deeper code detail, the source_path in .brain.yml tells it where to read from.
Power-user · Step 01

Lite vs. Full — pick how deep you want to go.

Steps 1–14 give you the Lite brain: Claude Desktop reads your vault as plain files. Good for most people. If you want a real semantic brain — searches by meaning, callable from Claude Code with one keystroke, with one-click sidebar buttons in Obsidian — say "yes" at Step 5 of the installer.

Lite Full
Search Filename + content (filesystem MCP) Semantic — BGE-M3 + Qdrant vector DB
Ergonomics Type into Claude Desktop 8 sidebar buttons + 7 slash commands + auto-recall MCP
Extra deps None Docker + Python venv (installer handles it)
Time to add later Re-run the installer; pick "yes" at Step 5
Power-user · Step 02

What Full adds — eight buttons, seven commands, one MCP.

The Full installer drops a ~/local-brain/ folder containing every piece of the system. None of it leaves your machine.

  • 📋 Open Dashboard · 🔍 Ask Brain · 🔄 Sync Brain — the everyday loop.
  • 📥 Intake · 📂 Import — start a new project, or teach the brain about an existing folder. Both ask which vault to write into.
  • 🤖 Models — toggle between Anthropic (Claude) and Ollama for the engine the buttons use.
  • 📐 View Mermaid · 🎨 View Excalidraw — open any project's infrastructure.md as a clean schematic, or convert it to a hand-editable Excalidraw canvas.
  • Slash commands/ask, /sync, /intake, /import, /dashboard, /status, /diagram drop into ~/.claude/commands/ automatically.
  • FastMCP serverlocal-brain registers with Claude Code so any session can call brain_search, brain_status, brain_list_projects on its own. Claude reaches for the brain when it would help; you don't have to ask.

Plain-English flowcharts of every button live at walkthroughs/index.html in the repo.

All set

Your brain is live.

Write whatever. Ask Claude later. Watch it find things you forgot you wrote. Everything stays on your machine.