Installing

Installation Guide

This guide will walk you through installing Thought Ledger and its dependencies on your local machine.

Step 1: Install Ollama

Ollama is the local AI runtime that powers Thought Ledger. It allows you to run AI models directly on your machine without API keys or cloud dependencies.

macOS Installation

# Download and install Ollama
curl -fsSL https://ollama.com/install.sh | sh

Or download the macOS installer directly.

Linux Installation

# Download and install Ollama
curl -fsSL https://ollama.com/install.sh | sh

For specific Linux distributions:

# Ubuntu/Debian
sudo apt update && sudo apt install -y curl

# Fedora
sudo dnf install -y curl

# Arch Linux
sudo pacman -S curl

Windows Installation

Install via WSL2:

# In WSL2 terminal
curl -fsSL https://ollama.com/install.sh | sh

Verify Ollama Installation

# Check Ollama is running
ollama --version

# Start Ollama service (if needed)
sudo systemctl start ollama

Step 2: Install Node.js

Thought Ledger requires Node.js 18 or higher.

Using Node Version Manager (Recommended)

# Install nvm
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash

# Reload shell
source ~/.bashrc

# Install Node.js
nvm install 18
nvm use 18

Direct Installation

Download from nodejs.org or use your system package manager:

# macOS (Homebrew)
brew install node@18

# Ubuntu/Debian
sudo apt install nodejs npm

# Fedora
sudo dnf install nodejs npm

Verify Node.js Installation

# Check Node.js version
node --version  # Should be v18+

# Check npm version
npm --version

Step 3: Install Thought Ledger

Now install Thought Ledger itself:

# Clone the repository
git clone https://github.com/your-org/thought-ledger.git
cd thought-ledger

# Install dependencies
npm install

# Build the application
npm run build

# Start the development server
npm run dev

Step 4: Download AI Models

Thought Ledger needs local AI models to function. We recommend starting with:

# Download a lightweight model (good for testing)
ollama pull llama3.2:3b

# Download a more capable model (recommended)
ollama pull llama3.2:8b

# Download a coding-focused model (optional)
ollama pull codegemma:7b

Available Models

Model	Size	Use Case	RAM Required
llama3.2:3b	2GB	Basic decisions, testing	4GB+
llama3.8b	5GB	General use, recommended	8GB+
codegemma:7b	5GB	Code-related decisions	8GB+
llama3.1:70b	40GB	Complex decisions	64GB+

Step 5: Configure Thought Ledger

Create your configuration file:

# Copy example configuration
cp config.example.json config.json

# Edit configuration
nano config.json

Example configuration:

{
  "ai": {
    "model": "llama3.2:8b",
    "ollama_url": "http://localhost:11434"
  },
  "memory": {
    "storage_path": "./data/decisions.db",
    "max_decisions": 10000
  },
  "ui": {
    "theme": "auto",
    "language": "en"
  }
}

Step 6: Start Thought Ledger

# Start the application
npm start

# Or run in development mode
npm run dev

Open your browser and navigate to http://localhost:3000 to access Thought Ledger.

Verification

Test your installation:

1. Check Ollama: ollama list should show downloaded models
2. Check Thought Ledger: The web interface should load at localhost:3000
3. Test AI: Try a simple decision in the interface

Next Steps

• Quick Start Guide - Learn the basics
• User Guide - Master decision memory features
• Configuration - Customize your setup

---

Having issues? Check our troubleshooting guide for common problems.