Quick Start Guide

The lightweight desktop client connects to privacy first server infrastructure. Think ChatGPT desktop, but with no restrictions and automatic privacy protection. Once you have access, setup is quick. Advanced users can also self host for complete offline operation.

What You're Getting

  • Lightweight Client: Compact desktop application (~250MB installer)
  • No Restrictions: No content filters, no usage limits, no censorship
  • Automatic Privacy: Zero-retention servers never log or store request data, network routing information is ephemeral
  • Anonymous by Design: We can't see your conversations - technically impossible

Installation Steps

Step 1: Get the client

The NL 1.0 desktop client is in private testing with a curated group of companies and early users. Installers are not publicly available yet. contact hello@nolimit.foundation if you would like to learn about access.

The steps below apply once you receive a build.

Step 2: Run the Installer

• Double-click the downloaded file
• Follow the installation wizard
• Choose installation directory (requires only 500MB space)
• Installer configures everything automatically

Step 3: Launch NL 1.0

• Open NL 1.0 from your applications menu
• Sign in with your account (or create one)
• You'll see a clean chat interface, similar to ChatGPT
• Start conversing immediately - all requests are automatically anonymized

Step 4: Verify Installation

# Open terminal/command prompt and run:
nolimit --version
# Output: NL 1.0.0 - Privacy-First AI System

First Conversation

Simply open the application and start chatting. Your requests are processed on infrastructure configured for no retention of conversation content.

You:

Write a Python function to calculate fibonacci numbers

NL 1.0:

def fibonacci(n):
if n <= 1:
return n
return fibonacci(n-1) + fibonacci(n-2)

What Makes NL Different

  • Zero Data Retention: Our servers process requests in RAM only and never log or store request data or network routing information
  • No Content Restrictions: Ask anything without fear of censorship or moderation
  • Anonymous Processing: Network routing data is never logged or stored. Inference servers only see anonymous session tokens
  • Unlimited Usage: No rate limits, no subscription tiers, no token counting