Sceni Code

AI-powered command-line workflow tool for developers. Without telemetry.

Installation • Quick Start • Features • Documentation • Contributing

Sceni Code is a fork of Qwen code, which in turn is a fork of Gemini used within our company

Key Differences

• No telemetry - We manually review all upstream code for telemetry and strip it out
• Less flexibility - We stripped all authentication and model integrations which we do not use. Only Open AI compatible remains
• No token limit - Upstream warns at 32K tokens. This fork doesn't

Installation

Prerequisites

Ensure you have Node.js version 20 or higher installed.

curl -qL https://www.npmjs.com/install.sh | sh

Install from npm

npm install -g @scenius/sceni-code@latest
sceni --version

Install from source

git clone https://github.com/scenius-software/sceni-code.git
cd sceni-code
npm install
npm install -g .

Run with Docker

Mount both the current directory and user srettings:

Unix/Linux/macOS:

docker run -it \
  -v "$(pwd):/workspace" \
  -v "$HOME/.sceni:/home/node/.sceni" \
  nickheskes/sceni-code

PowerShell (Windows):

docker run -it `
  -v "${PWD}:/workspace" `
  -v "$env:USERPROFILE\.sceni:/home/node/.sceni" `
  nickheskes/sceni-code

Quick Start

# Start Sceni Code
sceni

# Example commands
> Explain this codebase structure
> Help me refactor this function
> Generate unit tests for this module

Session Management

Session Commands

• /compress - Compress conversation history
• /clear - Clear all conversation history and start fresh
• /status - Check current token usage

Commands & Shortcuts

Session Commands

• /help - Display available commands
• /clear - Clear conversation history
• /compress - Compress history to save tokens
• /status - Show current session information
• /exit or /quit - Exit Sceni Code

Keyboard Shortcuts

• Ctrl+C - Cancel current operation
• Ctrl+D - Exit (on empty line)
• Up/Down - Navigate command history

Troubleshooting

If you encounter issues, check the troubleshooting guide.

Acknowledgments

This project is based on Qwen. Our hero's for LLM development and tooling. Which is based on, This project is based on Google Gemini CLI. We acknowledge and appreciate the excellent work of the Gemini CLI team. Our main contribution focuses on parser-level adaptations to better support Qwen-Coder models.

License

LICENSE