Using Claude Code Remote Control

Claude · Beginner ·🧠 Large Language Models ·3mo ago

Key Takeaways

The video demonstrates how to use Claude Code remote control to access Cloud Code sessions on the go, allowing users to pick up where they left off from any device. It covers setting up remote control, connecting to sessions, and using features like spawn mode.

Full Transcript

How often do you start a Cloud Code session at your desk, leave, and [music] a few hours later think, "I wish I could continue that session from literally anywhere?" [music] Well, good news. With remote control, you can connect Cloud Code web or the [music] Cloud app on your mobile device to a Cloud Code session running on your machine and pick up where you left off. The bad news is that your family will be concerned who you're texting so much. So, here's how it works. Navigate to your project directory and run Cloud remote control. This will start a new session and show you a URL that you can connect to with Cloud Code web. And if you hit the space bar, you'll get a QR code that you can scan with your phone. And from there, it will take you to your mobile browser or the Cloud mobile app, and you can see your session in progress. If you're already in a Cloud Code session and want to hand off to your remote devices, then type {slash} remote control and you'll see the URL there. Now, the URL will be provided for convenience, but realize that since Cloud Code is tied to your Cloud account, you can just go on your mobile device without explicitly clicking the link provided. Once you have everything set up and are connected, you get the same Cloud Code experience that you're used to. You have access to the same tools, MCP servers, configurations, and file system. Everything is still running on your machine. Nothing is moved to the cloud. The conversation then stays in sync across devices. If you type in your Cloud mobile app, you can then see it update in your terminal in real time. By default, we ask you to specify when you want a remote control session each time. However, in your {slash} config, you can enable remote control for all sessions, so you don't have to explicitly enable it each time. Cloud remote control also comes with a spawn mode that you can use to create new sessions remotely. As of this video, it's available to Max, Team, and Enterprise users. Type in Cloud remote control, then go on Cloud web or mobile. Then you can select your remote session by tapping the environment button and selecting your device. And there you can spawn multiple instances of Cloud Code. >> [music] >> If you want to pick up a session that you started on your desk, well, remote control can make that happen. We're currently rolling out to Pro and Max plan users.

Original Description

Learn more about using Claude Code remote control to access Claude Code sessions on the go.
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Learn how to use Cloud Code remote control to access your code sessions from anywhere, and discover features like spawn mode for creating new sessions remotely. This allows for seamless continuation of work across devices. The video covers setup, connection, and usage of remote control.

Key Takeaways
  1. Navigate to your project directory and run Cloud remote control
  2. Start a new session and connect to it with Cloud Code web or the Cloud app
  3. Use the QR code or URL to connect to the session from your mobile device
  4. Type {slash} remote control to hand off a session to your remote devices
  5. Configure remote control settings in your {slash} config
  6. Use spawn mode to create new sessions remotely
💡 Cloud Code remote control allows you to access your code sessions from any device, without moving your code to the cloud, and keeps your conversation in sync across devices.

Related AI Lessons

Embeddings Simplified
Learn the basics of embeddings and how they simplify complex data, a crucial concept in AI and ML
Medium · RAG
Building LSTMs with PyTorch and Lightning AI Part 7: Resuming Training with Checkpoints
Learn to resume LSTM training with checkpoints using PyTorch and Lightning AI, enabling efficient model iteration and development
Dev.to · Rijul Rajesh
How AI Learns with Less Labeled Data
Learn how AI can learn with less labeled data, a crucial aspect of machine learning beyond model selection
Medium · AI
Comparing Sarvam-30B and Qwen2.5–14B on Spider Text-to-SQL: An Active-Parameter Perspective
Learn how to compare large language models like Sarvam-30B and Qwen2.5-14B on the Spider Text-to-SQL benchmark from an active-parameter perspective
Medium · LLM
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →