Claude Code Remote Control: Continue Local Sessions from Any Device

Claude Code Remote Control connects claude.ai/code or the Claude mobile apps to a Claude Code session running locally on your machine. You can start a task at your desk and pick it up from your phone or another computer while Claude keeps running locally the entire time—nothing moves to the cloud.
Key Features
With Remote Control you can:
- Use your full local environment remotely: your filesystem, MCP servers, tools, and project configuration all stay available
- Work from both surfaces at once: the conversation stays in sync across all connected devices, so you can send messages from your terminal, browser, and phone interchangeably
- Survive interruptions: if your laptop sleeps or your network drops, the session reconnects automatically when your machine comes back online
Unlike Claude Code on the web, which runs on cloud infrastructure, Remote Control sessions run directly on your machine and interact with your local filesystem. The web and mobile interfaces are just a window into that local session.
Requirements
Before using Remote Control, confirm that your environment meets these conditions:
- Subscription: requires a Pro or Max plan. API keys are not supported. Remote Control is not available on Team or Enterprise plans.
- Authentication: run
claudeand use/loginto sign in through claude.ai if you haven't already - Workspace trust: run
claudein your project directory at least once to accept the workspace trust dialog
Starting a Remote Control Session
You can start a new session directly in Remote Control, or connect a session that's already running.
For a new session, navigate to your project directory and run:
claude remote-controlThe process stays running in your terminal, waiting for remote connections. It displays a session URL you can use to connect from another device, and you can press spacebar to show a QR code for quick access from your phone. While a remote session is active, the terminal shows connection status and tool activity.
This command supports the following flags:
--verbose: show detailed connection and session logs--sandbox/--no-sandbox: enable or disable sandboxing for filesystem and network isolation during the session. Sandboxing is off by default.
If you're already in a Claude Code session and want to continue it remotely, use the /remote-control (or /rc) command:
/remote-controlThis starts a Remote Control session that carries over your current conversation history and displays a session URL and QR code you can use to connect from another device. The --verbose, --sandbox, and --no-sandbox flags are not available with this command.
Use /rename before running /remote-control to give the session a descriptive name. This makes it easier to find in the session list across devices.
Connecting from Another Device
Once a Remote Control session is active, you have a few ways to connect from another device:
- Open the session URL in any browser to go directly to the session on claude.ai/code
- Scan the QR code shown alongside the session URL to open it directly in the Claude app
- Open claude.ai/code or the Claude app and find the session by name in the session list
Remote Control sessions show a computer icon with a green status dot when online. The remote session takes its name from your last message, your /rename value, or "Remote Control session" if there's no conversation history.
If the environment already has an active session, you'll be asked whether to continue it or start a new one.
📖 Read the full source: HN AI Agents
👀 See Also

Chamber: AI Agent for GPU Infrastructure Management
Chamber is an AI agent that manages GPU infrastructure by handling tasks like provisioning clusters, diagnosing failed jobs, and managing workloads. It provides structured operations with validation and rollback, not just raw shell commands.

Replacing complex retrieval pipelines with simple git commands for AI agents
A developer replaced their 3GB Docker image with sentence-transformers, rank-bm25, and scikit-learn with a single tool that lets AI agents execute read-only shell commands like git log, grep, and git diff directly on their memory repository.

Agent MCP Studio: Build Multi-Agent MCP Systems Entirely in a Browser via WASM
Agent MCP Studio lets you design, orchestrate, and export MCP agent systems from a single static HTML file using WebAssembly – no backend, no Docker, no server.

ClaudeMeter: Open-Source macOS Menu Bar App for Real-Time Claude Usage Tracking
ClaudeMeter is a free, open-source macOS menu bar app for Claude Max subscribers that displays session and weekly usage percentages, reset timers, and pace indicators without interrupting workflow. The entire app was built using Claude (Claude Code/Opus) for Swift code, Supabase backend, and Edge Functions.