Introduction
Sandboxed dev environments for coding agents.
What is Container Use?
Container Use lets each of your coding agents have their own containerized sandbox environment. Go from babysitting one agent at a time to enabling multiple agents to work safely in parallel with your preferred stack.
Container Use leverages Dagger for containerized workflows and Git worktrees for branching.
Sandboxed Environments
Each agent gets a fresh container in its own git branch - run multiple agents without conflicts, experiment safely, discard failures instantly.
Real-time Visibility
See complete command history and logs of what agents actually did, not just what they claim.
Direct Intervention
Drop into any agent’s terminal to see their state and take control when they get stuck.
Environment Control
Standard git workflow - just git checkout <branch_name> to review any agent’s work.
Why Container Use?
Scale Beyond Single Agent Workflows
Scale Beyond Single Agent Workflows
Most coding agents require constant supervision and can only work on one task at a time. Container Use breaks this limitation by providing isolated environments where multiple agents can work simultaneously without interfering with each other.
Safety and Experimentation
Safety and Experimentation
Agents can experiment freely in their isolated containers with secure access to API keys, database credentials, and other secrets. Secrets are resolved within the container environment - agents can use your credentials without the AI model ever seeing the actual values. If something goes wrong, simply discard the environment and start fresh. No more worrying about agents breaking your local development setup or exposing sensitive data.
Universal Compatibility
Universal Compatibility
Works with any agent, model, or infrastructure - no vendor lock-in. Container Use is an open-source MCP server that integrates with Claude Code, Cursor, VSCode, and other MCP-compatible agents.
Complete Transparency
Complete Transparency
Unlike black-box agent platforms, Container Use gives you full visibility into what your agents are actually doing. Every command, every file change, every process is logged and accessible.
Quick Demo
See video playlist for more examples.
Getting Started
This project is in early development and actively evolving. Expect rough edges, breaking changes, and incomplete documentation. But also expect rapid iteration and responsiveness to feedback.
Quickstart
Install Container Use on your system using Homebrew, shell script, or build from source
Agent Integration
Configure Container Use with your coding agent (Claude Code, Cursor, VSCode, etc.)
Community
Join our community to get help, share examples, and contribute to the project: