Show HN: Container Use for Agents

Summary

container-use Containerized environments for coding agents. (📦🤖) (📦🤖) (📦🤖) Container Use lets each of your coding agents have their own containerized environment. Go from babysitting one agent at a time to enabling multiple agents to work safely and independently with your preferred stack. It's an open-source MCP server that works as a CLI tool with Claude Code, Cursor, and other MCP-compatible agents. 📦 Isolated Environments : Each agent gets a fresh container in its own git branch - run multiple agents without conflicts, experiment safely, discard failures instantly. : 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. : 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. : 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. : Standard git workflow - just to review any agent's work. 🌎 Universal Compatibility: Works with any agent, model, or infrastructure - no vendor lock-in. 🦺 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. Installing make This will build the cu binary but NOT install it to your $PATH . If you want to build and install the binary into your $PATH , run: make install && hash -r The make install command will put cu in your $PATH . In order to use it, you will need to restart your terminal or run hash -r to refresh your $PATH (or equivalent for your shell). Agent Integration Enabling container-use requires 2 s...