Repository files navigation

🐾 Catnip

Run Claude Code Everywhere

Catnip helps you stay organized, run many agents in parallel, and operate agents remotely with our web and native mobile interfaces.

Catnip is a web service that automates git worktree creation and runs in a container. You can run Catnip in the cloud using GitHub Codespaces or locally on your machine.

The Problem: You want to keep Claude Code running as long as possible.

• Claude Code works best when it's sandboxed and has all the tools it needs to test or debug your code.
• It's difficult to keep track of multiple claude sessions and manage git worktrees.
• You want to be able to review changes / keep claude working when you're on the go from your phone

The Solution: Catnip runs in a container, manages worktrees for you, and exposes API's and UI's to interact with it:

• 🔒 Isolated Sandbox: All code runs containerized environment using either Docker or Apple's newContainer SDK. We can use--dangerously-skip-permissions without fear!
• 🧑‍💻 Worktree Management: Worktree's let you spawn multiple agents in parallel. Catnip keeps everything organized.
• 📱 Mobile Interface: Catnip has a native mobile interface. You can even interact with the Claude Code terminal interface on your phone!
• 💻 Full Terminal Access: The Claude Code terminal interface is 🔥. Open multiple terminals via the web interface, CLI, or directly via SSH.
• 👀 Preview Changes: Catnip has a built in proxy and port detection in the container. Start a web service and preview it live locally!
• 🌐 Universal Access: Still a big fan of Cursor or VS Code? No problem, full remote development directly in your IDE is supported.

Our iOS native interface is currently in beta. You can join theTestFlight group to try the app today. The app will help you configure an existing GitHub repository with catnip as described below. Once setup you can fire up claude code on the go! Please share any bug reports or feedback.

You can add Catnip to a.devcontainer/devcontainer.json in an existing GitHub repository. This gives you complete control over the environment that claude operates in. If you don't have a devcontainer config, add the following to your repo's github url:/new/main?dev_container_template=1&filename=.devcontainer%2Fdevcontainer.json to create one. Just add the catnip feature and ensure the port is forwarded:

{..."features": {"ghcr.io/wandb/catnip/feature:1": {}  },"forwardPorts": [6369],...}

Once your codespace is loaded, look for the cat logo in left sidebar. That will allow you to open the catnip interface in a new tab. You can also use catnip from a mobile device! Gotocatnip.run and login to your github account. We will automatically start your codespace if needed and then redirect you to the catnip mobile interface. Finally you can vibe code on the go!

You can also run catnip locally:

curl -sSfL install.catnip.sh| sh# Optionally start catnip from an existing git repocd~/Development/my_awesome_projectcatnip run# Open http://localhost:6369 🎉

catnip is a golang binary with a vite SPA embedded in it. Thewandb/catnip container was inspired by theopenai/codex-universal container. Callingcatnip run starts the universal container with catnip pre-installed.

It comes pre-configured with node, python, golang, gcc, and rust. You can have the container install a different version of the language on boot by setting any of these environment variables:

# Set specific language versions for AI developmentCATNIP_NODE_VERSION=20.11.0CATNIP_PYTHON_VERSION=3.12CATNIP_RUST_VERSION=1.75.0CATNIP_GO_VERSION=1.22

Catnip currently looks for a file namedsetup.sh in the root of your repo and runs it when a workspace is created. This is a great place to runpnpm install,pip install -r requirements.txt, oruv sync - perfect for AI projects with complex dependencies.

#!/bin/bashpip install -r requirements.txtpip install openai anthropic chromadbnpm install# Assuming --dind passed locally, or the docker-in-docker feature was addeddocker-compose up -d --build

catnip run accepts-e arguments. For instance if you want to passANTHROPIC_API_KEY from your host into the container you can simply add-e ANTHROPIC_API_KEY and then all terminals and AI agent sessions within the container will see that variable. You can also explicitly set variables,-e ANTHROPIC_BASE_URL=https://some.otherprovider.com/v1

catnip run -e ANTHROPIC_API_KEY -e OPENAI_API_KEY -e PINECONE_API_KEY

Thecatnip run command configures SSH within the container by default. It creates a key pair namedcatnip_remote and configures acatnip host allowing you to runssh catnip or open a remote development environment via theRemote-SSH extension. This works perfectly with Cursor, VS Code, and other editors that support remote development. You can disable ssh by adding--disable-ssh to the run command.

If you want the catnip container to be able to rundocker commands, pass the--dind flag to thecatnip run command. This mounts the docker socket from the host into the container allowing your terminals and AI agents to build or run containers - useful for containerized ML services or complex multi-service applications. If you're running in GitHub codespaces make sure you've

If you runcatnip from within a git repo, we mount the repo into the container and create a default workspace. When you start a Claude session in Catnip the system automatically commits changes as Claude makes them.

We also run a git server in the container. You will see a Git option in the "Open in..." menu that will provide you with a clone command like:

git clone -o catnip http://localhost:6369/my-sick-repo.git

As you create new workspaces in the container, you can rungit fetch catnip back on your host to see your changes outside of the container!

Catnip forwards ports directly to the host system. When a service starts within the container, Catnip automatically detects and forwards the port, making it accessible athttp://localhost:$PORT. Each workspace also has thePORT environment variable set to a known free port. For convenience, services can also be accessed through the Catnip UI proxy athttp://localhost:6369/$PORT.

This is especially powerful for LLM and agentic application development where you might have:

• FastAPI backends with LLM integration on port 8000
• React/Next.js chat interfaces on port 3000
• Streamlit data exploration dashboards on port 8501
• Jupyter notebooks for experimentation on port 8888
• Vector databases and other services on various ports

• 🎯 Native devcontainer support
• 📱 Mobile UI
• 🤖 Support for more AI coding agents
• 🌐 Other cloud native environment

We welcome contributions! Catnip is designed to make agentic programming more powerful and accessible for AI engineers.

1. 🍴 Fork the repository
2. 🌿 Run catnip in dev modecatnip run --dev (you must run this from within the catnip repo)
3. 💻 Make your changes
4. ✅ Add tests if applicable
5. 📤 Submit a pull request

The codebase includes both a Go backend for container orchestration and Git operations, plus a React/TypeScript frontend for the web interface. Contributing to AI agent integration, multi-workspace management, or real-time features are all great ways to help improve the platform for AI development workflows.

This project is licensed under the Apache 2.0 - see theLICENSE file for details.