OpenHands: Code Less, Make More

OpenHands (formerly OpenDevin) is a platform for software development agents powered by AI.

OpenHands agents can do anything a human developer can: modify code, run commands, browse the web, call APIs, and yes—even copy code snippets from StackOverflow.

Quick Start

The easiest way to run OpenHands is in Docker. See the Installation guide for system requirements and more information.

docker pull docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik

docker run -it --rm --pull=always \
    -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.19-nikolaik \
    -e LOG_ALL_EVENTS=true \
    -v /var/run/docker.sock:/var/run/docker.sock \
    -v ~/.openhands-state:/.openhands-state \
    -p 3000:3000 \
    --add-host host.docker.internal:host-gateway \
    --name openhands-app \
    docker.all-hands.dev/all-hands-ai/openhands:0.19

You'll find OpenHands running at http://localhost:3000!

Finally, you'll need a model provider and API key. Anthropic's Claude 3.5 Sonnet (anthropic/claude-3-5-sonnet-20241022) works best, but you have many options.

You can also connect OpenHands to your local filesystem, run OpenHands in a scriptable headless mode, interact with it via a friendly CLI, or run it on tagged issues with a github action.

Visit Installation for more information and setup instructions.

Hello World​

The first thing you might want to try is a simple "hello world" example. This can be more complicated than it sounds!

Try prompting the agent with:

Please write a bash script hello.sh that prints "hello world!"

You should see that the agent not only writes the script, it sets the correct permissions and runs the script to check the output.

You can continue prompting the agent to refine your code. This is a great way to work with agents. Start simple, and iterate.

Please modify hello.sh so that it accepts a name as the first argument, but defaults to "world"

You can also work in any language you need, though the agent might need to spend some time setting up its environment!

Please convert hello.sh to a Ruby script, and run it

Building From Scratch​

Agents do exceptionally well at "greenfield" tasks (tasks where they don't need any context about an existing codebase) and they can just start from scratch.

It's best to start with a simple task, and then iterate on it. It's also best to be as specific as possible about what you want, what the tech stack should be, etc.

For example, we might build a TODO app:

Please build a basic TODO list app in React. It should be frontend-only, and all state should be kept in localStorage.

We can keep iterating on the app once the skeleton is there:

Please allow adding an optional due date to every task.

Just like with normal development, it's good to commit and push your code frequently. This way you can always revert back to an old state if the agent goes off track. You can ask the agent to commit and push for you:

Please commit the changes and push them to a new branch called "feature/due-dates"

Adding New Code​

OpenHands can also do a great job adding new code to an existing code base.

For example, you can ask OpenHands to add a new GitHub action to your project which lints your code. OpenHands may take a peek at your codebase to see what language it should use and then drop a new file into ./github/workflows/lint.yml.

Please add a GitHub action that lints the code in this repository.

Some tasks might require a bit more context. While OpenHands can use ls and grep to search through your codebase, providing context up front allows it to move faster, and more accurately. And it'll cost you fewer tokens!

Please modify ./backend/api/routes.js to add a new route that returns a list of all tasks.

Please add a new React component that displays a list of Widgets to the ./frontend/components directory. It should use the existing Widget component.

Refactoring​

OpenHands does great at refactoring existing code, especially in small chunks. You probably don't want to try rearchitecting your whole codebase, but breaking up long files and functions, renaming variables, etc. tend to work very well.

Please rename all the single-letter variables in ./app.go.

Please break the function build_and_deploy_widgets into two functions, build_widgets and deploy_widgets in widget.php.

Please break ./api/routes.js into separate files for each route.

Bug Fixes​

OpenHands can also help you track down and fix bugs in your code. But as any developer knows, bug fixing can be extremely tricky, and often OpenHands will need more context. It helps if you've diagnosed the bug, but want OpenHands to figure out the logic.

Currently the email field in the /subscribe endpoint is rejecting .io domains. Please fix this.

The search_widgets function in ./app.py is doing a case-sensitive search. Please make it case-insensitive.

It often helps to do test-driven development when bug fixing with an agent. You can ask the agent to write a new test, and then iterate until it fixes the bug:

The hello function crashes on the empty string. Please write a test that reproduces this bug, then fix the code so it passes.

More​

OpenHands is capable of helping out on just about any coding task but it takes some practice to get the most out of it. Remember to:

• Keep your tasks small.
• Be as specific as possible.
• Provide as much context as possible.
• Commit and push frequently.

See Prompting Best Practices for more tips on how to get the most out of OpenHands.