Skip to content

Latest commit

 

History

History
 
 

computer-use-demo

README.md

Anthropic Computer Use Demo

Caution

Computer use is a beta feature. Please be aware that computer use poses unique risks that are distinct from standard API features or chat interfaces. These risks are heightened when using computer use to interact with the internet. To minimize risks, consider taking precautions such as:

  1. Use a dedicated virtual machine or container with minimal privileges to prevent direct system attacks or accidents.
  2. Avoid giving the model access to sensitive data, such as account login information, to prevent information theft.
  3. Limit internet access to an allowlist of domains to reduce exposure to malicious content.
  4. Ask a human to confirm decisions that may result in meaningful real-world consequences as well as any tasks requiring affirmative consent, such as accepting cookies, executing financial transactions, or agreeing to terms of service.

In some circumstances, Claude will follow commands found in content even if it conflicts with the user's instructions. For example, instructions on webpages or contained in images may override user instructions or cause Claude to make mistakes. We suggest taking precautions to isolate Claude from sensitive data and actions to avoid risks related to prompt injection.

Finally, please inform end users of relevant risks and obtain their consent prior to enabling computer use in your own products.

This repository helps you get started with computer use on Claude, with reference implementations of:

  • Build files to create a Docker container with all necessary dependencies
  • A computer use agent loop using the Anthropic API, Bedrock, or Vertex to access the updated Claude 3.5 Sonnet model
  • Anthropic-defined computer use tools
  • A streamlit app for interacting with the agent loop

Please use this form to provide feedback on the quality of the model responses, the API itself, or the quality of the documentation - we cannot wait to hear from you!

Important

The Beta API used in this reference implementation is subject to change. Please refer to the API release notes for the most up-to-date information.

Important

The components are weakly separated: the agent loop runs in the container being controlled by Claude, can only be used by one session at a time, and must be restarted or reset between sessions if necessary.

Quickstart: running the Docker container

Anthropic API

Tip

You can find your API key in the Anthropic Console.

export ANTHROPIC_API_KEY=%your_api_key%
docker run \
    -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
    -v $HOME/.anthropic:/home/computeruse/.anthropic \
    -p 5900:5900 \
    -p 8501:8501 \
    -p 6080:6080 \
    -p 8080:8080 \
    -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest

Once the container is running, see the Accessing the demo app section below for instructions on how to connect to the interface.

Bedrock

Tip

To use the new Claude 3.5 Sonnet on Bedrock, you first need to request model access.

You'll need to pass in AWS credentials with appropriate permissions to use Claude on Bedrock.

You have a few options for authenticating with Bedrock. See the boto3 documentation for more details and options.

Option 1: (suggested) Use the host's AWS credentials file and AWS profile

export AWS_PROFILE=<your_aws_profile>
docker run \
    -e API_PROVIDER=bedrock \
    -e AWS_PROFILE=$AWS_PROFILE \
    -e AWS_REGION=us-west-2 \
    -v $HOME/.aws:/home/computeruse/.aws \
    -v $HOME/.anthropic:/home/computeruse/.anthropic \
    -p 5900:5900 \
    -p 8501:8501 \
    -p 6080:6080 \
    -p 8080:8080 \
    -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest

Once the container is running, see the Accessing the demo app section below for instructions on how to connect to the interface.

Option 2: Use an access key and secret

export AWS_ACCESS_KEY_ID=%your_aws_access_key%
export AWS_SECRET_ACCESS_KEY=%your_aws_secret_access_key%
export AWS_SESSION_TOKEN=%your_aws_session_token%
docker run \
    -e API_PROVIDER=bedrock \
    -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
    -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
    -e AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN \
    -e AWS_REGION=us-west-2 \
    -v $HOME/.anthropic:/home/computeruse/.anthropic \
    -p 5900:5900 \
    -p 8501:8501 \
    -p 6080:6080 \
    -p 8080:8080 \
    -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest

Once the container is running, see the Accessing the demo app section below for instructions on how to connect to the interface.

Vertex

You'll need to pass in Google Cloud credentials with appropriate permissions to use Claude on Vertex.

docker build . -t computer-use-demo
gcloud auth application-default login
export VERTEX_REGION=%your_vertex_region%
export VERTEX_PROJECT_ID=%your_vertex_project_id%
docker run \
    -e API_PROVIDER=vertex \
    -e CLOUD_ML_REGION=$VERTEX_REGION \
    -e ANTHROPIC_VERTEX_PROJECT_ID=$VERTEX_PROJECT_ID \
    -v $HOME/.config/gcloud/application_default_credentials.json:/home/computeruse/.config/gcloud/application_default_credentials.json \
    -p 5900:5900 \
    -p 8501:8501 \
    -p 6080:6080 \
    -p 8080:8080 \
    -it computer-use-demo

Once the container is running, see the Accessing the demo app section below for instructions on how to connect to the interface.

This example shows how to use the Google Cloud Application Default Credentials to authenticate with Vertex.

You can also set GOOGLE_APPLICATION_CREDENTIALS to use an arbitrary credential file, see the Google Cloud Authentication documentation for more details.

Accessing the demo app

Once the container is running, open your browser to http://localhost:8080 to access the combined interface that includes both the agent chat and desktop view.

The container stores settings like the API key and custom system prompt in ~/.anthropic/. Mount this directory to persist these settings between container runs.

Alternative access points:

Screen size

Environment variables WIDTH and HEIGHT can be used to set the screen size. For example:

docker run \
    -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
    -v $HOME/.anthropic:/home/computeruse/.anthropic \
    -p 5900:5900 \
    -p 8501:8501 \
    -p 6080:6080 \
    -p 8080:8080 \
    -e WIDTH=1920 \
    -e HEIGHT=1080 \
    -it ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest

We do not recommend sending screenshots in resolutions above XGA/WXGA to avoid issues related to image resizing. Relying on the image resizing behavior in the API will result in lower model accuracy and slower performance than implementing scaling in your tools directly. The computer tool implementation in this project demonstrates how to scale both images and coordinates from higher resolutions to the suggested resolutions.

When implementing computer use yourself, we recommend using XGA resolution (1024x768):

  • For higher resolutions: Scale the image down to XGA and let the model interact with this scaled version, then map the coordinates back to the original resolution proportionally.
  • For lower resolutions or smaller devices (e.g. mobile devices): Add black padding around the display area until it reaches 1024x768.

Development

./setup.sh  # configure venv, install development dependencies, and install pre-commit hooks
docker build . -t computer-use-demo:local  # manually build the docker image (optional)
export ANTHROPIC_API_KEY=%your_api_key%
docker run \
    -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
    -v $(pwd)/computer_use_demo:/home/computeruse/computer_use_demo/ `# mount local python module for development` \
    -v $HOME/.anthropic:/home/computeruse/.anthropic \
    -p 5900:5900 \
    -p 8501:8501 \
    -p 6080:6080 \
    -p 8080:8080 \
    -it computer-use-demo:local  # can also use ghcr.io/anthropics/anthropic-quickstarts:computer-use-demo-latest

The docker run command above mounts the repo inside the docker image, such that you can edit files from the host. Streamlit is already configured with auto reloading.