Skip to main content

Quick Start

A quick start guide to setup docker container of our Waterwheel agent on your local machine.

What You'll Need​

  • Mac (Apple "M" series chip)
  • Docker Desktop
  • Your AI access API key

Installation​

note

All files mentioned in this section are bundled in mac-local-install.zip. Download it and extract its contents before proceeding.

1. Create the Folder Structure​

Run create-sync-subfolders.sh to create the local folder structure used for Docker volume mapping.

chmod +x create-sync-subfolders.sh
./create-sync-subfolders.sh /path/to/sync

2. Configure Environment Variables​

Open dot_env.txt and fill in the following variables.

WATERWHEEL_SYNC_VOLUME_PATH=${to_fill} # The folder `/path/to/sync` created in step 1
API_PROVIDER=${to_fill}                # AI provider
AI_MODEL=${to_fill}                    # AI model
AI_API_KEY=${to_fill}                  # AI API key

3. Place the Environment File​

Rename dot_env to .env and place it in the same directory as docker-compose.yml.

4. Copy Instruction Files​

Copy the following three files into agent/instructions under /path/to/sync.

5. Copy Task File​

Copy test-wikipedia-english.md into /path/to/sync/agent/tasks.

note

You can also try complicated chained test cases by copying 1_test_wikipedia_search.md and 2_test_wikipedia_navigate.md into /path/to/sync/agent/tasks. However, the API cost may be above $1 per test without configuration tuning.

6. Deploy the Docker Container​

From the same directory as docker-compose.yml, run:

docker compose up -d

Verify Installation​

To verify the installation, run the following command on your local machine and confirm no errors are reported in /path/to/sync/agent/outputs/agent.log.

docker compose exec waterwheel-agent run-qa --dry-run

Execute Tests​

To execute all tests under /path/to/sync/agent/tasks, run the following command on your local machine.

docker compose exec waterwheel-agent run-qa

Once the command completes, check the results at /path/to/sync/agent/outputs/test-results.json.