Skip to main content
By the end of this guide, you’ll have a running Hive experiment evolving code from a demo repository.

​
Launching your first experiment

1

Install the CLI

The CLI requires Python 3.12 or higher. It can be installed from PyPI using the following command:
pip install hivekit
2

Initialize and log in

Initialize your user configuration:
hive init
You will be prompted to input your organisation ID. If you do not know your organisation ID, please contact your organisation administrator.Then authenticate with the Hive platform:
hive login
This will open up a browser window, where you will log in using your Hiverge credentials.
If you do not have a Hiverge account yet, contact your organisation administrator to help set up an account for you.
3

Setup the experiment configuration

Hive experiments are configured using YAML files. In this quickstart we will launch an experiment using this demo repository. Create a file called hive.yaml with the following contents:
hive.yaml
apiversion: v1alpha1
experiment_name: my-demo-experiment-

repo:
  source: https://github.com/hiverge/demo.git
  branch: main
  evaluation_script: evaluation.py
  target_code:
    - main.py

runtime:
  num_agents: 2
  max_runtime_seconds: 1800

sandbox:
  base_image: python:3.14-slim
  setup_script: |
    pip install -r requirements.txt
  evaluation_timeout: 60
  resources:
    cpu: "2"
    memory: 4Gi
The clone happens client-side. For private repos, consider using SSH (e.g. git@github.com:<org>/<repo>.git).
4

Launch the experiment

You are now ready to launch your first Hive experiment by calling:
hive create exp -c hive.yaml
The - suffix on experiment_name in the YAML appends a random unique ID. We recommend using this to avoid clashes where two experiments share the same name.
5

Manage the experiment

To list all Hive experiments currently running:
hive list exp
To get details of of a running Hive experiment:
hive get exp my-demo-experiment-abc123
You can view more details about Hive experiments by visiting the dashboard, which can be accessed using:
hive dashboard
To stop a running Hive experiment:
hive stop exp my-demo-experiment-abc123

​
Next steps

Prepare an experiment

Learn how to prepare your own codebase to run a custom Hive experiment.

Dashboard

View the progress and results of your running experiments.