Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.hiverge.ai/llms.txt

Use this file to discover all available pages before exploring further.

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

Setup the experiment configuration

Hive experiments are configured using YAML files. To create an initial configuration file, run:
hive init
You will be prompted to input your organisation ID. If you do not know your organisation ID, please contact your organisation administrator.This will create a default configuration file at ~/.hive/config.yaml with the following contents:
~/.hive/config.yaml
version: v1alpha1
organisation_id: 'your-org-id'

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

runtime:
  num_agents: 1
  max_runtime_seconds: -1  # -1 = unlimited
  max_iterations: -1       # -1 = unlimited

sandbox:
  base_image: python:3.9-slim
  setup_script: |
    pip install -r requirements.txt
  evaluation_timeout: 60
  resources:
    cpu: "2"
    memory: 4Gi
In this quickstart tutorial, we will launch an experiment using this demo repository. To configure this, run the following command to open up ~/.hive/config.yaml in your default text editor:
hive edit config
Then change the repo.source field to:
repo:
  source: https://github.com/hiverge/demo.git
To launch an experiment using a private repository, you will also need to add a GitHub authentication token to the repo.github_token field in the configuration YAML.
3

Log in to the Hive

Authenticate yourself with the Hive platform by using:
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.
4

Launch the experiment

You are now ready to launch your first Hive experiment by calling:
hive create exp my-demo-experiment-
Adding a - suffix to the experiment name appends a random unique ID to it. 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 delete a running Hive experiment:
hive delete 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.