earlyai-agent

AI-powered automatic unit test generation for Python, by Early.

earlyai-agent is the Python analysis engine used by the Early CLI to generate green (passing) unit tests. It analyzes your source code, identifies public functions and methods, and generates pytest tests using AI.

Note: earlyai-agent is a dependency of the Early CLI and is not intended to be used standalone. Install and operate it through the Early CLI.

Installation

1. Install the Early CLI

npm install -g @earlyai/cli

See the CLI Installation Guide for details.

2. Install earlyai-agent

pip install earlyai-agent

Requirements: Python 3.11+

3. Get an API Key

You need an EarlyAI API key to use the agent. Contact support@startearly.ai or visit www.startearly.ai to get one.

Usage

All commands are run through the Early CLI. See the full CLI documentation for all options.

Generate tests for a project

early generate-project \
  --api-key <your-api-key> \
  --token <your-github-token> \
  --target-directory src/ \
  --ref-name <branch-name> \
  --test-framework pytest

See the Repo CLI Guide for more details.

Generate tests on a pull request

early generate-pr \
  --api-key <your-api-key> \
  --token <your-github-token> \
  --pr-number 123 \
  --ref-name feature/my-branch \
  --test-framework pytest

See the PR CLI Guide for more details.

Run locally

For quick local evaluation, see Running Early CLI Locally.

Configuration

All options can be set via CLI flags or environment variables:

For the full configuration reference, see CLI Configuration.

Test file placement

• siblingFolder (default): Tests are placed in a folder next to the source file

  src/services/user.py
  src/services/user.early.test/test_get_user.py
  

• rootFolder: Tests are placed in a root tests/ directory mirroring the source structure

CI/CD Integration

GitHub Actions (PR)

Add to .github/workflows/early-pr-test-generation.yml:

name: Early PR Test Generation

permissions:
  contents: write
  pull-requests: write
  packages: read

on:
  pull_request:
    types: [opened, reopened, synchronize]
    branches: [main]

jobs:
  early-test-generation:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
        with:
          ref: ${{ github.head_ref }}

      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"

      - uses: actions/setup-node@v4
        with:
          node-version: 20

      - name: Install dependencies
        run: |
          pip install earlyai-agent
          npm install -g @earlyai/cli

      - name: Generate tests
        continue-on-error: true
        env:
          API_KEY: ${{ secrets.EARLY_AGENT_API_KEY }}
          TOKEN: ${{ secrets.GITHUB_TOKEN }}
          PR_NUMBER: ${{ github.event.pull_request.number }}
          REF_NAME: ${{ github.head_ref }}
          BASE_REF: ${{ github.base_ref }}
          TEST_FRAMEWORK: pytest
        run: early generate-pr

For other CI/CD systems (Jenkins, CircleCI, Bitbucket Pipelines), see the Agent Onboarding Guide.

How It Works

1. Scan -- Discovers Python source files in the target directory
2. Extract -- Analyzes each file to identify public functions and methods
3. Generate -- Uses AI to generate unit tests for each function
4. Validate -- Runs generated tests with pytest, keeping only green (passing) tests

Troubleshooting

• Troubleshooting Common Failures
• Why Were No Tests Generated?
• FAQ

Support

• Documentation: docs.startearly.ai
• Email: support@startearly.ai
• Website: www.startearly.ai

License

Commercial