boot-code 0.1.4

👋 Welcome to Boot!

Your AI-powered code generator. Write a 5-line spec. Get a working code base that passes tests and builds.

Boot uses AI to generate production-ready code from simple specifications. No more boilerplate. No more setup hassle. Just describe what you want.

Install (30 seconds)

You'll need Python 3.11 or newer.

Step 1: Install the CLI

pip install boot-code

Step 2: Set your API keys

boot needs an API key from either OpenAI and/or Google Gemini.

The simplest way is to create a .env file in the project directory where you plan to run the command.

# Copy the .env file
cp .env.example .env

# Put your API keys inside .env
OPENAI_API_KEY="sk-..."
GEMINI_API_KEY="AIza..."

Use (2 minutes)

Run the main CLI module and follow the prompts:

# Generate a new pipeline from your spec
boot generate path/to/your/spec.toml

# See all available commands and options
boot --help

That's it. Answer a few questions, and watch your pipeline appear.

What You Get

• Complete project structure with all the files you need.
• Working code that's ready to run on your data.
• Unit tests to ensure quality and reliability.
• Visualizations to help you see your results.
• Documentation so your team understands the pipeline.

Why Boot?

Instead of spending hours writing boilerplate, Boot generates:

✅ Production-ready code following best practices
✅ Complete test suites with 90%+ coverage
✅ Interactive visualizations for immediate insights
✅ Professional documentation your team will love
✅ Modern tooling (Streamlit, Black, pytest)

Performance Comparison

Advanced Usage

Below is an example of more advanced usage, using all available flags:

boot generate examples/consumer_tech/spec.toml \
--provider gemini \ 
--model gemini-2.5-pro \
--api-key "AIzaSy..." \
--two-pass \
--temperature 0.1 \
--timeout 180 \
--output-dir Desktop/ecommerce_gemini_pro

poetry run boot generate examples/rust/my_rust_spec.toml --build-pass

Where:

• --provider: Explicitly selects the LLM provider, overriding any default or .env setting.
• --model: Specifies a particular model to use for the generation, rather than the default.
• --api-key: Provides the API key directly on the command line, which takes precedence over any key in an .env file or other environment settings.
• --two-pass: Enables the secondary review pass, where the initial code is sent back to the LLM for refinement and improvement
• --temperature: Sets the generation temperature to a very low value, making the output more deterministic and less random.
• --timeout: Sets the API request timeout, which is useful for complex specifications that may take the model longer to process.
• --output-dir: Specifies a custom directory for the generated project files, overriding the default generated_jobs location.

Examples

Explore real-world use cases in the examples/ directory:

• E-commerce - Top selling products analysis (SQL)
• Healthcare - Patient length of stay analysis (SQL)
• Finance - Stock volatility calculation (Python)
• Energy - Renewable energy production analysis (Python)
• Consumer Tech - Ad attribution pipeline (PySpark)

Supported Languages

Development

See the DEVELOPER_GUIDE.md

Support

• 📖 Documentation: Check the docs/ directory.
• 🐛 Issues: Report bugs on GitHub Issues.