Thanks for your interest in contributing to Amy! This document outlines how to get started.
- Fork the repository
- Clone your fork locally
- Install dependencies with
julia --project=. -e 'using Pkg; Pkg.instantiate()' - Ensure Ollama is running with DeepSeek-R1 model
- Run tests with
julia --project=. -e 'using Pkg; Pkg.test()'
# Install dependencies
julia --project=. -e 'using Pkg; Pkg.instantiate()'
# Run tests
julia --project=. -e 'using Pkg; Pkg.test()'
# Run an example
julia --project=. examples/llm_demo.jl- Check existing issues first to avoid duplicates
- Use a clear, descriptive title
- Include steps to reproduce the issue
- Describe expected vs actual behavior
- Open an issue describing the feature
- Explain the use case and why it would be valuable
- Be open to discussion about implementation approaches
- Create a branch from
mainfor your changes - Make your changes with clear, focused commits
- Ensure all tests pass
- Open a PR with a clear description of changes
- Link any related issues
- Follow existing patterns in the codebase
- Use meaningful variable and function names
- Add docstrings to public functions
- Include unit tests for new functionality
- Mathematical domains: Add new tool categories (plasma physics, relativity)
- LLM improvements: Enhance agent prompts for better reasoning
- Verification: More validation checks and physical constraints
- Examples: New use cases and demonstrations
- Documentation: Tutorials, examples, API documentation
Open an issue or reach out to the maintainers. We're happy to help!