Thank you for your interest in contributing. This project values transparency, auditability, and human judgment above all else. Every contribution — code, documentation, or discussion — becomes part of the repository's permanent history.
Before contributing, please read the ETHOS to understand the builder principles behind this project.
Open a GitHub Issue with:
- A clear, descriptive title.
- Steps to reproduce the problem.
- What you expected to happen and what actually happened.
- Your environment (OS, Bun version, LLM provider).
Open a GitHub Issue describing:
- The problem or gap the feature addresses.
- How it fits within the existing architecture (issues as conversation, Git as memory, Actions as runtime).
- Any security implications — review the Capabilities Analysis to understand the access model.
- Fork the repository and create a branch from
main. - Make your changes in small, reviewable increments.
- Test locally with
cd .github-gstack-intelligence && bun installand verify dependencies install cleanly. - Open a pull request with a clear description of what changed and why.
.github-gstack-intelligence/ # Core agent framework
.pi/ # Agent personality, skills, and LLM config
install/ # Default templates for agent identity and settings
lifecycle/ # Agent orchestrator and runtime hooks
state/ # Git-tracked session history and issue mappings
.github/ # GitHub Actions workflows and issue templates
See the README for a detailed breakdown of every file.
- Install Bun.
- Clone the repository.
- Install dependencies:
cd .github-gstack-intelligence && bun install
- Add an LLM API key as a repository secret (see Supported Providers).
- Documentation is Markdown. Use tables, clear headings, and concise language consistent with existing files.
- Code is TypeScript, executed with Bun.
- Skills are self-contained Markdown files in
.github-gstack-intelligence/skills/. - Help documentation for each skill lives in
.github-gstack-intelligence/help/. - Commit messages should be short and descriptive. Every commit is permanent and auditable.
If you discover a security vulnerability, do not open a public issue. Contact the maintainers privately through GitHub's Security Advisory feature.
All contributions are subject to review for security implications. Changes that expand the agent's capabilities or permissions require careful review.
All contributors are expected to follow the Code of Conduct.
By contributing, you agree that your contributions will be licensed under the MIT License.