Kasetto

Declarative AI agent environment management is simplified through a single YAML file that replaces manual setup scripts. This approach allows users to define skills, MCP servers, and agents once and maintain consistency across different configurations using the `extends` feature for composition. The tool seamlessly integrates with various version control platforms, including GitHub, GitLab, Bitbucket, Codeberg, Gitea, and self-hosted instances, making it suitable for enterprise and private repositories. Onboarding new engineers becomes straightforward with a single command, ensuring that everyone works with the same environment and eliminating drift and surprises. The tool supports a wide range of AI agents, such as Claude Code, Cursor, Codex, Windsurf, and Copilot, allowing users to manage and update configurations across multiple agents simultaneously. Skill directories are defined by the presence of a SKILL.md file, eliminating the need for a registry or boilerplate code. MCP server configurations are automatically merged into supported formats, facilitating the distribution of rules and tools. Built in Rust, the tool offers instant startup and efficient synchronization through SHA-256 hashing and lock file diffing, ensuring that only changes are processed. It is available as a single static binary for macOS, Linux, and Windows, making it easy to integrate into CI pipelines with features like --json output and proper exit codes, maintaining consistent behavior across different environments.