Back to directory

Kasetto

A declarative, Rust-based manager for AI agent environments that syncs skills, MCP servers, commands and instructions across projects, machines and multiple coding agents from one YAML config.

Kasetto

Kasetto manages AI agent environments declaratively: skills, commands, MCP servers, instructions and agents are defined in one YAML file that can be applied globally or scoped to a project, with configs composing through an extends mechanism so organization, team and project settings stay in sync.

It pulls configuration from GitHub, GitLab, Bitbucket, Codeberg, Gitea or self-hosted instances, public or private, and transforms the same source into each target agent's native format, including instruction files such as CLAUDE.md, .cursor/rules and AGENTS.md, for agents including Claude Code, Cursor, Codex, Windsurf and Gemini CLI. Secrets are referenced as placeholders and resolved at sync time from environment variables, a credentials file, or a secret manager such as 1Password or Vault.

It is written in Rust as a single static binary for macOS, Linux and Windows, hashes content and diffs a lock file so only changed items sync, and supports JSON output and exit codes for CI.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.