A declarative AI agent environment manager, written in Rust.

Name comes from the Japanese word カセット (kasetto) - cassette. Think of Skills and MCPs as cassettes you plug in, swap out, and share across machines.

Why Kasetto

There are good tools in this space already - Vercel Skills installs skills from a curated catalog, and Claude Plugins offer runtime integrations. Both work well for one-off installs, but neither gives you a declarative, version-controlled config.

Kasetto is a community-first project that solves a different problem: declarative, reproducible skill management across machines and agents.

• Declarative — one YAML file, your whole setup: skills, commands, MCPs, and agents. Apply globally or scope to a project; configs compose with extends, so org, team, and project stay in sync.
• Enterprise & private repositories — pull from anywhere: GitHub, GitLab, Bitbucket, Codeberg, Gitea, and self-hosted instances, public or private. Onboard a new engineer with one command; everyone gets the same environment, zero drift.
• Multi-agent — write once, ship everywhere. Claude Code, Cursor, Codex, Windsurf, Copilot, Gemini CLI, and many more — one sync keeps them all current.
• Skills, Commands & MCPs — all three asset kinds, one source: skills, commands, and MCPs. Everything is transformed into each agent's native format, and auto-merged. Distribute rules, tools, and prompts as easily as sharing a repository link.
• Speed — instant by design. Built in Rust, it hashes content and diffs a lock file so only what changed gets touched — full syncs finish in seconds.
• Universal — one static binary for macOS, Linux, and Windows. Install as kasetto, run as kst. CI-friendly with --json output and real exit codes.

Inspired by uv - what uv did for Python packages, Kasetto aims to do for AI skills.

Install

Standalone Installer

macOS and Linux:

curl -fsSL kasetto.dev/install | sh

Windows:

powershell -ExecutionPolicy Bypass -c "irm kasetto.dev/install.ps1 | iex"

Homebrew

brew install pivoshenko/tap/kasetto

Scoop (Windows)

scoop bucket add kasetto https://github.com/pivoshenko/scoop-bucket
scoop install kasetto

Cargo

cargo install kasetto

Getting Started

1. Scaffold a config:

kst init            # creates ./kasetto.yaml in the current directory
kst init --global   # or a global one at ~/.config/kasetto/kasetto.yaml

Edit the generated kasetto.yaml — pick an agent, add a skills: source, and you're ready to sync.

2. Sync skills into your agents:

# uses ./kasetto.yaml in the current directory
kst sync

# or point at a shared team config over HTTPS
kst sync --config https://example.com/team-skills.yaml

Want bare kst sync to always pull from a remote URL? Persist it in ~/.config/kasetto/config.yaml:

source: https://github.com/pivoshenko/pivoshenko.ai/blob/main/kasetto.yaml

After that, kst sync resolves the URL automatically — no --config flag needed.

That's it. Kasetto pulls the skills and installs them into the right agent directory. The next time you run sync, only what changed gets updated.

See pivoshenko/pivoshenko.ai for a community example pulling skills from multiple packs for Claude Code and OpenCode.

3. See what's installed:

kst list      # interactive browser with vim-style navigation
kst doctor    # version, paths, last sync status

Commands

One-line synopsis below. Full flags and examples in the commands reference.

• kst init — generate a starter kasetto.yaml (local or --global).
• kst sync — read config, fetch sources, install skills + MCPs into agent dirs.
• kst list — interactive TUI (or plain/JSON) of installed skills and MCPs from the lock file.
• kst doctor — local diagnostics: version, paths, last sync status, broken skills.
• kst clean — remove tracked skills and MCP configs for the given scope.
• kst self update — fetch latest release, verify SHA256, replace binary in place.
• kst self uninstall — remove installed assets, data, and the binary.
• kst completions <shell> — emit shell completion script (bash/zsh/fish/powershell).

Most commands accept --json, --plain, --quiet, and --project | --global.

Configuration

When --config is omitted, Kasetto looks for config in this order:

1. $KASETTO_CONFIG env var
2. source: key in $XDG_CONFIG_HOME/kasetto/config.yaml
3. ./kasetto.yaml
4. $XDG_CONFIG_HOME/kasetto/kasetto.yaml (or ~/.config/kasetto/kasetto.yaml)

Run kst init to scaffold a local config, or kst init --global for the global one.

# Option A: preset destination by agent (see README for supported agent values)
agent:
  - codex
  - claude-code

# Option B: manual destination (takes precedence if both are set)
# destination: ./.agents/skills

skills:
  # "*" syncs every skill in the source — each is a directory with a SKILL.md,
  # discovered in the source root or its skills/ subdirectory
  - source: https://github.com/vercel-labs/next-skills
    # ref: v1.0.0   # pin to a tag or commit; omit to track the default branch
    skills: "*"

  # or list skills by name
  - source: https://github.com/anthropics/skills
    skills:
      - doc-coauthoring
      - frontend-design
      - pptx

  # sub-dir: resolve the named skills under this path, e.g. skills/productivity/grill-me/
  - source: https://github.com/mattpocock/skills
    sub-dir: skills/productivity
    skills:
      - grill-me
      - caveman

  # path: a skill in a non-standard location → <path>/<name>/, here skills/engineering/improve-codebase-architecture/
  - source: https://github.com/mattpocock/skills
    skills:
      - name: improve-codebase-architecture
        path: skills/engineering

commands:
  # names resolve to commands/<name>.md in the source (nested dirs namespace, e.g. git:commit)
  - source: https://github.com/gsd-build/get-shit-done
    commands:
      - gsd:explore
      - gsd:fast

mcps:
  # names resolve to mcps/<name>.json in the source
  - source: https://github.com/pivoshenko/pivoshenko.ai
    branch: main   # track a specific branch (use ref: to pin a tag or commit)
    mcps:
      - github
      - vercel
      - kaggle

Full key reference, merge rules, and extends: inheritance live in the configuration docs.

Supported Agents

Set the agent field and Kasetto figures out where to put things.

Full list of supported agents

Agent	Config value	Install path
Amp	amp	~/.config/agents/skills/
Antigravity	antigravity	~/.gemini/antigravity/skills/
Augment	augment	~/.augment/skills/
Claude Code	claude-code	~/.claude/skills/
Cline	cline	~/.agents/skills/
Codex	codex	~/.codex/skills/
Continue	continue	~/.continue/skills/
Cursor	cursor	~/.cursor/skills/
Gemini CLI	gemini-cli	~/.gemini/skills/
GitHub Copilot	github-copilot	~/.copilot/skills/
Goose	goose	~/.config/goose/skills/
Junie	junie	~/.junie/skills/
Kiro CLI	kiro-cli	~/.kiro/skills/
OpenClaw	openclaw	~/.openclaw/skills/
OpenCode	opencode	~/.config/opencode/skills/
OpenHands	openhands	~/.openhands/skills/
Replit	replit	~/.config/agents/skills/
Roo Code	roo	~/.roo/skills/
Trae	trae	~/.trae/skills/
Warp	warp	~/.agents/skills/
Windsurf	windsurf	~/.codeium/windsurf/skills/

Don't see your agent? Use the destination field to point at any path.

Private Repositories & Enterprise

Private GitHub, GitLab, Bitbucket, Codeberg, Gitea, and self-hosted instances work via env-var tokens (GITHUB_TOKEN, GITLAB_TOKEN, BITBUCKET_TOKEN, GITEA_TOKEN, etc.) — no login command, no credentials file. The same tokens apply to remote --config URLs.

Full host table and auth resolution rules in the authentication docs.

Contributing

See CONTRIBUTING.md for development setup and guidelines.

License

Licensed under either MIT or Apache-2.0, at your option.