kasetto
Reduces environment setup overhead and configuration drift by automating declarative agent environment provisioning, lowering operational burden and improvin…
A declarative AI agent environment manager written in Rust. One YAML file (kasetto.yaml) defines your skills, commands, MCP servers, and instruction files; 'kst sync' installs them in each agent's native format across Claude Code, Cursor, Codex, Windsurf, Copilot, Gemini CLI, and more. Pulls from public or private GitHub/GitLab/Bitbucket/Gitea repos, composes configs via extends, and resolves ${kst_...} secret placeholders from your environment or secret manager instead of storing tokens in config.
- Declare environment configurations once and reuse them across multiple AI agent projects
- Automate setup of development environments for teams working on Claude integrations
- Version control and quickly switch between different AI agent environment setups
Reduces environment setup overhead and configuration drift by automating declarative agent environment provisioning, lowering operational burden and improving reproducibility across teams.
Platform engineers and DevOps teams managing multi-agent AI deployments requiring consistent, versioned environment configurations.
https://github.com/pivoshenko/kasetto
By pivoshenko
How to Get It
curl -fsSL kasetto.dev/install | sh # or: brew tap pivoshenko/tap && brew install kasetto, or: cargo install kasetto
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me declare environment configurations once and reuse them across multiple AI agent projects
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 105 GitHub stars; contributors unknown; last commit 0d ago; license no license.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 105 GitHub stars; contributors unknown; last commit 0d ago; license no license.