VibeKit - Run coding agents in a secure sandbox
byโข
VibeKit is an open-source SDK to run coding agents like OpenAI Codex and Claude in secure sandboxes. Let agents write code, install packages, or open PRs safely โ with streaming, async tasks, and telemetry built-in.
MIT licensed, TypeScript, zero lock-in.



Replies
VibeKit
No human-in-the-loop? In general, in have found it difficult to get results at the right productivity levels without human in the loop
Super RAG
@manu_goel2ย We are planning to add human-in-the-loop functionality in the future.
VibeKit strikes the right balance between flexibility and safety โ letting coding agents work freely in secure environments. Love the open-source ethos, async support, and dev-friendly setup. A solid foundation for agent-powered tooling!
VibeKit sets a strong foundation for safe autonomous coding ๐ง ๐ก๏ธ. Running agents in a secure sandbox keeps experimentation flexible without compromising system integrity.
VibeKit is a powerful open-source SDK for running coding agents like OpenAI Codex and Claude in secure sandboxes! With the ability to safely allow agents to write code, install packages, and open PRs, it brings flexibility and security to your development process. Iโm excited to see how its built-in streaming, async tasks, and telemetry make it an invaluable tool for developers, all while being MIT licensed and offering zero lock-in!
Thanks for sharing, i will try it