VibeKit 🖖 by Superagent Launches: The Safety Layer for Your Coding Agent

VibeKit 🖖 by Superagent recently launched!

‍

^{"Open-source sandboxing and observability for Claude Code, Gemini CLI, et al."}

‍

Founded by Alan Zabihi & Ismail Pelaseyed

Hey everyone! 👋 Meet Alan & Ismail. They're building VibeKit, an open-source safety layer for Claude Code, Gemini CLI, and other coding agents.

‍

❌ The Problem

The founders loved coding with AI agents — until the day Anthropic emailed them to say they had found their API keys in a public GitHub repo and revoked them.

The leak came from their own coding agent. That’s when the VibeKit founders realized most developers have no way to see — let alone control — what their AI agents are doing:

• Which files they read or write.
• What shell commands they run.
• What data leaves their machine.
• Whether secrets get exposed in API calls.

‍

🖖 The VibeKit Solution

VibeKit is a universal CLI wrapper that runs any coding agent in a local, isolated Docker sandbox.

‍

It comes with:

• Secret redaction before anything leaves your machine.
• Full observability into file changes, commands, API calls, and outbound data.
• Offline-first, open-source (MIT), and works with any agent — Claude, GPT-4o, Gemini, etc.

‍

💻 Try it out

‍

Then watch everything your AI is doing — safely.

‍

🎥 Demo video

https://youtu.be/vDwJ4xcdRBM

‍

📂 GitHub

https://github.com/superagent-ai/vibekit

‍

📖 Docs

https://docs.vibekit.sh

‍

Learn More

^‍

^{🌐 Visit www.vibekit.sh to learn more.}

^‍

^{🕵️ If you use coding agents day-to-day:}

^{• Run them through VibeKit — see what they’re really doing.}

^{• Share your weirdest or most alarming finds with the founders — they’re building a public library of “agent fails.”}

‍

^{💌 Contact the founders via email here.}  

^‍

^{👣 Follow Superagent on LinkedIn & X.}

‍