Kavach

Tactical Zero-Trust OS Firewall for Local AI Agents

3 followers

Tactical Zero-Trust OS Firewall for Local AI Agents

3 followers

Visit website

The Tactical Zero-Trust AI Firewall. Contribute to LucidAkshay/kavach development by creating an account on GitHub.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

EOL Dataset by HeroDevs — Find every EOL dependency in your stack. Free. In 5 minutes.

Find every EOL dependency in your stack. Free. In 5 minutes.

Promoted

Maker

📌

Hi Product Hunt! 👋 I’m Akshay, the builder behind Kavach. Like many of you, I’ve been building and experimenting with local LLMs and autonomous agents. But the anxiety of giving an AI unrestricted read/write access to my file system was holding me back. One hallucinated script could wipe out a src directory or corrupt my configs. I couldn't find a good "emergency brake," so I built one. Kavach (Sanskrit for "Armor") is a tactical security layer that intercepts system calls at the OS level. It doesn't just monitor logs; it actively stops unauthorized changes. Here is what makes it tick: 👻 The Phantom Workspace: If an untrusted agent tries to modify a file, Kavach redirects the action to a hidden virtual directory. The AI thinks it succeeded, but your real code is safe. ⏳ Temporal Rollback: If a file gets mangled, our cryptographic micro-cache lets you one-click "time-travel" it back to its exact state from milliseconds prior. 🧠 The Turing Protocol: To stop multimodal models from using RPA to just click "Approve" on firewall alerts, the UI uses adversarial noise patterns to blind AI OCR. I built the backend in Rust for near-zero latency, paired with a Tauri + React frontend. It runs 100% locally with zero cloud dependencies. If you are tinkering with AI agents, I’d love for you to download the v1.0 (available for Windows & macOS), protect your perimeter, and try to bypass the Phantom Workspace. I'll be hanging out in the comments all day, let me know what you think, what features you'd want next, or if you just want to talk Rust and local LLMs! 🛡️

Report

2mo ago

Maker

We just crossed 100 Stars on GitHub! 🌟

I wanted to drop a massive thank you to the Product Hunt community. The support, the technical deep-dives, and the feedback over the last few days have been absolutely incredible.

When I first started building Kavach, I really just wanted to solve my own anxiety around running local autonomous agents. Seeing so many of you resonate with the need for a true "emergency brake" validates exactly why this open-source project needs to exist.

A special shoutout to everyone who has already downloaded the v1.0, tested the Rust hooks, and provided feedback.

What's next? We just officially opened up the Discussions tab on our GitHub repository! We are actively mapping out the v1.1 roadmap, including things like Linux/eBPF support, the Faraday Clipboard Guard, and new Honeypot Decoys.

If you have wild feature requests or if you want to take on the "Phantom Bypass Challenge" to test our security hooks, come join the community on GitHub.

Thank you all again for making this launch so special! 🛡️🚀

Report

1mo ago

Reviews

Most Informative

We just crossed 100 Stars on GitHub! 🌟

I wanted to drop a massive thank you to the Product Hunt community. The support, the technical deep-dives, and the feedback over the last few days have been absolutely incredible.

A special shoutout to everyone who has already downloaded the v1.0, tested the Rust hooks, and provided feedback.

If you have wild feature requests or if you want to take on the "Phantom Bypass Challenge" to test our security hooks, come join the community on GitHub.

Thank you all again for making this launch so special! 🛡️🚀