Urgent.News

What's breaking now, across thousands of outlets.

AI

open-kritt: a Chinese translation of the self-hosted AI vulnerability research tool

open-kritt: a Chinese translation of the self-hosted AI vulnerability research platform The original Kritt-ai/open-kritt repository has 2284 stars and is written in JavaScript. It is an open-source, self-hosted platform for AI-driven security and vulnerability research. The project's own one-line description is: "Open-source, self-hosted AI vulnerability research tool that orchestrates agents to…

open-kritt is an AI-powered vulnerability research platform that was originally created in JavaScript by the Kritt-ai repository. The platform aims to provide an open-source, self-hosted solution for security researchers and developers to find and validate security issues in code. A Chinese translation of the original project, located at yangshun2005/open-kritt-cn, was published on October 14, 2026.

This translation includes a Chinese quick-start guide and a fully translated version of the original README, aiming to make the platform accessible to Chinese-speaking users.

To set up the platform, users need Git, Docker with Docker Compose, and Node.js 20 or newer. The platform can be accessed via a local web browser at http://localhost:5173 after running the setup and start commands. The translation notes that network users in China may need to use a mirror or accelerated source due to potential difficulties downloading Docker images or npm dependencies.

One notable aspect of open-kritt is its approach to vulnerability research. Instead of conducting a single large prompt against a whole codebase, the platform breaks down the process into small, explicit tasks. Multiple AI agents execute these tasks in parallel, and their outputs are merged to create deduplicated, ranked, and verifiable findings.

Users can control their own prompts, workflows, model providers, and infrastructure. The translation highlights the importance of security considerations, such as no default application-layer authentication and agents running as root, which must be noted and addressed during setup.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Also reported by 1 other outlet

Read the original at dev.to →

More in AI

More from Wednesday 14 October →