GitHub radar
Open-Kritt: AI Agents to Secure Your Code!
Open source platform created by the Kritt team to orchestrate AI agents (such as Codex, Claude Code, or any OpenAI/Anthropic compatible model) to discover actual security bugs in code. We developed open-kritt based on our internal tooling which has already resulted in over $1.5M in verified bug-bounties (researcher: Blockian).
open-kritt is an open source security research platform built by the Kritt team to orchestrate AI agents (like Claude Code, Codex or any other model via OpenAI/Anthropic API) to find actual security issues in code repositories. Rather than asking one model about all the code, we break down the task into smaller prompt chains and run them in parallel across multiple agents. Afterwards we filter out duplicates and order the findings by their severity. We built open-kritt on top of our internal tools which were already used to verify more than $1.5M worth of bug-bounties (Blockian, researcher).
Why a vibe-coder should care
While building applications with AI agents, there might be security issues that can be abused by others. Use open-kritt to perform the same multi-agent code analysis as professionals do on your own code before releasing it!
▌ More finds