AI BriefingAI Agent-Based Security Research Platform open-kritt Released
Key point
It is an open-source security platform that breaks down complex security review tasks into small units, which multiple AI agents then perform in parallel.
Details
open-kritt has been released, designed to solve the context loss and low accuracy problems that occur when an LLM analyzes a large repository all at once.
This platform breaks down the security review process into small, defined tasks such as entry point mapping, reachable flow tracing, and hypothesis generation, allowing multiple AI agents to perform them in parallel. This makes it possible to verify and prioritize the results.
Key features and characteristics:
- Workflow composition: Build reusable security research playbooks
- Scan and analysis: Analyze local/remote repositories using Codex, Claude Code, etc.
- Verification and reporting: Verify issues and generate PoCs (proofs of concept) via post-scripts
- Model flexibility: Support for various models including OpenAI, Anthropic, and OpenRouter
- Self-hosted: Users directly control prompts and infrastructure for enhanced security
This project is a refined version of an internal project from a research team that recorded over $1.5 million in bug bounties, and it is distributed under the AGPL-3.0 license.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Whiteboard Launches Open-Source VS Code Fork for Human-AI Collaborative Software Design
OpenComputer Hosts 'Ship Video' Agent Using Claude Opus 5.5 to Generate Explainer Videos from Code