artex-global
Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For autho
What is artex-global?
Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For authorized, defensive and detection use only. (upstream: Autumn-27/ARTEX, AGPL-3.0)
Overview of artex-global
What it is
ARTEX — Global Edition is an autonomous penetration-testing system driven by LLM multi-agents, with a Go backend and Next.js frontend. The UI and generated output default to English and can be switched to Korean, Chinese, Spanish, or Japanese in Settings. This repository is a localized edition of the Chinese open-source project Autumn-27/ARTEX (AGPL-3.0), adapted for worldwide use. It is published for use only within authorized environments to build defensive and detection capabilities. Unauthorized use is a crime; the repository includes warnings about Korean network and privacy laws. The internal reasoning prompts are kept in the original language to preserve benchmarked performance, while user-facing output is forced into the selected language.
Key features
- LLM-driven multi-agent autonomous penetration testing: agents break down goals, execute real tools, and accumulate discovered assets and vulnerabilities into a graph.
- Single Go binary with embedded Next.js frontend; all data stored in PostgreSQL.
- Output language selectable in Settings: English (default), Korean, Chinese, Spanish, or Japanese.
- Supports swapping the LLM provider to any OpenAI-compatible endpoint.
- Includes defensive and detection material such as detection signatures and hardening checklists.
- Published as a Docker image on GitHub Container Registry.
Use cases
- Learning and research in locally isolated environments (e.g., deliberately vulnerable targets such as OWASP Juice Shop or DVWA).
- Building defensive and detection capabilities against autonomous AI attacks.
- Verification of penetration-testing workflows within authorized scope with explicit written authorization.
Getting started
See the repository README for full instructions. Prerequisites: Docker and Docker Compose, an LLM API key (ANTHROPIC_API_KEY or OPENAI_API_KEY). The database is PostgreSQL, brought up by compose. The artex service pulls ghcr.io/jiwoochris/artex-global.
License and pricing
License: AGPL-3.0. Pricing: open source.
Based on the project's public README and repository metadata.