Skip to content
ARTEX.sh

ARTEX vs CyberStrikeAI:two Go consoles, one with its own C2.

CyberStrikeAI (AIPentest/CyberStrikeAI) is an Apache-2.0 platform in Go that joins AI agents, MCP tools, a knowledge base and workflows in one console. ARTEX is an AGPL platform in Go that lives on in forks. This page compares design, license, safety controls, status, published numbers and attack reporting, as of 2026-11-17.

Data as of 2026-11-17

ARTEX and CyberStrikeAI side by side

AspectARTEXCyberStrikeAI
MaintainerAutumn-27 wrote it. The original repo was deleted on 2026-10-08. RuoJi6/ARTEX is the main maintained forkAIPentest, a GitHub organization
StartedFirst commit on 2026-07-26Repo created 2025-11-08
Language and stackGo 1.26, Next.js 16 console, PostgreSQL 16Go 1.25 or newer with Python 3.10 or newer for some tools, SQLite storage
LicenseAGPL-3.0Apache-2.0
ArchitectureA planner and 3 workers by default over an asset graph and an exploration graphPi-based agents in single, Deep, Plan-Execute or Supervisor modes, graph workflows, 100+ YAML tool recipes, MCP and a RAG knowledge base
Guard and safety controlsEvery tool call passes intercept rules, an LLM judge and human approval. A recording proxy keeps all traffic. Default block on .gov and .eduApproval modes, tool allowlists, an audit agent, regex call blocking with government domains blocked by default, user roles and audit logs
High-risk featuresNo built-in C2 or WebShell manager in the open code described on this siteWebShell management and a built-in C2 with listeners and beacons. The README says to use them only on systems you are authorized to test
DeploymentOne Go binary with a web console and PostgreSQL, from release zips or DockerA run.sh script builds and starts it. HTTPS with a self-signed certificate on 127.0.0.1:8080 by default
MaintenanceRuoJi6/ARTEX: v0.3.30 on 2026-11-14, last push 2026-11-14, 2,194 stars (2026-11-17)v1.8.0 on 2026-11-13, last push 2026-11-16, 8,776 stars and 1,981 forks (2026-11-17)
Offsec Harness IndexEntry 01, tier Confirmed, breach stated. 14 primary reports. Key figure: 200+ organizations targeted (CrowdStrike)Tier Confirmed, breach stated. 5 primary reports, including Kaspersky, TrendAI and Team Cymru. Key figure: 3 to 4 days to domain admin
Public benchmarkBaidu Agent+ final: 1st overall (2026-09-03). Live range 67.83/100, 7th. TSecBench 89.78/100, 6thNo benchmark score in its README

Two consoles with different reach

Both projects are Go servers that you run yourself and use from a web console. CyberStrikeAI's README describes a broad workspace: agents that turn plain requests into tool runs, several multi-agent modes, visual workflows, an asset list, vulnerability tracking, attack chain views and chat bots for WeChat, Lark, Telegram, Slack and others. It ships more than 100 tool recipes and a Burp Suite extension.

ARTEX is narrower. It runs a planner and workers over two graphs and produces one report per finding. The clearest gap is in the high-risk features. CyberStrikeAI's README lists WebShell management and a built-in command and control server with listeners, encrypted beacons and payload helpers, and it marks both for authorized use only. The ARTEX open code described on this site has no such parts.

Safety controls

On paper the two have similar control layers. CyberStrikeAI's README lists approval modes, tool allowlists, an audit agent that reviews actions, regex checks that can block a tool call before it runs, with government domains blocked by default, plus user roles and audit logs. ARTEX puts each tool call through intercept rules, an LLM judge and human approval, blocks .gov and .edu assets by default and records all traffic through a proxy.

Both depend on how they are set up. CyberStrikeAI listens on 127.0.0.1 by default and prints a one-time admin password on first start, and its README points to a hardening guide before exposing it. ARTEX consoles left open on the internet have been counted by scanners, as this site's exposed consoles page shows.

In the Offsec Harness Index

Both tools have the tier Confirmed in the Offsec Harness Index. For ARTEX it cites 14 primary reports, and its key figure, 200+ organizations targeted, comes from CrowdStrike's report of 2026-10-29.

For CyberStrikeAI it cites five primary reports. Kaspersky's report of 2026-11-02 describes attacks on schools and universities in Latin America and Africa where the operator set the plan and the model on the command server chose the steps. The index gives 3 to 4 days to domain admin as the row's key figure. TrendAI's report of 2026-10-27 saw 44 agents run against at least 19 organizations, 16 or more in Japan, with deep compromise at only a small share. Team Cymru's report of 2026-03-02 tracked its use on attacker servers. CERT-In and Google also name it, and JPCERT/CC listed it beside ARTEX in its Japan alert. These rows record what was reported, not a ranking, and they say nothing about the maintainers' intent.

Status, license and numbers

CyberStrikeAI is Apache-2.0, released v1.8.0 on 2026-11-13 and had a push on 2026-11-16. It has 8,776 stars on 2026-11-17. ARTEX is AGPL-3.0, so a modified network service must publish its source, and its release line lives in forks such as RuoJi6/ARTEX at v0.3.30.

ARTEX has public contest scores from the Baidu Agent+ final and TSecBench. CyberStrikeAI's README gives no benchmark score, so there is no number to set against them.

More comparisons

Compare
  • AntiFox vs ARTEX

    AntiFox is a public fork that says it was built on ARTEX and adds report delivery. What changed, how active it is and its license.

  • ARTEX vs PentestGPT

    A Go platform with a web console against a Python command-line agent from a USENIX Security 2024 paper.

  • ARTEX vs Strix

    A self-hosted Go platform against an Apache-2.0 Python agent with a Docker sandbox, a cloud edition and CI support.

  • ARTEX vs CAI

    An AGPL platform still maintained in forks against CAI from Alias Robotics, now archived with a commercial successor.

  • ARTEX vs HexStrike AI

    A self-contained agent platform against an MCP server that lets your own AI client call more than 150 security tools.

  • ARTEX vs PentAGI

    Two self-hosted multi-agent systems written in Go: an AGPL platform kept alive in forks and VXControl's MIT system with a Docker sandbox.

  • ARTEX vs Cairn

    Cairn is the one project the ARTEX README lists as its reference. Both grow a graph of facts and intents; one is a Go platform, the other a Python engine.

  • ARTEX vs Shannon

    Both AGPL-3.0. ARTEX runs open-ended assessments from a console; Shannon reads an app's source and only reports what it can prove.

  • ARTEX vs T3MP3ST

    Both AGPL-3.0. ARTEX gates every tool call; T3MP3ST drives the coding agent you already use and has been quiet since 2026-09-08.

  • ARTEX vs AgenticPentest

    ARTEX is AGPL-3.0 and gates every tool call; AgenticPentest is a two-week-old MIT workbench that fences work by scope and approves state-changing actions.

  • ARTEX vs ARIA-X

    ARTEX and an independent Python rebuild: shared design ideas, different storage and control defaults, no performance ranking.

Follow the ARTEX story.

New forks, releases and reports, dated and sourced.

Isometric plane with glowing light columns