Skip to content
ARTEX.sh

ARTEX vs Shannon:an open-ended platform against a code-first web pentester.

Shannon (KeygraphHQ/shannon) is an AGPL-3.0 AI pentester for web apps and APIs from Keygraph, run from the command line or in CI. ARTEX is an AGPL-3.0 platform that lives on in forks. This page compares design, safety controls, status, published numbers and attack reporting, as of 2026-11-17.

Data as of 2026-11-17

ARTEX and Shannon side by side

AspectARTEXShannon
MaintainerAutumn-27 wrote it. The original repo was deleted on 2026-10-08. RuoJi6/ARTEX is the main maintained forkKeygraph, which also sells Pro and Enterprise editions built on Shannon
LanguageGo 1.26, Next.js 16 console, PostgreSQL 16TypeScript, run with Node.js 22 or newer and Docker
LicenseAGPL-3.0AGPL-3.0, with a commercial license on request
TargetsAssets set per task, from domains and hosts to services and endpointsA web app or API whose source code you have. Black-box testing is only in the paid editions
ArchitectureA planner and 3 workers by default over an asset graph and an exploration graphCode analysis and recon agents feed a merged queue to exploitation agents. Only findings with a working proof are reported
Guard and safety controlsEvery tool call passes intercept rules, an LLM judge and human approval. A recording proxy keeps all trafficRules of engagement in config, the repo mounted read-only in a throwaway container, warnings not to run on production. No approval step described
DeploymentOne Go binary with a web console and PostgreSQL, from release zips or Dockernpx launcher with a Docker worker, plus an official GitHub Action and GitLab CI component
MaintenanceRuoJi6/ARTEX: v0.3.30 on 2026-11-14, last push 2026-11-14, 2,194 stars (2026-11-17)v3.5.1 on 2026-11-11, last push 2026-11-16, 52,016 stars and 6,088 forks (2026-11-17)
Offsec Harness IndexEntry 01, tier Confirmed, breach stated. 14 primary reports. Key figure: 200+ organizations targeted (CrowdStrike)Tier: no attack on record. Its use tags quote its own README, not attack reports
Public benchmarkBaidu Agent+ final: 1st overall (2026-09-03). Live range 67.83/100, 7th. TSecBench 89.78/100, 6thKeygraph's own Photoview 2.4.0 test: 23 true findings and 1 false positive with Claude Opus 5, at $115 in tokens

Different jobs

Shannon's README calls it an autonomous AI pentester for web applications and APIs. It needs the app's source code: it maps the code, runs recon against the running app, merges both lists of suspects and hands them to exploitation agents. Its rule is no exploit, no report, so a finding appears only with a working proof. It writes PDF and Markdown reports plus JSON and SARIF, and it is built to run in CI against staging builds.

ARTEX is an open-ended assessment platform. It starts from a set of assets, keeps them in a shared graph, and lets a planner and workers explore until a goal is proven, with a person able to steer the run from the console. It does not need source code and is not built around a pull request or release pipeline.

Safety controls

Shannon's README says its agents can create users, submit forms and change data, so it should run only on apps you own or may test, never on production, and preferably on staging or local copies. Each scan runs in a throwaway Docker container with the repository mounted read-only, and rules of engagement are set in a config file. The README also warns that findings need human review and that scanning untrusted code can expose the agents to prompt injection. It does not describe a step where a person approves each action.

ARTEX checks each tool call with intercept rules, an LLM judge and human approval, and records all traffic through a proxy. The two designs answer different risks: Shannon narrows what it targets and what it reports, ARTEX gates each action during an open-ended run.

In the Offsec Harness Index

The Offsec Harness Index lists ARTEX as entry 01 with the tier Confirmed, citing 14 primary reports; its key figure, 200+ organizations targeted, comes from CrowdStrike's report of 2026-10-29.

Shannon is on the index with the tier no attack on record. Its use tags come from quotes in its own README, not from attack reports. The index says that tier means none in primary reporting, which is not the same as none happening. It is a statement about reporting as of 2026-11-17, not a safety rating.

Status, license and numbers

Both are AGPL-3.0, and Keygraph also sells a commercial license. Shannon released v3.5.1 on 2026-11-11 and has 52,016 stars on 2026-11-17, against 2,194 for RuoJi6/ARTEX. Keygraph is not accepting outside code contributions. Its paid Pro edition costs $50 per active developer per month, and an Enterprise edition can be self-hosted.

Shannon's numbers come from Keygraph's own follow-up to a Doyensec study on Photoview 2.4.0: the Claude Opus 5 run reported 24 issues, 23 of them true, for $115 in tokens, and a DeepSeek v4 Flash run found 18 for $6.10. Keygraph ran and scored that test itself. ARTEX's numbers come from the Baidu Agent+ contest and TSecBench. A single web app test and a contest range measure different things, so this page does not rank 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 CyberStrikeAI

    Two Go platforms with a web console and human approval. CyberStrikeAI is Apache-2.0 and also ships WebShell management and a built-in C2.

  • 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