Free · Open Source · MIT

ARGUS

Named after Argus Panoptes — the hundred-eyed giant who never slept and saw everything.

Static scanners tell you what looks wrong. Argus proves it: it reads your code, then spins your app up and actually attacks it — dumping data via SQLi, forging admin JWTs, reaching cloud metadata via SSRF — and explains every finding in plain English, tailored to your codebase.

pip install argus-panoptesCOPY
Download the desktop app View on GitHub
2
Phases
19
Attack agents
GitHub stars
0
Telemetry
MIT
License
00See it in 30 seconds

Nothing to configure. Nothing external touched.

argus demo scans and attacks a bundled, intentionally-vulnerable app so you can watch the full flow immediately.

◈ ARGUS — STATIC SCAN
Risk Score 98/100  [CRITICAL]
   HIGH   SQL injection · command injection · unsafe yaml.load

◈ ARGUS — ATTACK AGENT
  [INJECTOR:SQLI-ERROR]         ✓ SQL injection (error-based)
  [AUTHBREAKER:JWT-WEAK-SECRET] ✓ JWT signed with a weak secret
  [XSSHUNTER:REFLECTED]         ✓ Reflected XSS
  [SSRFPROBER:CALLBACK]         ✓ Server-Side Request Forgery (blind)
  [IDORHUNTER]                  ✓ Insecure Direct Object Reference
  [FILEATTACKER:TRAVERSAL]      ✓ Path traversal (arbitrary file read)
every finding above ships with a runnable proof-of-concept, not a guess.
01How it works

Two phases. One standard: proof or it didn't happen.

Phase I · Static Analysis

Read, before it runs.

Built-in rules, dependency CVEs, secret detection (regex + entropy + git history), behavioral supply-chain analysis, then an LLM layer that validates and explains every finding for your code.

Phase II · Attack Agent

Then it strikes.

A swarm of 19 specialised agents attacks the running app — with an out-of-band callback server to confirm blind vulnerabilities, and a runnable proof-of-concept behind every confirmed finding.

02The attack swarm

Every eye, watching a different weakness.

Hover an eye. Each one hunts a different class of vulnerability, orchestrated as a single swarm against the running app.

03Proof, not vibes

Every scanner claims to catch things. Argus measures it.

argus benchmark runs the full attack swarm against known-vulnerable apps — OWASP Juice Shop, DVWA, VAmPI — and reports a real detection rate against a hand-curated ground truth. Published on every release. Not smoothed over.

100%
argus_demo
14–29%
juice_shop
33%
dvwa
20%
vampi

Every gap here is a known, documented one — Juice Shop is an Angular SPA racing a bootstrap timer, DVWA needs a per-session difficulty unlock, VAmPI's OpenAPI auto-discovery alone moved it from 0% to 20%. Full run-by-run history in ROADMAP.md.

04Meets you where you work

CLI, CI, editor, or a native app — same engine underneath.

Command line

pip install argus-panoptes — scan, attack, fix, and export SARIF/PDF/Jira from one binary.

CI-native

A GitHub Action, --fail-on severity gating, and per-rule policy files for PR checks that actually block.

Inside your editor

argus mcp-server exposes scan/attack/fix as MCP tools for Claude Code, Cursor, and Copilot.

Desktop app

A real native shell (Tauri) driving the same Python engine — live attack feed, reports, and settings, no demo data.

Pre-commit hook

Catch a hardcoded secret or an injectable query before it ever reaches a PR.

Local or BYOK

Run fully offline against a local Ollama model, or bring your own Groq/Gemini/Claude/OpenRouter key.

Read the full docs — install flags, CI setup, MCP, pre-commit →

05Why Argus

Nobody else combines all six.

StaticActive attackLLM reasoningFreeLocal modelOpen source
SnykPartial
SonarQubePartialPartial
Semgrep
Burp SuitePartial
OWASP ZAP
Argus
06Take it home

No account. No telemetry. Ever.

Grab the CLI from PyPI, or the desktop app's native installer for your platform.

Windows

NSIS / MSI installer

Latest release →

macOS

Universal .dmg (Apple Silicon + Intel)

Latest release →

Linux

.deb · .rpm · .AppImage

Latest release →
pip install argus-panoptesCOPY

All platforms, Docker, and CLI extras →

FAQ

Questions, answered.

Is Argus really free?

Yes — MIT licensed, no account, no paywall, no usage limits. Run it fully offline against a local model if you don't want to touch a cloud provider at all.

Does it send my code anywhere?

Only if you configure a cloud LLM provider (Groq, Gemini, Claude, OpenRouter) — and even then, only the specific finding context sent for reasoning, never your whole repo. Local-model mode (Ollama) never leaves your machine.

Is active attacking (Phase 2) safe to run?

Argus only attacks the exact origin you authorize — off-origin links, redirects, and API specs on a target page can't pull it out of scope. Read the security & responsible use policy before pointing it at anything you don't own.

Where do I report bugs or request features?

GitHub Issues — PRs welcome too.