CAI (Cybersecurity AI) vs PentAGI
CAI (Cybersecurity AI) (Alias Robotics) and PentAGI (VXControl) side by side on public data, as of Nov 21, 2026.
PentAGI has 3.5x the GitHub stars of CAI (Cybersecurity AI) (34.7K against 9,870). PentAGI shipped 1 stable release in the past 90 days.
Which should you choose?
Choose CAI (Cybersecurity AI) if
- you work in the terminal
- you want the one gaining users faster (downloads up 27% in 30 days, +39% in the last 7)
Choose PentAGI if
- you want code you can read, fork or self-host (MIT)
- you want to switch between model providers (11 documented against 3)
- you want to run it unattended in scripts or CI
- you prefer the more widely used tool, with more docs and answers around (Gid Score 29 against 20)
Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.
Side-by-side numbers
| Metric | CAI (Cybersecurity AI) | PentAGI |
|---|---|---|
| Gid Score | 20 | 29 |
| Usage data as of | Nov 21 | Nov 21 |
| Rank by Gid Score | #231 | #166 |
| Downloads, last 7 days | 851 | — |
| Downloads, 7-day change | up 39.1% | — |
| Downloads, 30-day change | up 27.4% | — |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 9,870 | 34.7K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 0 | 1 |
| Latest stable release | — | 2.2.0 · 47d ago |
| Stable releases, 90 days | — | 1 |
| Terminal-Bench (best run) | — | — |
| Price | Free | Free (OSS) |
| License | MIT components plus proprietary additions licensed for research use only (LICENSE in aliasrobotics/cai) | MIT |
| First released | April 2025 | January 2025 |
| Interfaces | CLI, Self-hosted | Web app, API, Self-hosted |
| Models | — | — |
A dash means there is no public data for that metric as of Nov 21, 2026.
Trends
CAI (Cybersecurity AI)
A Python framework from Alias Robotics for building and running AI security agents for reconnaissance, exploitation, privilege escalation and defensive tasks, with guardrails and human-in-the-loop controls.
Pricing: Community edition free; CAI PRO is EUR 350 a month or EUR 3,990 a year with hosted models; Enterprise on-premises custom.
PentAGI
A self-hosted multi-agent system that carries out penetration testing tasks in a sandboxed environment, written in Go and React and working with several model providers.
Pricing: Free and open source (MIT), self-hosted; users pay their own model costs.
Latest release 2.2.0:
- Reasoning the way each vendor expects it — adaptive thinking, effort levels, thinking budgets, and a real "off" are sent in each model family's native form.
- Three new providers — MiniMax, Mistral, and xAI, for 13 provider types in total. Any other OpenAI-compatible endpoint works through the custom provider, which now also calls Azure OpenAI…
- Tested, not just listed — every built-in provider, plus example configurations for OpenRouter, DeepInfra, Ollama Cloud, self-hosted vLLM, and others, ships with a ctester report in examples/tests/…
- Current catalogues — GPT-6, Claude Opus 5.x and Fable 5.x, Gemini 3.x, Qwen 3.8, GLM 5.3, DeepSeek V4, and Grok 4.7, with prices checked against vendor pages.
CAI (Cybersecurity AI) vs PentAGI: common questions
How do CAI (Cybersecurity AI) and PentAGI prices compare?
CAI (Cybersecurity AI): Free. PentAGI: Free (OSS). Prices come from each vendor's pricing page.
Is CAI (Cybersecurity AI) or PentAGI open source?
PentAGI is open source (MIT); CAI (Cybersecurity AI) is source-available (MIT components plus proprietary additions licensed for research use only).
Which is more popular, CAI (Cybersecurity AI) or PentAGI?
PentAGI has a Gid Score of 29 against 20 for CAI (Cybersecurity AI). The score combines package downloads, editor installs, GitHub activity and attention, updated daily.
Do CAI (Cybersecurity AI) and PentAGI support MCP servers?
CAI (Cybersecurity AI) documents support for MCP servers; PentAGI's documentation does not.