CAI (Cybersecurity AI) vs PentAGI
CAI (Cybersecurity AI) (Alias Robotics) and PentAGI (VXControl) side by side on public data, as of Oct 6, 2026.
PentAGI has 2.6x the GitHub stars of CAI (Cybersecurity AI) (25.3K against 9,847). PentAGI shipped 1 stable releases in the past 90 days.
Side-by-side numbers
| Metric | CAI (Cybersecurity AI) | PentAGI |
|---|---|---|
| Pulse Score | 10 | 30 |
| Overall rank | #210 | #133 |
| Downloads, last 7 days | 686 | — |
| Downloads, 7-day change | up 58.8% | — |
| Downloads, 30-day change | down 46.7% | — |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 9,847 | 25.3K |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 0 | 0 |
| Latest stable release | — | 2.2.0 · yesterday |
| Stable releases, 90 days | 1 | |
| Terminal-Bench (best run) | — | — |
| Price | Free | Free (OSS) |
| License | MIT | |
| First released | April 2025 | January 2025 |
| Interfaces | — | — |
| Models |
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. Combinations a vendor would reject are…
- 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. Agent chains are compacted to the…