17 open-source offensive AI security frameworks: Cairn hits 4.9k stars
evilsocket · x · 2026-11-08
Security researcher fr0gger curated a list of 17 offensive-AI / autonomous pentesting frameworks worth watching, including Cairn, CyberStrike, PentAGI, PentestGPT, VulnBot, Strix, HexStrike AI and hackingBuddyGPT. Cairn (4.9k GitHub stars, AGPL-3.0) is a general-purpose AI state-space search engine validated first on autonomous penetration testing, defining no roles or workflows — given an origin state it searches for solutions itself. The thread started from ShanHolo asking which offensive AI frameworks the security community should watch beyond Artex.
More from coding & agent
- Engineer's data: 11x more merged PRs per month at AI-native Tano vs pre-AI PostHog — bibryam · 2026-11-08
- Anthropic's Official claude-quickstarts Repo Nears 20k Stars for Claude API Developers — anthropics · 2026-11-08
- Working With AI: Getting Better Results by Being 'Dumber', Not Smarter — glcst · 2026-11-08
- Dev Built a Claude Code Limit Widget With Claude Code Writing 130 of 160 Commits — Fade97 · 2026-11-08
- Curated X lists of the Claude Code and Codex teams to follow the builders directly — bibryam · 2026-11-08
- CS student shares permission design principles for agents that touch real files — ASK-1T · 2026-11-08