Pryxor/pryxor

Runtime security layer for AI agents. Intercepts every tool calls, decides and execute the real actions without the agent never hold a credential.

2 best points · 0 comments · 1 Hacker News post · 4 GitHub stars · View on GitHub

Hacker News discussions

• I build an open-source runtime security layer for AI agents – Let's break it (2 points, 0 comments, by makan09, 2026-10-11)