PrismorSec/immunity-agent

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

11 best points · 2 comments · 1 Hacker News post · 479 GitHub stars · View on GitHub

Hacker News discussions

• Your .env is safe but your ~/.claude is not (11 points, 2 comments, by noobcoder, 2026-04-07)