PrismorSec/prismor
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.)
Outside contributors get real replies here, and their work gets merged.
12 of 17outside PRs merged (71%)
checked
Where newcomer work lands
The evidence