Prismor
Runtime security control plane for AI agents
Visit prismor.dev ↗What is Prismor?
Prismor is an open-source security layer that intercepts and controls every tool call made by AI agents before execution. It enforces security policies, blocks destructive actions, masks secrets, and maintains a full audit trail. The platform works with Claude, Codex, LangChain, CrewAI, and other agent frameworks.
Designed for enterprises running autonomous agents, Prismor addresses risks like prompt injection, unintended destructive commands, secret exfiltration, and supply chain attacks. It provides a local dashboard for monitoring agent activity, policy-as-code configuration, and observe-or-enforce modes. The project is built with tools including Claude Code, Codex, and Cursor.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Prismor automatically. Evidence: GitHub PrismorSec/prismor; repo has .claude, .codex, .cursor. View source.
Similar vibe-coded apps
IDE to orchestrate multiple coding agents in one workspace
AI framework that injects project specs into coding agents across 20+ platforms
Production-grade multimodal AI model for video and audio generation
Local-first AI agent workspace with desktop GUI and terminal TUI
Prescriptive methodology and agent skills for spec-driven development with AI
