Veto – Intercept dangerous commands before AI executes them
Veto – Intercept dangerous commands before AI executes them
Hey HN, With tools like Moltbot( https://clawd.bot/ ) gaining traction, I got thinking about AI agents executing shell commands with full permissions by default. I built veto to add a safety layer: 1.Intercepts commands before execution 2.Risk-based authentication (Touch ID for critical, simple confirm for low) 3.Custom rules for project-specific patterns 4.Full audit trail Currently supports Claude Code (via hooks). Looking into Moltbot integration but it doesn't expose hooks yet — if anyone has ideas, I'm all ears. Feedback welcome. https://github.com/runkids/veto
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
Redis-GIS – Geospatial and Geofencing Commands for Redis
Wrapper for Executing Commands in Go
Vim-pnpm Bindings for pnpm commands in Vim
TalosPro – AI that executes (not just suggests)
Generate Curl Commands in a Webapp
Bashfs – Run commands as your filesystem
Run synchronous and asynchronous commands in WebDrivers
Jop - J language commands for Ruby
Automate Commands with Go
GitHub Slash Commands