← Latest products

Doberman

The AI watchdog that stops Claude from deleting your database. Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute. Landing Page: https://www.trydoberman.dev/ The Problem: AI guardrails only protect against 89% of dangerous commands.

Open source

277 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. GuardRail

    github.com

    shell guards that stop Claude Code before it pushes to main

    Hacker News5 pts

  2. A pre-execution guard that stops AI agents running destructive commands

    github.com

    A pre-execution guard that stops your coding agent running destructive commands. One shell file, no dependencies.

    Hacker News5 pts

  3. AgentGuard

    github.com

    Auto-kill AI agents before they burn through your budget

    Hacker News47 pts

  4. A context-aware permission guard for Claude Code

    github.com

    a guard that blocks catastrophic agent actions

    Hacker News127 pts

  5. Retroguard

    retroguard.ai

    Verifiably secure AI guardrails

    Hacker News6 pts