← Latest products

I built a firewall for agents because prompt engineering isn't security

The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence. I’ve been working in DevOps and infrastructure for years (currently in the fintech/security space), and as I started playing with AI agents, I noticed a scary pattern.

Open source

510 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. FireClaw

    github.com

    Open-source proxy defending AI agents from prompt injection

    Hacker News5 pts

  2. AgentTrust

    github.com

    Zero-trust security and human approvals for AI agents

    Hacker News16 pts

  3. Claw Patrol

    github.com

    a security firewall for agents

    Hacker News112 pts

  4. Agent Arena

    wiz.jock.pl

    Test How Manipulation-Proof Your AI Agent Is

    Hacker News47 pts

  5. Tired of duct-taping access control into agent prompts. Here's the fix

    github.com

    Your agent team, on your machine. Open-source harness for multi-user Claude agents.

    Hacker News22 pts