Show HN: Korveo – a local firewall for AI agents
Korveo is a local firewall designed for AI agents, providing comprehensive monitoring and protection against potential threats. It offers real-time tracking of AI actions and decision-making processes, ensuring that harmful activities are blocked before they occur. The system operates entirely locally, requiring no external accounts or data sharing.
- ▪Korveo allows users to observe and govern AI agent operations with universal tracing and a policy engine.
- ▪The firewall includes multiple detection methods to defend against various threats, including prompt injections and PII leaks.
- ▪It is designed to be resilient, ensuring that the AI agent continues to function even if the Korveo system experiences downtime.
Opening excerpt (first ~120 words) tap to expand
Quickstart · Four Pillars · Integrations · OWASP Guardrails · Discussions See everything your AI agent does — and stop it before it does something catastrophic. A full trace of every LLM call, tool, and decision, plus a real-time firewall that blocks credential exfil, cross-tenant leaks, and destructive tool calls. 100% local. No account, no API key, no data egress. One command. pip install -U korveo korveo quickstart # API + dashboard + starter policies, zero config korveo demo # watch the firewall block a live attack (~30s, no keys) korveo demo instruments a real agent, then prompt-injects it into wiping data and stealing credentials — and you watch the firewall block it live, on your machine. ~30 seconds, no keys.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.