Show HN: Prempti – Guardrails and observability for AI coding agents

Category: security

Tags: ai-agents, guardrails, observability

Score: 6.8/10 (Innovation: 7, Technical: 6, Documentation: 7, Utility: 7)

Prempti brings Falco's runtime security to AI coding agents by intercepting tool calls and applying customizable guardrails (allow/deny/ask) with full audit logging. It's interesting because it addresses the growing need for visibility and control over autonomous agent behavior on developer machines, offering a cooperative policy layer that agents can understand and respect.

Target audience: backend devs, devops, security engineers

Repository: https://falco.org/blog/introducing-prempti/ · Rust · Apache-2.0 · 19 stars

View on Hacker News