Markets
Plow Latch Launched an Adversarial LLM Gatekeeper That Sits Between Your Agent and Your Mac
Plow Latch hit #7 on Product Hunt today selling scoped desktop control for AI agents: the agent gets only the tools and credentials it needs, data stays on the machine, it can run fully locally, and a second adversarial LLM watches for the agent going rogue. The related Latch product at runlatch.sh sells terminal-first policy enforcement, runtime authorization and audit trails for Claude Code, Codex and OpenClaw with per-session scoping, so production repos lock down while prototyping stays permissive. Agent least-privilege is becoming a paid product category rather than a config file.
Source
↳ Follow the thread