Launching today
Relay Security
Block dangerous AI agent actions before execution
1 follower
Block dangerous AI agent actions before execution
1 follower
Most agent security tools filter prompts before they reach the LLM. Relay checks the action instead — sitting between your agent and its tools, validating every GitHub call, shell command, database query, or deploy before execution. Blocked calls return a clear reason. Every decision is logged. Policies update from the dashboard without touching your agent code. Open source, model-agnostic, with optional Docker sandboxing for shell agents.
Relay Security Reviews
Reviews