Cencurity is a security gateway that proxies LLM/agent traffic and detects / masks / blocks sensitive data and risky code patterns in requests and responses, while recording everything as Audit Logs.
Hi Product Hunt! I’m one of the makers of Cencurity.\n\nAs we started shipping LLM agents, we realized traditional app security doesn’t cover agent behaviors: prompt injection, unsafe tool calls, data leakage, and “invisible” actions with no auditability.\n\nCencurity helps teams add guardrails + audit trails for agent actions in production.\n\nWould love feedback—what’s the scariest failure mode you’ve seen with agents, and what integrations would you want next?
Congrats on the launch @vlad1323! Love the audit logging approach, crucial for enterprise adoption. How are you planning to reach security teams who'd champion this internally?
Small technical note for builders interested:
Cencurity runs as a proxy in front of OpenAI-compatible APIs and inspects both inbound tool calls and outbound responses in real-time.
It can block dangerous code patterns before execution and keeps full audit logs for every policy match.
Everything runs locally via Docker, so teams can self-host without sending data to external services.
park