Launching today
Aegisora
The narrow control plane for AI agent tool and API calls.
46 followers
The narrow control plane for AI agent tool and API calls.
46 followers
Stop selling abstract "AI safety". Enterprises buy operational control. Aegisora is an open-source, zero-latency proxy layer built for AppSec teams. Intercept malicious LLM actions, enforce least-privilege API access, mask PII on the fly, and generate readable audit logs for autonomous agents—without the bloated middleware.
Aegisora
Hey Product Hunt community! 👋
As we transition from simple chat interfaces to fully autonomous AI agents handling core enterprise workflows, a massive blind spot has emerged: runtime security.
While building Aegisora, our goal was simple—give engineering and security teams absolute visibility and zero-trust control over what their AI agents execute in production. From blocking semantic prompt injections to stopping unauthorized API calls and PII leaks, Aegisora acts as the secure proxy layer for the agentic era.
I'd love to hear how your teams are currently handling runtime guardrails and API safety. Let's discuss in the comments below! 👇
🔗 It's fully open source (MIT licensed) — check out the code or grab a "good first issue" if you'd like to contribute: https://github.com/ozereray/aegisora.ai
💬 Come chat with the community on Discord: https://discord.gg/8CM3PpQRT5