Paper Overview
Research Area: AI Authors: Nikita Benkovich, Vitalii Valkov Published: 2026-05-28 arXiv: 2605.27575
Abstract
As organizations move toward production deployments of AI agents, which execute non-deterministic workflows, maintain stateful sessions, and often operate with privileged access to internal services, the engineering challenge shifts from building individual agents to operating them at scale with proper isolation, governance, and security. In this paper we present Agyn, an open-source platform designed around three key principles tailored for agent workloads:
1. A signal-driven, stateful serverless runtime on Kubernetes — providing scalable, on-demand execution for agent workloads while preserving session state. 2. A Terraform provider for agent and harness definition — enabling infrastructure-as-code workflows for deploying and managing agents. 3. A security model grounded in zero-trust and least-privilege principles — addressing the risks of agents operating with privileged access to internal services.
Agyn is agent-agnostic, model-agnostic, and cloud-agnostic.
Key Takeaways
- Focuses on operating agents at scale, not just building individual agents.
- Combines Kubernetes-based serverless runtime with declarative infrastructure via Terraform.
- Emphasizes security as a first-class design principle for production agent deployments.