Agyn

Agyn is the open-source management layer for AI agents — it takes agents off employee laptops and runs them safely across the whole organization. Every agent runs in an isolated sandbox. Secrets stay hidden from the model. Each team gets its own spend cap, role-based access, and a complete audit trail. Works with any agent (Claude Code, Codex, custom builds) and any model. Self-hosted or cloud. Built for the moment AI stops being a side project and starts touching production data — when security, finance, and IT need real controls before they say yes. Non-technical teams get agents they can actually use. Engineering keeps oversight. Finance sees every dollar spent on tokens. IT stops worrying about shadow AI. If your company is moving from agent experiments to agents in production, Agyn is the layer that makes it possible.

Agyn is a self-hosted AI agent platform designed for safely running agents in a company. It facilitates the operation of AI models like Claude Code and Codex on Kubernetes, ensuring isolated environments for each agent. The platform addresses security vulnerabilities by preventing credential exfiltration and intrusion through controlled access and egress rules. Users deploy agents on their Kubernetes cluster using a Helm release. Agents operate in isolated environments with access control and egress rules. The platform records all interactions, allowing for tracing and monitoring of agent activities. Users can choose which AI model to run and manage agent permissions through a console interface. Agyn is targeted at companies that require secure and efficient management of multiple AI agents. It is particularly suitable for teams looking to integrate AI functionality into their workflows while maintaining strict security and access controls. The platform is built for organizations that want to leverage AI without compromising on safety.