Firewall: filters and an audit log for what your AI agents may do on the internet
Internet requests from agents pass through ZiyaOS. The firewall checks every destination against your rules, blocks everything else and shows every request in the dashboard.
Whatever no rule allows is blocked: calls to your systems as well as targets on the internet. You open only what is really needed.
Rules per agent
Every agent gets its own destinations. The sales agent only reaches your CRM, the research agent selected websites.
Approval in one click
If an agent needs a new target, it asks a human. You allow once, permanently, or block.
External agents too
Claude Code, Codex, Cursor and your own agents work through the gateway with the same rules, the same firewall and Code Mode.
Frequently asked questions
Can I control which websites an agent may access?
Yes, you control which websites an agent may access. Internet requests from agents run through ZiyaOS. You set rules per destination and per agent and require approval where needed. Every request ends up in the log.
How do you make sure the AI doesn't do anything wrong?
We make sure the AI doesn’t do anything wrong with the central Guard: every action an AI wants to take runs through it. Without a rule or explicit approval, there is no access. Every action is logged: who, when, what, why, from where and to where. The same applies to people, apps and workflows.