Frequently asked questions
From the manual
Are open models really good enough?
For well-scoped internal workloads, yes. We prove it on your own data during the audit before you commit to a build.
What if we already pay for ChatGPT seats?
Keep them for ad-hoc use. Agents on your own compute are for the high-volume work where the meter hurts.
We only have 15 staff. Too small?
Not at all. A single-agent build on one workstation is a common first project.
Can we host in our existing cloud account?
Yes. Your VPC, your tenancy, your keys.
What happens if AgentOS 98 disappears?
You keep everything: code, models, hardware and docs. That is the point.
The basics
What is AgentOS 98?
A complete service: we design the agent, spec the hardware, deploy it inside your infrastructure, and hand it over. Docs, training and keys included — you own the lot.
What is an agent stack?
The model, the compute, your data sources, and the guardrails — all running on hardware you control, from a workstation under a desk to a rack in a local datacentre.
Why self-host instead of an API?
API bills grow with usage, seats, and model upgrades. Self-hosting puts a fixed-cost GPU in your office or cloud — your prompts, documents, and models never leave your infrastructure. No per-token meter, no surprise invoices, no data offshore.
How does it save money?
You replace metered API bills and manual back-office work with a fixed-cost GPU. Invoices, reports, support tickets, and scheduling drafts happen automatically — so your team spends time on work that actually moves the business forward.
BOOK A WORKLOAD AUDIT
Book a 45-minute workload audit. We'll map where agents genuinely pay off, what the hardware costs, and if it's not the right move, we'll say so.