Turnkey on-prem AI inference boxes for regulated SMBs. Run sensitive workloads locally with full audit trails and compliance guardrails — while intelligently routing everything else to AWS Bedrock for speed and cost savings.
Hardware we're shipping now
Air-cooled, office-friendly designs. No liquid cooling, no data center required. Built with Supermicro and Dell hardware, powered by NVIDIA and AMD GPUs.
Entry Box
$39k–$45k
Pilot price — includes setup + 1-day vibe-coder workshop
Form factors
Small law firms, dental practices, K-8 schools, or solo practitioners
Best for teams of 10–30 users
Mid Box
$89k
Pilot price — includes setup + 2-day workshop + first-app sprint
Form factors
Mid-size law firms, healthcare clinics, school districts, or manufacturers
Best for teams of 20–60 concurrent users
Why teams choose GenTrellis
GenTrellis combines on-prem sovereignty with intelligent cloud routing, hands-on enablement, and compliance guardrails that regulated SMBs actually need.
Sensitive workflows — contracts, patient notes, student data, PLC code — never leave your network. Your data stays on infrastructure you control.
Hardware is paid once. The intelligent router fills spare GPU capacity automatically. Most customers break even in 4–9 months vs. pure cloud.
See the full comparison→We don't just ship hardware — we teach your vibe coders how to build secure internal apps using smol-agent, RAG, and guardrails.
Developer enablement→Start with an Entry box and add Mid or Enterprise units as you grow. Seamless Ray clustering. Bedrock resale gives flexibility.
“GenTrellis sees nothing — ever.”
Your data. Your policies. Your audit trail.
Protection levels
Some workflows need more than privacy. They need rules about what the AI can see, say, retrieve, and do. Choose the right level for each workflow.
Source-grounded with PII detection and content policy
“What is our refund policy for students who withdraw mid-semester?”
Based on the student handbook, students who withdraw before the census date receive a full tuition refund. After census date, refunds are prorated: 75% in weeks 3-4, 50% in weeks 5-8, and 0% after week 8. The withdrawal form must be submitted to the Registrar's office.
Built for your industry
Each vertical is tuned to the buyer pain, sensitive data, and workflow language that matters in your market.
For Engineering Firms
Make your firm's hard-won engineering knowledge reusable with a private AI knowledge engine you control. Help junior staff work more like senior staff with grounded answers from project files, reports, and process and safety knowledge.
Explore this vertical →
For Law Firms
Turn prior matters, internal research, templates, and drafting knowledge into a private AI knowledge engine your firm controls. Help associates get grounded answers and better first drafts, safe for privileged and sensitive legal work.
Explore this vertical →
For Medical Practices
Turn SOPs, admin workflows, compliance materials, and internal operating knowledge into a private AI knowledge engine your organization controls. Help staff get grounded answers and better workflow guidance, safe for sensitive operational knowledge.
Explore this vertical →
For Schools
PlayTrek gives schools a GenAI-assisted learning and workflow platform, with GenTrellis underneath as a private AI knowledge engine designed for FERPA-sensitive environments and school-controlled deployment.
Explore this vertical →
How it works
Choose Entry or Mid hardware. 50% deposit secures your Q2 2026 delivery slot.
On-site or remote setup, data connection, and a hands-on vibe-coder workshop to build your first apps.
Sensitive work stays local with protection levels. The router handles the rest through Bedrock automatically.
What's included
Not just hardware. Setup, training, software stack, and support — everything your team needs to ship production AI apps.
We configure your box, connect your data, and validate everything works before we leave.
1–2 day hands-on workshop where your team builds production apps on your own data using smol-agent and local RAG.
Learn more about workshops→Sensitivity-based tiering routes sensitive work locally and everything else to Bedrock — automatically.
vLLM inference, smol-agent multi-agent harness, local RAG, NeMo Guardrails, and policy engine — ready to go.
Developer details→Priority support plus audit-ready logs from day one. We're available while your team ramps up.
Reserve your Q2 2026 delivery slot with a 50% deposit. Balance due on delivery.
For developers & vibe coders
GenTrellis exposes an OpenAI-compatible API your team can vibe-code against. Unlike Claude Code, your solutions run against local endpoints with protection levels, RAG, and multi-agent crews built in. We include hands-on workshops to get your team shipping production apps on day one.
FAQ
Reserve your pilot
Reserve your pilot box starting at $39k with a 50% deposit. We'll set up your hardware, connect your data, and train your team.