Skip to content
Free Spinifex sandbox. Create a sandbox Your Spinifex account is live. Access your console

We unlocked AWS. Don't stay stuck.

Run AWS workloads on any compute you want. Zero re-write.

Watch the full 59-second introduction
The Spinifex stack

Move all or parts of your workloads to the right compute infrastructure.

AI inference to better GPUs, storage to somewhere cheaper, move the stuff that makes sense to move, leave the rest.

Apps
Your infrastructure & apps
AI training Inference Web & APIs Databases Batch & data
Tooling
AWS Tooling
One portable stack.
Runs the same on a single node, cluster, edge, or air-gapped rack.
Spinifex
AWS Orchestration
EC2
Compute
QEMU / KVM
EBS
Block storage
Viperblock
S3
Object storage
Predastore
VPC
Networking
OVN / OVS
IAM
Identity
SigV4 · policies
EKS
Kubernetes
K8s-conformant
+ ALB · ECS · ECR · RDS and more of the core AWS services See all
OS
Operating System Debian / Ubuntu LTS · systemd · KVM · Linux bridge · Open vSwitch
Hardware
CPU Intel · AMD · ARM
How it works

The cloud you know. Running where you put it.

Same APIs

Nothing to rewrite

The diff is one flag: --endpoint-url. The SDK clients, the Terraform provider and the AMIs you already built carry over untouched.

Your infrastructure

Run it anywhere

Start on a Neocloud partner's fleet, move into your own racks, then push the same build out to a single box at the edge. One platform, every deployment shape.

Open core

Yours to keep

AGPL-licensed and auditable, down to the storage engine. Read the source, run it in production, send us a patch. No vendor can lock you out of the platform your business runs on.

Engineering depth

AWS-compatible APIs. Real compute. Not emulation.

An emulator returns a plausible response. Spinifex boots the machine. A call lands on the gateway, crosses NATS to the daemon that owns the resource, and comes back having launched a QEMU guest, attached a Viperblock volume, or written an erasure-coded object into Predastore. Your software cannot tell the difference, because there isn't one.

Object storage

Predastore

Every object is split into data and parity shards by Reed–Solomon erasure coding and spread across nodes. Lose a disk and the bucket still reads. Rebuilds run online, with no operator in the loop.

Block storage

Viperblock

Volumes sit on a write-ahead log behind an NVMe write-back cache that replays crash-consistently. On our reference rugged hardware that cut p99 write latency by 4–6×.

Compute

QEMU/KVM

Instances are real KVM guests, with PCIe devices passed straight through so GPUs, SDRs and capture cards run at near-native speed. Cloud-init, user-data and SSH key injection behave as they do in EC2.

AWS compatibility

All the AWS services you need on one endpoint. Outpost parity and beyond.

422 AWS API actions, implemented against the real API rather than a mock. The AWS SDK, the AWS CLI and Terraform point at one endpoint, and your workloads run unchanged at the edge, on-premise, or on a partner Neocloud.

Request a service More to come — tell us what you need next.
Spinifex · AWS Orchestration Your hardware · Edge · Neocloud partner
EC2
Compute
Available
EBS
Block storage
Available
S3
Object storage
Available
VPC
Networking
Available
IAM
Identity & auth
Available
ALB / NLB
Load balancers
Available
EKS
Kubernetes
Available
ECR
Container registry
Available
ECS
Container service
Available
RDS
Databases
Available
Route 53
DNS
Available
Bedrock Q4 '26
Foundation models
Lambda Q1 '27
Serverless functions
SQS Q1 '27
Message queues

Roadmap items ship under the same AWS API surface. Code written for AWS today keeps working the moment they land. Track what's shipped in the release notes .

Validated hardware

Validated on partner hardware. Ready to order and deploy.

Each platform here has been through a Spinifex validation on the actual silicon, and the reference architecture and benchmark numbers are published in our docs. The list grows with every vendor we work through.

Rugged edge

Carries the same AWS workload out to sites with no rack and nowhere to put one. A single fanless HX401 runs a complete Spinifex deployment on its own, with no machine room behind it.

Cloud partners

Take your AWS workloads to the neoclouds. Without rewriting a line.

Neoclouds and alternative hyperscalers are where new GPU capacity and new regions are coming online, priced to win workloads away from AWS. Spinifex lets your AWS estate follow that capacity. Install it on OCI, Vultr or Latitude.sh bare metal or VMs, our preferred partners, and you have an AWS API compatible region in an account you control. Your teams keep the AWS CLI, SDKs and Terraform they use today, and code moves across with a new endpoint.

GPU capacity
Partners with accelerators in stock, so training and inference start on your schedule rather than a hyperscaler's quota queue.
Pricing
Compute, storage and egress well below AWS list price, from providers competing hard for your workloads.
Region choice
Stand a region up next to your users, including markets AWS serves thinly or not at all, and move it later with the same Terraform.
Sovereignty
Data and the control plane stay in the jurisdiction that regulates them, in an account where you hold the keys.
Featured partner
Bare metal and VM

Run Spinifex on Oracle Cloud Infrastructure (OCI) from a single bare-metal server or VM up to a fleet of nodes in a redundant, highly available cluster, all inside your own OCI tenancy. Your AWS workloads land there without a rewrite, backed by deep GPU bare-metal capacity, dedicated sovereign regions for government and regulated industries, and egress priced at a fraction of the other large US clouds.

Bare metal

One command brings up Spinifex on single-tenant Latitude.sh bare metal, with deep coverage across Latin America alongside the US, Europe and Asia-Pacific for workloads that have to run in-country. GPU servers come from the same platform, so an AI workload and the services around it land in one place.

Deployments

Your software was built for AWS. That doesn't mean you're stuck in it.

Run it on a partner Neocloud, in your own data centre, or at the edge. The AWS-compatible surface on top is the same.

01 Neoclouds

Lift & shift to a partner

Move workloads off the hyperscalers and onto our Neocloud partner ecosystem, without rewriting them. GPU capacity, cheaper, available now.

Explore neoclouds
Partner capacity. Your AWS tooling.
02 On-premise

Run it in your own DC

Bring your own hardware. Host Spinifex in your data centre with full control of stack, data, and jurisdiction.

Explore on-premise
Your racks, network, and data.
03 Edge

Cloud where the cloud can't reach

Air-gapped sites, vehicles, vessels, factories, clinics. Compute next to the data, running through disconnection.

Explore edge
Compute stays with the workload, even offline.
Free hosted sandbox

Try Spinifex. With one of your own workloads.

Point your AWS CLI or Terraform at a hosted Spinifex environment and watch your own software run. Nothing to install, no card required, credentials in under 60 seconds.