──No Cold Starts

──Scale pods to zero without unscheduling, and wake or migrate them instantly.

──Architect eliminates the tax on idle capacity with no code changes or complicated analytics suites.

Kubernetes scheduling flow diagram

> Tired of Performance Insurance?

Most clusters are deployed with extra capacity so that services are available when needed or to accommodate a traffic spike. This over-provisioning is expensive and wasteful.

Architect gives you zero-overhead pod snapshots and keeps pods scheduled and "running" in Kubernetes upon sleep. On wake, it eliminates delays associated with PVC mounts, load balancer registration, Kubernetes scheduling and software startup times associated with enterprise and stateful workloads so applications and services are available immediately.

Architect eliminates the need for over-provisioning and allows you to:

Hibernate any pod in place and wake it without cold starts in <50ms.

Use spot to deploy pods without service disruption upon pre-emption.

Move any pod anywhere with state integrity and without service interruption.

# How Architect works

Pod hibernation might seem simple, but waking one instantly is complex enough to be approaching magic. Waking a pod anywhere requires you to maintain complete state, reattach dependencies and maintain network connectivity. Fast and transparent.

We refer to Architect as a Kubernetes Availability Automation because it does all of this with a quick and simple install:

├─1.
Deploy Architect

With a simple change to your deployment and ZERO code modification, you can employ Architect on any cluster for any pod.

├─2.
Architect gives you continuous state capture

The state of every pod in your cluster will be efficiently captured and ready to be “re”deployed or saved for hibernation.

├─3.
Hibernate pods, but keep them scheduled

Architect will automatically sleep any pod. Sound dangerous? We give you the ability to tune how Architect behaves based on your needs.

└─4.
Wake up your pods, rehydrate and reconnect them instantly

Upon wake, Architect instantly restores the pod with complete state and it is immediately ready, complete with network connectivity all in under 50ms.

● ● ●
loopholelabs — -zsh — 90x25
Acme App
/~\ Architect
# Install /~\ Architect with one command
$ helm install architect architect/architect
# Watch your workloads hibernate automatically
$ kubectl get pods
--------------------------------------------------------------------
NAME STATUS CPU MEMORY
--------------------------------------------------------------------
frontend-7d4b8c6-x9k2 Running 0m 0Mi # <- hibernated
api-server-5f7c9d-h3j7 Running 95m 512Mi # <- active
ml-model-8c9d2f-p4m8 Running 0m 0Mi # <- hibernated
--------------------------------------------------------------------
# First request wakes the pod in <50ms
$ curl frontend.example.com Response: 200 OK (47ms) # <- instant
wake, no cold start
--------------------------------------------------------------------

Architect magic: Pod network migrations without pause and without custom CNI

Architect employs dynamic real time routing and doesnt require custom CNI plugins or need some complex setup. It elegantly migrates connections using our eBPF network layer and maintains universal compatibility with any cluster.

Compatible with Tigera, Cilium, and AWS VPC CNI

! Let Your Cattle Sleep Standing Up

While you could manually put a pod to sleep, it is inefficient and requires manual intervention and modification of your code in order to capture state.

OLD WAY ~ MANUAL /

Code modification.
Manual offload of state to external storage.
Checkpointing limits full image.
Loss of data.
Startup time in seconds.
Network migration with custom CNI and not instant.

NEW WAY ~ WITH ARCHITECT /

No code mods, simple install.
Automated, efficient capture of state.
Full image integrity checked.
No loss of data.
Startup time < 50ms.
Instant network connectivity with dynamic real time routing.

/ Works the way you work

Architect works with all your standard Kubernetes configurations and cloud native technologies and you can try it today by following our quick start.

Save as you scale

Scale idle workloads to zero, gaining better bin-packing and cost savings.

Eliminate startup time

Pods start immediately as you need them. Even complex enterprise workloads.

Kubernetes native

Architect follows the same patterns and exposes primitives the way you already work.

Architect integrates with Valkey, Kafka, PyTorch, vLLM, NVIDIA and deploys to any cloud

> Get started: Run the way you run today

Its easy to get started with Architect. It requires no code modification or complex analytics tooling. Just a helm install and labels and you are ready to rock.

󰆾

Build your containers with standard tooling and deliver them without code modification.

󰦕

Deploy with a simple helm chart on any infrastructure including spot instances, on nearly any cloud.

󰆾

Hibernate or move your pods anywhere to optimize for utilization or cost, without interruption.

   AAA    RRRRRRRR   CCCCCC  HH     HH IIIIII TTTTTTTT EEEEEEE  CCCCCC  TTTTTTTT
  AA AA   RR     RR CC    CC HH     HH   II      TT    EE      CC    CC    TT
 AA   AA  RR     RR CC       HH     HH   II      TT    EE      CC          TT
AA     AA RRRRRRRR  CC       HHHHHHHHH   II      TT    EEEEEE  CC          TT
AAAAAAAAA RR   RR   CC       HH     HH   II      TT    EE      CC          TT
AA     AA RR    RR  CC    CC HH     HH   II      TT    EE      CC    CC    TT
AA     AA RR     RR  CCCCCC  HH     HH IIIIII    TT    EEEEEEE  CCCCCC     TT