GPU compute,
signed unsigned
complexity.
A Kubernetes-native AI/ML platform. Deploy inference endpoints and training jobs on GPU clusters with scale-to-zero, zero-trust networking, and no vendor lock-in — every layer is open source and replaceable.
Resolving model registry...
✓ Image pulled from Harbor (cached)
✓ GPU pool: 8x A100-80GB MIG (3g.40gb partitions)
✓ Autoscaler: KEDA + Kueue (0 → 8 replicas)
✓ Network: Cilium eBPF + WireGuard mTLS
✓ Endpoint: llama-70b.unsigned.gg
✓ Deployed. Scale-to-zero active. First request wakes in ~4s.
$
Infrastructure that gets out of your way.
Scale to zero, scale to thousands
KEDA + Kueue autoscaling with MIG-isolated GPU partitions. Pay nothing when idle. Burst to full cluster capacity on demand. No cold-start tax beyond the first request. Replica counts are unsigned — there is no going below zero.
Zero-trust by default
Cilium eBPF dataplane with WireGuard-encrypted pod-to-pod traffic. Network policies enforced at the kernel level. mTLS everywhere, no sidecars.
Full observability stack
Prometheus, Grafana, Loki, and Tempo pre-configured. Cluster utilization, distributed latency traces, and cost dashboards out of the box. Alert on what matters.
Secrets & policy as code
OpenBao for secrets management, Kyverno for admission control, SPIRE for cryptographic workload identity, and External Secrets Operator syncing credentials. Nothing hardcoded, ever.
GitOps everything
ArgoCD manages the full stack. Every change is a pull request. Every deployment is auditable. Rollback is a git revert.
OpenAI-compatible endpoints
NVIDIA Dynamo + Triton inference serving. Drop-in replacement for the OpenAI API — bring your own models or pull from the registry. One endpoint, any framework.
Production-grade, opinionated stack.
Every component is open source. The platform is the integration, not the lock-in.
From request to inference.
Every layer is replaceable. No proprietary glue. Fork the stack and run it yourself.
Pay for compute, not complexity.
There is no rate card, because there is nothing for sale. unsigned is the platform we run cerebral on, and these are our own books — kept open on purpose. GPU clusters are not cheap; running them well is the craft. Every layer is open source, and what we fix goes back upstream. Villains keep secrets. We publish the bill.
- ✓ GPU-seconds metered, per-second
- ✓ Idle fleet costs $0 — scale-to-zero
- ✓ Egress isn't a profit center here
- ✓ Observability is load-bearing, not an add-on
- ✓ Nobody pays per seat — there are no seats
- ✓ Every layer open source — we can leave too
The whole operation: 12 boxes · cpu pool 12 · gpu pool 0 · k8s v1.37.0. Published because we have nothing to sell you — transparency is cheaper than marketing.
Bare-metal Talos · Vultr ewr
CPU pool · 12 dedicated nodes
GPU · rented A100/H100 colo path
0x05 · Access
There is no list.
unsigned is not a platform company. It's the platform we built for ourselves, documented like a dataroom. If you're a founder auditing how we operate: the architecture above, the books above, and /learn are the real thing, not the brochure.
Ask Anythingopens your mail client — questions answered, nothing sold
→ customers: 0x0 — none, by design
→ operators: cerebral
→ auditors & the curious: welcome
→ sales inquiries: returns ENOSYS