Introducing SkaiBridge

Your infrastructure,
bridged to AI.

SkaiBridge puts a secure relay agent on every server you own and connects them to AI-powered automation. No VPN. No credential sprawl. No compromises.

Any AIModel-agnostic by design
ZeroCredentials ever leave your network
100%HMAC-authenticated relay
Scroll
The Problem

AI needs access to your infrastructure.
Your infrastructure needs to stay secure.

Traditional approaches to AI infrastructure access involve sharing SSH keys, exposing management APIs, or piping everything through third-party clouds. SkaiBridge solves the trust problem without the risk.

Zero credential exposure

Agents authenticate via HMAC-SHA256. No SSH keys, no API tokens, no passwords leave your network. The control plane never holds your secrets.

Multi-tenant by design

Strict tenant isolation at every layer - database, API, and agent key namespacing. One control plane, many customers, zero crossover.

Allowlist-enforced execution

Every command passes through a profile-gated allowlist before execution. Standard, power-user, and unrestricted profiles. Destructive commands are always blocked.

Cross-platform agents

Native agents for Linux and Windows Server. Linux agents run bash. Windows agents run PowerShell with WinRM support for remote hosts.

Self-healing agents

Agents heartbeat to the control plane and self-update their executor via Gitea. If a process dies, PM2 or node-windows respawns it automatically.

Full audit trail

Every command, every agent, every tenant - logged. Per-agent audit logs locally and surfaced in the central dashboard for compliance and forensics.

Model-agnostic by design

SkaiBridge isn't married to one AI vendor. Point it at Claude, GPT, Gemini, Grok, or a fully local open-weight model - the relay, the guardrails, and the audit trail work identically no matter which model is doing the reasoning.

The AI never acts alone

The model reasons over your logs - it doesn't get to freelance. Even where automated response is enabled, execution runs through a fixed, human-approved template against a narrow allowlist you control, never a command the AI wrote itself. Anything outside that allowlist stops for a human to approve before it touches a system.

Coming in v1.1

Self-learning dependency mapping

Agents keep a rolling history of what they're actually talking to on the network. When something breaks, SkaiBridge diffs current connections against that recent history to surface which dependency just disappeared - so an investigation starts from a short list of likely culprits instead of a blank slate, cutting time to root cause.

Pricing Tiers

Two ways to bridge your infrastructure

Start with VFR for monitoring and automation. Upgrade to AutoPilot when you are ready to put AI in the loop.

VFR
SkaiBridge VFR
Relay without the AI overhead
  • Unlimited relay agents
  • Multi-tenant control plane
  • HMAC-authenticated relay
  • Allowlist-enforced execution
  • Linux + Windows agents
  • Full audit logging
  • Dashboard and agent management
  • LLM integration
  • AI-driven automation
  • Token metering
Request Access
AutoPilot
SkaiBridge AutoPilot
AI in the loop, infrastructure still yours
  • Everything in VFR
  • Any LLM - Claude, GPT, Gemini, Grok, or your own local model
  • Events console with full detection lifecycle - open, acknowledged, remediated, closed
  • On-demand AI root-cause insight for any detected event
  • Allowlist-gated auto-remediation for known failure patterns (rule-based, model never in the decision loop)
  • One-click ticket creation into your existing ITSM
  • AI-driven automation workflows
  • Natural language to shell
  • Per-tenant token metering
  • Consumption-based billing
  • MCP server integration
  • Optional on-prem Gateway for zero-egress / air-gapped deployments →
Request Access

Pricing announced at GA. Early access customers receive founding rate lock.

On-Prem & Air-Gapped

Some infrastructure can never touch the cloud.
SkaiBridge Gateway doesn't ask it to.

The SkaiBridge Gateway is a self-hosted inference appliance that runs the AI reasoning layer entirely inside your network - connected or fully air-gapped. Built for regulated, classified, or security-conscious environments where sending logs and infrastructure data to SkaiBridge Control Plane isn't an option.

Zero data egress

In air-gapped mode, nothing leaves your network - not prompts, not logs, not infrastructure data. Model and configuration updates move by signed, checksummed bundle instead of a live connection.

Two deployment modes

Run connected, with the gateway pulling signed updates over the network, or fully air-gapped, importing the same signed bundles by physical media. Mode switching is a deliberate, audited action - never a silent toggle.

Open-weight, non-adversarial model

The Gateway runs Mistral, an Apache-2.0-licensed model from a French company with no adversarial-government ties - not a black-box API call to a vendor you're asked to trust blind.

Signed, verifiable updates

Every model and configuration update ships as an Ed25519-signed bundle with atomic apply and rollback. If a bundle doesn't verify, it doesn't install - proven in production, not just on paper.

The same guardrails, enforced locally

Allowlist enforcement, rate limiting, and full audit logging run on the gateway itself - the exact same trust model as cloud-connected SkaiBridge, just with nothing leaving the building.

Built for uptime

GPU-tier appliances pair with a CPU-tier standby for automatic failover, health-checked at the inference engine itself - not just a ping. Dual-GPU HA is available for workloads that can't tolerate degraded throughput.

CPU Appliance
Standard Gateway
Right-sized for focused fleets
  • Runs entirely on commodity server hardware - no GPU required
  • Same Mistral, Apache-2.0 model as every other tier
  • Best fit for smaller fleets or lighter concurrent load
  • Doubles as the automatic failover node in a GPU-tier HA pair
GPU Appliance
Performance Gateway
Built for concurrency at scale
  • Datacenter-class GPU for high-concurrency inference
  • Same model, same answers - the GPU buys throughput, not a different brain
  • Recommended for larger fleets, multi-user workloads, or busy detection pipelines
  • Optional dual-GPU HA for zero-degradation failover

Hardware sizing depends on fleet size and concurrency needs. Talk to us and we'll help you pick the right tier.

Architecture

Simple relay. Serious infrastructure.

🤖
Claude / ChatGPT / Gemini / Grok / Others
HMAC-signed request
SkaiBridge Control Plane
Relay + allowlist check
💻
Agent (your server)
01

Install the agent

One command deploys a SkaiBridge agent on any server. The agent registers with your control plane tenant and starts heartbeating immediately.

02

Define your allowlist

Commands are gated by profile - standard, power-user, or unrestricted. Destructive operations are always blocked. You control exactly what the agent can and cannot execute.

03

Connect AI (AutoPilot)

With SkaiBridge AutoPilot, AI models communicate through the relay. Natural language becomes allowlist-validated shell commands with every token tracked and every action audited.

04

Monitor from the dashboard

Fleet health, agent heartbeats, command history, and token consumption in real time. Multi-tenant - each customer sees only their own infrastructure.

About Relay Labs

Built by infrastructure engineers, for infrastructure engineers.

Relay Labs LLC was founded by a team of systems architects and systems engineers with deep roots in managed cloud, enterprise data center operations, and large-scale systems engineering.

SkaiBridge is the product we wished existed when we were managing hundreds of servers and needed AI tooling that could actually touch the infrastructure - safely, auditably, and without handing over the keys to the kingdom.

We operate our own managed cloud at CyrusOne DUR1 in Durham, NC. SkaiBridge runs in production on our own servers before we ever ask you to trust it with yours.

HeadquartersRaleigh, NC
Founded2026
Infrastructure experience30+ years
Data centerCyrusOne DUR1
Early Access

Be first to bridge your infrastructure.

SkaiBridge is in active development and accepting early access requests. Founding customers get a rate lock, direct engineering access, and input on the roadmap.