# AltairaLabs — define, test and govern AI agents across any runtime > AltairaLabs gives enterprises a common way to define, operate, observe and continuously evaluate AI agents across models, clouds and runtimes, while keeping sensitive agent data under their control. Canonical page: https://www.altairalabs.ai/ Standardise agent behaviour, not infrastructure. # A production linefor AI agents. Any team can have an agent running by tonight. That’s the pilot. Production is the hard part: what it’s allowed to do, how you prove it behaves, who’s watching it, and who signed for it. Omnia is the production line that answers all four, for every agent you run, whatever stack it’s on. Your teams keep the stacks they’ve chosen. [Free while you build. Free to run. Enterprise features when you need them.](https://www.altairalabs.ai/pricing) [Run Omnia free](https://omnia.altairalabs.ai) [Talk to us](https://calendly.com/altairalabs-ai/altairalabs-how-can-i-help) ![The Omnia control plane, showing every agent running in a cluster](https://www.altairalabs.ai/images/product/dashboard-dark.png) omnia · your cluster · 16 agents · 27 of 33 converged An invoice queue, a claims backlog, a customer on the phone. One plane over all of it. the bit in between ## A production line does the same five things, whatever’s on it. Nobody’s doing it wrong. Buy a machine and you get a machine. The machines will be different next year. The line is the business. [defines it What it is. What it may do. How you know it’s behaving. One definition, versioned.](https://www.altairalabs.ai/platform)[tests it Before it goes live, and every day after. You can’t read an agent and know what it’ll do. You run it, and you check.](https://www.altairalabs.ai/assurance)[watches it Every call, every tool, one place. Whatever stack it’s on.](https://www.altairalabs.ai/console)[governs it What it can touch. What it can send. Who signed for it.](https://www.altairalabs.ai/governance)[keeps the record When a supervisor asks what happened, the answer’s already written.](https://www.altairalabs.ai/privacy) what you’re buying ## Everything you build here, you can take away. Every quarter brings a new set of tools and a new integration layer to write for them. The usual alternative is one vendor who takes the sprawl away and takes your data with it. This runs in your own infrastructure, and the foundations under it are open. The definitions you write, the tests that prove them and the runtime they execute on are yours to keep. open, and yours to fork [PromptPackthe spec for what an agent is](https://promptpack.org)[PromptArenathe testing](https://promptarena.altairalabs.ai)[PromptKitthe runtime](https://promptkit.altairalabs.ai) four deployerspublic repos, one public interface Omnia is the one part you can’t read the source of. It runs in your cluster, and nothing leaves it. [The licences, in full →](https://www.altairalabs.ai/open-source) how the line is built ## What you approved is what’s running. One versioned artefact: the tools it may call, the models it was tested against, the steps it follows, the checks it has to pass. The agent can’t step outside it, and those checks keep running against the real work. The seven stages run as a cycle: ideate, then define and test against each other until the agent holds, then the pack compiles, then the deploy gate, then the runtime, then live evaluation, whose failures come back as regression cases at define ⇆ test, and it starts again. 01 Ideate 02 ⇆ 03inner loop Define ⇆ test scenarios · personas · self-play · adversarial · duplex voice 04✦ The pack compiles prompts · tools · workflows · skills · requires · evals 05 Deploy gate 06 Run 07 Observe, evaluate, feed it back Live evals, telemetry and audit. A failure becomes the next test case. ## What you’ll want answered before you install anything. [what do my people actually use? One place to build, run and ship. An agent there can be callable, scheduled, conversational or voice, all off one definition.](https://www.altairalabs.ai/console)[do I have to move anything? No. One definition, four targets. Your cluster, AgentCore, Vertex Agents or Foundry, with one console answering for all four.](https://www.altairalabs.ai/run-anywhere)[who may call what? A rule, on every call, in the record. Checked against the identity of the person who asked, on what the agent reads and what it sends.](https://www.altairalabs.ai/governance)[what happens to our data? It stays where you put it. Redacted before the model, before the recording, and again before memory.](https://www.altairalabs.ai/privacy)[does it remember the customer? Four tiers, and a rule about which wins. What the business knows, what the agent learned, and what belongs to one person.](https://www.altairalabs.ai/memory)[how do I know it still works? Because the testing never stopped. The same cases, run again against every model you allow, on a schedule.](https://www.altairalabs.ai/assurance)[what about ten thousand a night? Ten thousand, and no two the same. The user side is simulated too, so every run is a different conversation. Load-test it, evaluate it, or keep what passed.](https://www.altairalabs.ai/scale) design partners ## “Every team is building agents differently, and it’s going to become a mess.” If that’s a sentence you’ve said out loud this quarter, we’d like to hear the rest of it. We work with one or two teams at a time, you talk to the people building the platform rather than to an account manager, and a partner’s terms hold through general availability. Bring the estate you already have. The first conversation is worth having before any of it moves. [Talk to us](https://calendly.com/altairalabs-ai/altairalabs-how-can-i-help) [Or read how the whole thing fits together →](https://www.altairalabs.ai/platform) ## Every feature, in your own cluster, in ten minutes. omnia ❯ helm install omnia oci://ghcr.io/altairalabs/charts/omnia 8 services reconciled · dev licence · every feature \# enterprise features need an agreement once real traffic depends on them [Run Omnia free](https://omnia.altairalabs.ai)no trial period · no time limit · runs in production [No cluster? Start with PromptArena, the open-source tester →](https://promptarena.altairalabs.ai)