Skip to content

Getting started#

Install it yourself. The full platform — control plane, sandboxes, database, and audit trail — is one Helm chart, and it runs on a single-node cluster on your laptop as happily as it runs in your data centre.

There is no sales call to book first, no environment to request, and no evaluation key to wait for. Activation is a browser sign-in with a Lens ID you create yourself in a minute.

Pick your path#

  • Try it locally with a coding agent

    Paste one prompt into Claude Code, Codex, or OpenCode. It installs the platform, launches an agent, and hands you both URLs. The fastest way in.

  • Try it locally by hand

    The same result, one command at a time, so you see exactly what lands in your cluster.

  • Install on Kubernetes

    The real deployment: Helm values, ingress, external database, inference providers, and sandbox hardening.

What you need#

  • A machine that can run docker, minikube, kubectl, and helm (v3.8+), with outbound internet.
  • A Lens ID account — sign up at app.k8slens.dev.
  • One inference-provider credential for managed inference — an AWS Bedrock API key, or a Microsoft Foundry resource URL and API key with a Claude deployment.

That is the whole list. Everything else the install brings with it.

What you end up with#

A running platform, and Prism — Lens Agents' ready-made managed agent — answering you in a browser tab from inside a sandbox that has the network denied by default, holds no real credentials, and writes every action it takes to the audit trail.

From there, the governance chain is yours to drive: attach a policy, connect the systems the agent must work with, and watch what it may and may not reach.

  • Core concepts — the architecture, the sandbox isolation model, and the identity model
  • Sandboxes — creating, running, and exposing agents
  • Administration — org policy ceilings, bindings, teams, tokens, spending limits, and audit
  • Security — threat model, compliance posture, and the security whitepaper

If you want a hand#

Self-serve is the main path, and it stays that way. But some things are worth a conversation: an air-gapped install, microVM isolation with a Kata Containers or gVisor runtime class, SSO against your directory, or a policy set that has to satisfy a specific control framework.

Talk to us and we will scope it with you — architecture review, security-model walkthrough, and a production-shaped environment configured alongside your team. Install first if you prefer; the conversation is more useful when you already know what you are asking about.

See also Support for the full set of contact channels.