Kelos

Kelos

Run and orchestrate coding agents on Kubernetes.

  How It Works ·
  Quick Start ·
  Usage ·
  Documentation ·
  Contributing

Kelos turns coding agents into Kubernetes workloads. Give an agent a goal and
Kelos provides the repository, credentials, tools, compute, and workflow needed
to complete it.

Use Kelos for one-off tasks, persistent conversations, event-driven
automation, pipelines, and parallel work across many repositories. It supports
Claude Code, OpenAI Codex, Google Gemini, OpenCode, Cursor, and
custom agent images.

  Set up the Kelos Console

Why Kelos?

- Run agents in isolated Kubernetes workloads instead of on developer laptops.
- Reuse the same repositories, instructions, skills, and tools across agents.
- Keep interactive Sessions alive and reconnect from terminal or web clients.
- Trigger work from GitHub, Jira, Linear, cron schedules, or generic webhooks.
- Observe, limit, and operate agent workloads with familiar Kubernetes controls.

How It Works

The controller turns Kelos resources into Pods, Jobs, and StatefulSets.

Core Primitives

Task status records useful results such as branches, commits, pull requests,
and token usage. The resources remain ordinary Kubernetes objects, so advanced
users can review them, keep them in Git, or manage them with existing delivery
tools.

See the API and CLI reference for the underlying fields and
commands.

Quick Start

You need a Kubernetes 1.28+ cluster with
cert-manager installed.

Install the CLI:

Homebrew and source installs are also available:

Install Kelos:

For Helm installations and upgrades, see the
chart documentation.

Install the first-party Kelos skill in your coding agent:

The skill teaches your agent how to configure Kelos, create the right
resources,…