Quickstart

1. Install Kent server and CLI

Windows

Open PowerShell and run:

irm https://kent.sh/install.ps1 | iex

macOS

Homebrew (Apple Silicon)

brew tap respawn-llc/tap
brew install respawn-llc/tap/kent

Linux

Install script

curl -fsSL https://kent.sh/install.sh | sh

Homebrew

brew tap respawn-llc/tap
brew install respawn-llc/tap/kent

Arch Linux (AUR)

The kent-bin AUR package is community-maintained.

yay -S kent-bin

These versions are not auto-updated. Please keep them updated manually by re-running install scripts.

Check the installed version with: kent --version

2. Install the background service

Note

Kent consists of two apps: whatever client you prefer, and the server. To use Kent, you first need to have a running server. Run kent serve every time, or install a system service once.

If the install script did not install the background service, or you used a package manager, install it below.

Windows

Open PowerShell as Administrator and run:

kent service install

macOS

kent service install

Linux

kent service install

See Kent Server for more info.

3. Install Kent Desktop

The desktop app lets you use Kent’s Workflows and Tasks feature to build agentic graphs and deterministic pipelines to fully automate processes and scale to 10s or 100s of agents.

Manual install

Download the installer for macOS Apple Silicon, Linux x86_64, or Windows x64 at kent.sh/desktop, or install the macOS app via Homebrew:

brew install --cask respawn-llc/tap/kent-desktop

Homebrew installs update through brew upgrade, standalone installs self-update.

Note

The desktop app, due to the asynchronous nature of workflows, needs a server to connect to.

First use

Security Warning

Out of the box, Kent does not ship a sandbox, and does not enforce tool calling permissions. Using Kent is equivalent to running claude --dangerously-skip-permissions or codex --yolo. The model will have full access to your entire computer. By using Kent, you accept full responsibility for what the model does on your computer. If you want to safely run Kent in a real sandbox, see Sandboxing.

Start Kent CLI with: kent. The first run will ask you to pick auth option and walk you through onboarding. The session picker shows when a newer Kent server release is available; update Kent through the installation channel you used.

Supported auth options:

• OpenAI/Codex subscription OAuth via the startup sign-in picker.
• No auth for custom providers. This option supports any provider like ollama, omlx local models, or third-party providers like GLM coding plan. The only requirement is that the provider supports the OpenAI Responses format.

Note

Anthropic or Gemini subscriptions/models will not be supported until these companies allow third-party harnesses in their ToS.

• Press F1 to invoke the help menu.
• Use Enter to steer the model, Tab to queue messages. Slash commands can be queued too!
• Use Shift+Tab to toggle between detailed transcript mode and lean ongoing mode.
• Type $ <command> to execute a shell command and show its output to the model.
• Press Esc twice to enter Edit mode, which lets you go back in time, edit a previous message, and fork the session starting with it. Use Up/Down to walk through user messages. File edits are not rolled back.
• Use the Up/Down arrow keys to select and resend previous prompts.
• Press Ctrl+V/D, Alt+V/D to paste clipboard images or text.
• Use /review to start a code review. After the review finishes, you can use /back to teleport to the original session.
• /name <new-name> will set your session name in the picker and terminal title.
• /autocompaction will toggle compaction, and /compact will trigger one. If autocompact is off, you can go above 100% context usage if model allows it. Going above 100% will cost more and degrade model performance. Repeating /compact before the next model request succeeds without compacting the conversation again.
• Run /status to get detailed info about the session.

For the full command reference, see Slash Commands.

Configuration

Kent reads settings from ~/.kent/config.toml. The full reference is on the Configuration page.

Skills and slash commands

On first launch, the setup wizard can optionally import existing skills and slash-command directories from supported providers.

Kent discovers skills from:

• <workspace>/.kent/skills
• ~/.kent/skills
• <persistence-root>/.generated/skills

You can disable skills for new sessions in config.toml:

[skills]
creating-skills = false

Changes take effect when a session starts or after compaction.

Supervisor

• Use /supervisor to toggle its invocation for the current session. Supervisor is a feature that will automatically review the work done by the model. It increases costs by ~15% (if using the main model) but improves results. By default supervisor uses the same model as the main one. That may be too costly / too slow for you. Configuration page contains instructions on how to change supervisor model.

Advanced

Once you’re comfortable driving the traditional agentic CLI, consider upgrading to workflows.