Get started

A plugin for Claude Code

Ask Natterjack.

Where the business meets the codebase.

One dashboard on top of your team’s repos. Engineers start apps and Claude runs from the browser. Product, ops and support ask the code directly, read-only, without waiting on an engineer.

Get started View on GitHub

Free to install · Runs on your machine · v0.6.0

Two audiences, one room

The questions and the code, in the same place.

Engineers get a home base for running things. Everyone else gets a way to ask how things work, and an answer from the code itself.

For engineers

Stop juggling terminals.

  • Start the stack for any worktree with one click, on the right ports, with logs.
  • Run Claude from the browser and answer its questions with buttons.
  • Let a run watch your PRs instead of babysitting them.
  • New laptop? The Machine page lists what’s missing and installs it.
For product, ops and support

Ask the code, not an engineer.

  • Ask how something works and get an answer from the real code, read-only.
  • Bring in Confluence, Notion or Drive through Claude’s connectors. Confluence answers cite the pages they used.
  • A simpler dashboard with the build-and-run pages hidden.
  • No git access? Download a read-only snapshot and ask away.

Fewer “quick question” interruptions for engineers. Faster, first-hand answers for everyone else.

What’s inside

A home base for the whole team.

Natterjack installs a dashboard into your workspace. Here’s what’s on it.

Runs

Start Claude from the browser. Answer it with a click.

When Claude needs a decision, it asks on the page and you answer with buttons. Every run keeps its transcript, its subagents and a Changes tab with a diff of what it touched.

  • “Continue in terminal” hands the session to claude --resume when you want the keyboard back.
  • Plan mode (read-only) is a switch on each run.
  • Limits on concurrent runs, and new runs pause when your plan’s usage window is nearly spent.

Issues

Your tracker, next to the code it’s about.

The team’s board from Linear, Jira or GitHub Issues, with two buttons on every ticket. Other trackers can be added through adapters.

  • Explain answers read-only, against the real code.
  • Implement runs your team’s own /implement skill.
  • Tracker keys stay on the server and never reach the browser.

Apps & Workspaces

Start the whole stack. In order. On the right ports.

Start and stop each app, or a whole stack, for each git worktree, with logs. No more remembering commands and ports, or keeping six terminals open.

  • Stacks start in the order you set: database, then API, then web.
  • Apps keep running when the dashboard restarts.
  • On Windows, no console windows pop up.

Machine

Onboarding in hours, not days.

Natterjack knows what this computer needs for your stack and checks it live: Node, Go, PHP, Python, .NET, Java, Docker, databases and more. Missing something? Click Install.

  • Checks come from your repos’ own version files.
  • Apps that need a missing tool say so on their card.
  • Build tools can be shown to developers only.

Ask

A question box that starts a Claude run against the real code, read-only by default. While you type, a free local search shows the files Claude will start from. With Confluence connected, it searches and cites your pages too.

PR watches

A run can watch its pull requests and wake up for a new review or comment, failing checks, a change in review decision, or a branch that’s behind or conflicting.

Docs, Links, Infrastructure

Team docs from your repos or Confluence, Notion and Drive. Link tiles anyone can add to. Environments, URLs and accounts with click-to-copy values.

Roles

Product, ops and support get a simpler dashboard. Build-and-run pages are hidden, and Implement isn’t available to readers.

Snapshots

People without git access download read-only copies of the code, published by CI, and can still Ask, Explore and read the docs.

And the rest

Search across everything without spending tokens, skills as cards, plan usage limits, memory, and a file explorer.

How setup works

Discovery, not forms.

Run one command in the folder that holds your repos. Claude works out your setup, asks about the gaps, and hands you a dashboard that already knows your stack.

  1. 1

    Discover

    Claude scans your repos: stacks, ports, run commands, databases, CI, deploy targets, ticket keys in your branches, and your design system.

  2. 2

    Interview

    It asks only what it couldn’t work out, in a round or two of questions: which repos, which tracker, which apps run together.

  3. 3

    Brand

    It writes the config and brands the dashboard with your team’s own colors and logo, and checks the contrast.

  4. 4

    Start

    The dashboard starts on localhost. Teammates pull, start it, and the Machine and Repos pages walk them through the rest.

Your copy, your changes.

The dashboard is copied into your workspace and you own that copy. Change anything. When a new version comes out, /agentic-os:upgrade merges it around your changes.

Run it your way

On a laptop, or on your own infrastructure.

Engineers run Natterjack on their own machines. People without a dev machine can use a hosted copy behind your company’s single sign-on. The same workspace serves both.

Local

For engineers

  • Runs on each person’s computer at localhost:3333.
  • Uses the Claude Code you’re already signed in to.
  • Everything in the feature tour above, including Apps, Workspaces and Machine.
Install it

Hosted

For product, ops and support

  • Each person gets their own container behind your single sign-on: Google Workspace, Entra ID, Okta and others.
  • One shared address. A small router starts each person’s container when they arrive.
  • Everyone signs in with their own Claude seat, so their claude.ai connectors just work.
  • Runs on Kubernetes (GKE, EKS, AKS) or a VM with Docker.
Read the hosting guide

Trust and safety

It can start processes. So it’s careful about who can ask.

The dashboard runs Claude and your apps as you, so it only listens to you.

Local and locked down

The dashboard binds to 127.0.0.1 only, with checks against DNS rebinding and other origins, and a per-install token on every POST.

Read-only by default

Ask runs in plan mode unless you switch it off. People on the reader profile never get Implement.

Keys stay put

Tracker keys never reach the browser. Install buttons and app commands come only from config files, never from the page.

One container per person

Hosted mode isn’t a shared multi-user server. Each person gets their own container, disk and Claude sign-in.

Where it’s heading

Claude today. Your choice of model tomorrow.

Natterjack runs on Claude Code today. Much of the dashboard, like Apps, Machine, Docs, Links and the issue board, is plain tooling that doesn’t need a model at all. We want the agent behind Runs and Ask to be your choice too.

Available now

Claude Code

What Natterjack runs on today. Sign in with a Claude subscription, or use an Anthropic API key, Amazon Bedrock or Google Vertex AI.

Exploring

OpenAI Codex

Codex as the agent behind Runs and Ask, for teams that have standardized on OpenAI.

Exploring

Models on your machine

Open-weight models running locally, through tools like Ollama or LM Studio. Nothing leaves the laptop.

Exploring

Models in your infrastructure

Models you serve inside your own network or cloud account, so prompts and code stay where your security team wants them.

“Exploring” means exactly that: ideas we’re weighing, not dates. Tell us what your team would use.

Get started

Three commands to a dashboard.

Install the plugin in Claude Code, then run create in the folder that holds your team’s repos.

You’ll need

The dashboard’s Machine page helps with everything else your stack needs.

View the source on GitHub
1 · In Claude Code
/plugin marketplace add lhoezee/skills
/plugin install agentic-os@lhoezee-skills
2 · In the folder with your repos
/agentic-os:create

The plugin is called agentic-os in Claude Code. Afterwards, /agentic-os:doctor checks everything and /agentic-os:upgrade pulls in new versions.