FREN
Sign inGet started
Orchestrate · Review · Ship

Manage your AI agents like a tech lead

Run 6 agents in parallel, review their diffs, send your notes straight back, then commit and open the pull request — all in one window.

Try free for 7 daysSee all features
6
agents in parallel
3
CLIs supported
€3
per month, everything included
Features

One loop, from prompt to pull request

Launch several agents, review their diffs, send notes back, commit. Everything else in the app serves that loop.

  • Multi-agent grid

    Up to 6 agent terminals in a configurable grid or tabs, reorderable by drag & drop.

  • Real-time diffs

    See every file each agent touches live — full view or diff, inline or side-by-side, editable.

  • Review notes

    Annotate an agent's changes and send your notes back to it to address in one click.

  • Agentic Kanban

    A Kanban board exposed to agents over a local MCP server so they self-coordinate on tasks.

  • MCP Marketplace

    Browse and install MCP integrations into your agents without leaving the app.

  • Commit & Pull Request

    Commit and open PRs from the app, with AI-generated messages and descriptions.

  • Conversation history

    SQLite-backed full-text search across every past session, with resume support.

  • Multi-CLI

    Claude Code, OpenAI Codex and Google Gemini — pick the CLI and model per task.

Orchestrate

Six agents, one window

Stop juggling terminal tabs. Launch Claude Code, Codex and Gemini side by side in a grid or tab layout, reorder them by drag & drop, and keep every parallel workstream in view.

  • Configurable grid (1–6 panes) or tabbed layout
  • Per-terminal live status: working, waiting, idle
  • Pick the CLI, model and project when you spawn a terminal
Review

Diffs and review notes that flow back to the agent

A real-time diff panel shows exactly which files each agent modifies. Read the full file or the diff, inline or side-by-side, edit on the fly — then annotate lines and send your notes straight back to an agent to fix.

  • Live file-level and git diffs per session
  • Inline / side-by-side, full-file or diff, remembered per file
  • Annotate changes and dispatch the notes to an agent
Coordinate

A Kanban board your agents can drive

The board is exposed to agents through a local MCP server, so they can pick up, move and complete tasks themselves. Create tasks with a Notion-style editor, choose the CLI and model, and auto-dispatch — or import from Jira.

  • Agent-controlled board over local MCP
  • Per-task CLI + model selection and auto-dispatch
  • Import tickets from Jira
Configure

Manage every agent's skills, hooks and context

A dedicated editor for skills, hooks, subagents and custom agents — per agent or shared globally. Create and edit them in place, and visualise how full each agent's context window is, the way /context does.

  • Per-agent and global configuration views
  • Create skills, hooks, subagents and custom agents
  • Live context-window usage visualisation
Extend

An MCP marketplace built in

Discover and install Model Context Protocol integrations into your agents without ever leaving the orchestrator. Browse the catalog, install in a click, and manage what each client can reach.

  • Curated MCP catalog with search and filters
  • One-click install into detected MCP clients
  • Add, remove and manage integrations per client
Automation, with guardrails

Turbo Mode — unattended runs, on your terms

Turbo Mode tells the CLI to stop asking for confirmation, so agents can edit files and run commands unattended. That is powerful and risky: we recommend using it inside a container or an isolated git worktree, on a project you fully control. You get a clear warning before it's enabled, and you can turn it off at any time.

  • Off by default — a single switch you turn on yourself
  • A warning before activation; only use it on projects you fully control
  • Best paired with a container or an isolated git worktree, so mistakes stay contained
Ship

Commit and open PRs without leaving the app

Stage exactly what you want, commit, push and open a pull request on GitHub or GitLab from a single dialog — with commit messages and PR descriptions generated by your local agent.

  • Selective staging and commit
  • AI-generated commit messages and PR descriptions
  • Push and open PRs on GitHub or GitLab
Pricing

One plan. The whole loop.

One subscription unlocks the full app on all your machines.

Code Agents OrchestratorAll features
€3/ month

7 days free, then billed monthly · cancel anytime · Prices include VAT.

No charge for 7 days · Secure payment by Stripe · Card, Apple Pay, Google Pay, SEPA

  • Run up to 6 agents in parallel
  • Review live diffs and send notes back to the agent
  • Commit and open the PR from the app
  • Claude Code, Codex and Gemini — bring your own subscriptions
Launch offer — lifetime€59

Pay once, use Pro forever — about 20 months of subscription, then it's yours for good.

Available until December 31, 2026, or until all 200 licences are sold. While this offer is displayed, licences are still available.

From checkout to your first agent

  1. 1

    Create your account and subscribe

    Pick monthly or annual billing and pay securely with Stripe. Cancel anytime from your account.

  2. 2

    Download the app

    Grab the installer for macOS, Windows or Linux from your account page.

  3. 3

    Sign in from the app

    On first launch, the app opens your browser to link itself to your subscription.

Frequently asked questions

Do I need my own Claude, Codex or Gemini subscriptions?

Yes. Code Agents Orchestrator launches the official CLIs installed on your machine (Claude Code, Codex, Gemini CLI), and they use your own accounts or API keys. We don't resell model access — the app is the cockpit around them.

Does my code go to your servers?

No. The agents run locally on your computer and your code never passes through our servers. It only goes where you send it yourself: to the model provider behind the CLI you chose, and to GitHub, GitLab or Jira if you use those features. Our servers only handle your account, the license check, updates and the bug reports you choose to send.

What data do you collect?

Your account email, subscription status, the names of your signed-in devices, and the bug reports you choose to send. Anonymous crash reports and usage statistics (which help us see where new users get stuck) are opt-in: nothing is sent unless you accept, and you can change your mind at any time.

How does the 7-day free trial work?

You enter your card at checkout but are not charged for 7 days. Cancel any time from your account before the trial ends and you pay nothing. Each account gets one trial.

Does it work offline?

The app itself runs locally. It re-checks your license regularly and keeps working for up to 72 hours without reaching our servers, then asks you to reconnect.

Which operating systems are supported?

macOS, Windows and Linux.

How does the lifetime offer work?

It is a one-time payment for permanent access to the full app, limited to a fixed batch of 200 licences. The pricing page shows how many are left. See the Terms of Sale for the conditions.