Getting Started

This guide walks you through setting up RenX and starting your first project.

1. Download and Install

Download the RenX desktop application from our website. RenX is available for macOS (Apple Silicon and Intel), Windows, and Linux.

After downloading, install the application following your operating system’s standard process:

2. Sign In

When you launch RenX for the first time, you’ll see the welcome screen with a Sign in button.

Click Sign in. Your system browser will open for authentication. Once you complete the sign-in flow, you’ll be redirected back to the app automatically.

3. Connect an API Key

RenX uses a Bring Your Own Key (BYOK) model — you provide your own API keys from AI providers like OpenAI, Anthropic, Google, or others.

To add your first API key:

  1. Click the Settings icon (gear) at the bottom of the left sidebar.
  2. Select API and Pricing.
  3. Click Add Provider.
  4. Choose your provider (e.g., OpenAI, Anthropic).
  5. Paste your API key.
  6. Optionally set a label and base URL.
  7. Click Save.

Your API key is stored securely in your operating system’s credential storage (e.g., macOS Keychain) and is never sent to Open Mercury’s servers.

You can add multiple providers and switch between them. The active provider is shown with an “Active” badge.

4. Start Your First Project

Once signed in with an API key connected, you’re ready to start a project.

From the Conversations tab (the first tab in the sidebar), you’ll see the Start Session card:

Fill in the following:

  1. Machine — Select which machine to work on. “Local” is your current machine. If you have RenX running on another computer, it will appear here too.

  2. Folder — Select the project directory your agent will work in. Click to browse your filesystem or choose from recent directories.

  3. Agent — Choose which agent to use. If you haven’t created any custom agents yet, select the default agent.

  4. Prompt — Describe what you want the agent to do. For example:

    • “Review this codebase and summarise the architecture”
    • “Fix the failing tests in the test suite”
    • “Create a REST API for user management”

  5. Click the Send button (arrow icon).

Your session will start, and the agent will begin working. You’ll see messages streaming in as the agent thinks, plans, and takes actions.

5. Managing Sessions

Your sessions appear in the left sidebar under Conversations, grouped by agent and workspace folder.

Each session shows:

Click any session to reopen it. You can continue the conversation by typing a follow-up prompt in the input field at the bottom.

To start a new session, click New Project at the top of the session list.

6. Permission Requests

When your agent needs to perform an action that requires approval — such as writing files, running commands, or making API calls — it will send you a permission request.

You can:

Permission requests appear as a badge count on the Conversations tab icon.

7. Next Steps

Now that you’re up and running, explore these guides in roughly this order:

Core workflows

Advanced configuration