Agentic Copilot
Agent Go Home
Agent Go Private · optional extras

Local machine bridges, step by step

Everything here is optional. Agent Go Private works fully inside the browser without any of it. This page is for three extras: letting the agent use your whole desktop, letting it run commands in a project folder, and using your own Claude Code or ChatGPT subscription as the model. Written for people who do not use terminals every day.

Download the bridges pack version — · — KB Back to Agent Go Private

First, three things you need once

  1. A terminal. That is a window where you type commands. On Windows: press the Windows key, type PowerShell, press Enter. A blue or black window opens; you type into it and press Enter. Keep it open for the steps below.
  2. Python. Go to python.org/downloads, click the big Download button, run the installer, and on its first screen tick "Add python.exe to PATH" before clicking Install. That tick is what lets the commands below find Python. Then close and reopen the terminal and type python --version : you should see a version number, 3.10 or higher.
  3. The pack. Click "Download the bridges pack" above. Right-click the zip, Extract All, and put the folder somewhere permanent, for example Documents\Agent Go Bridges. Inside you will see two folders: desktop-server and whisper-server.

A. Let the agent use your desktop and run commands

  1. Install the helper's parts. In the terminal, paste this and press Enter: pip install flask pyautogui mss pillow . Lines scroll by for a minute and end with "Successfully installed". If you also want the agent to read PDF files on your disk, paste pip install PyMuPDF pytesseract as well.
  2. Start the helper. In the extracted folder, open desktop-server and double-click start-desktop.bat. A black window opens and stays open; that window is the helper running. Leave it open while you use the agent (close it when you are done).
  3. Copy your token. The first time, that window prints a line with a long code called the desktop token. Select it and copy it (or open the file desktop-server\.desktop-token in Notepad; the token is in there and stays the same).
  4. Give the token to the extension. In the side panel click ⚙ Settings, scroll to Advanced settings, local machine bridges, paste the token into Desktop token. Leave "Desktop control server URL" as http://localhost:8777. Click the Test button under it: it should turn green and show your screen size, for example "screen 1920x1080".
  5. Choose what to allow. Tick Enable desktop control if you want the agent to move the mouse, type and take screenshots outside the browser. Tick Enable Run commands if you want it to run commands like tests or builds, and type the folder they should run in under Project directory (for example C:\Users\you\my-project). Click Save.
  6. Try it. In the side panel type "Take a screenshot of my desktop and describe what you see". Before it acts, the panel asks you to approve; click Approve. If anything ever goes wrong, push the mouse hard into any corner of the screen: the helper stops immediately.

B. Talk to the agent, transcribed on your own computer

  1. In the terminal paste pip install flask faster-whisper and press Enter.
  2. In the extracted folder open whisper-server and double-click start-whisper.bat. The first time it downloads the speech model (a few hundred MB); wait for the window to say it is ready. Leave the window open.
  3. In Settings, the "Local Whisper server URL" stays http://localhost:8765; click its Test button, it turns green. The 🎤 button in the side panel now works through your computer. If the helper is not running, the button quietly uses Chrome's own speech service instead.

C. Use your Claude Code or ChatGPT subscription as the model

If you already pay for Claude Code or ChatGPT, the desktop helper from section A can pass the agent's requests to that tool, signed in with your own account. The model is then billed to that plan, and no API key is needed. This is off until you turn it on.

  1. Install the tool and sign in, once. This needs Node.js: if node --version shows nothing, install it from nodejs.org (the "LTS" button), then reopen the terminal. For Claude, paste npm install -g @anthropic-ai/claude-code , then type claude and follow the sign-in it shows you. Check with claude -p "say ok" : it should answer "ok". For ChatGPT, paste npm install -g @openai/codex , then codex login.
  2. Allow the helper to use it. In the desktop-server folder, right-click start-desktop.bat → Edit (it opens in Notepad). Find the line REM set DESKTOP_ENABLE_CLI_BRIDGES=1 and delete the REM at its start so it reads set DESKTOP_ENABLE_CLI_BRIDGES=1. Save, close the helper window if it is open, and double-click start-desktop.bat again.
  3. Tell the extension. Make sure section A steps 3 and 4 are done (token pasted, Test green). Then at the top of Settings, under Inference provider, choose Claude (SUBSCRIPTION, via local Claude Code CLI) and click Save. The badge in the panel header now names that provider, and your next task runs through your plan.
  4. Good to know. The ChatGPT choice is for reviews and drafts only: its tool returns text and cannot click or fill pages. Long answers can take a minute; the panel keeps showing progress. Using your plan this way is between you and Anthropic or OpenAI; their terms apply.

Stopping, and staying safe