Want to give your ChatGPT a gift? Give it PickleShell.

Give ChatGPT a local machine to work with.

PickleShell connects ChatGPT Assistant to an OpenCode agent running on your machine. It can inspect repositories, edit files, run tests, transfer small files, and coordinate long-running tasks — turning ChatGPT from an advisor into an assistant that helps get the work done.

ChatGPT conversation demonstrating PickleShell creating a Git repository and README from an attached cucumber logo
🌱 Architecture

How PickleShell connects ChatGPT to your local machine

ChatGPT sends a task to your local OpenCode agent, the agent works inside the selected workspace, and the results come back to ChatGPT so it can review the work and continue with the next step.

💬

ChatGPT

User prompt or file attachment

🔒

Secure MCP Tunnel

Outbound-only, encrypted

🔧

Gateway + OpenCode

Authenticated, workspace-scoped execution

💡 What it is for

Put ChatGPT Assistant to work

PickleShell solves a practical problem: ChatGPT can analyze tasks, but it normally cannot work directly with a local repository.

Through PickleShell, ChatGPT sends instructions and small files to a local OpenCode agent, follows the execution, reads the result, and can continue in the same session when it passes the session ID.

The agent runs on your machine, inside a selected workspace, through a protected outbound-only tunnel. PickleShell removes the human relay between ChatGPT and OpenCode, while you remain the owner and observer.

PickleShell is for developers and experienced users. Installation is designed to be guided by Codex: ask it to clone the repository, read AGENTS.md, and walk you through the setup step by step. AGENTS.md covers the architecture, installation, tunnel configuration, plugin setup, and troubleshooting.

🚀 Use Case

Let your ChatGPT Assistant control your empire

Create three PickleShell tunnels to three different machines, then give the plugins unique names: PickleShell Mars, PickleShell Moon, and PickleShell Starbase. The first tunnel connects to a machine on Mars, the second to a machine on the Moon, and the third to a machine at Starbase. Tell your ChatGPT Assistant which named plugin belongs to which machine, and it can route each task to the right destination.

With this setup, your ChatGPT Assistant can manage colonies on Mars and the Moon, as well as coordinate launches from Starbase to them — the big rockets Elon launches. The same pattern is useful today for everything from saving a technical specification to asking the OpenCode agent on a selected machine to carry out a complex task directly from ChatGPT.

ChatGPT connection dialog for adding the PickleShell app and reviewing its permissions
💬 Contact

Have a question or found a problem?

Open an issue on GitHub to report a bug, suggest an improvement, or ask for help. Include the relevant setup details and steps to reproduce the problem.

🚀 Get started

Ready to bridge ChatGPT and your local agent?

Read the deployment guide, configure the tunnel, refresh the PickleShell plugin in ChatGPT, and run the smoke checks before touching a production workspace.