am-will/gooey-pi

Desktop workspace for Pi, OMP, and Prime Agent

What it solves

GooeyPi provides a unified desktop interface for multiple AI coding agents—specifically Pi, OMP, and Prime Agent. It eliminates the need to interact with these agents through separate, fragmented interfaces by consolidating them into a single workspace that supports macOS, Linux, and Windows.

How it works

The application acts as a frontend workspace that detects and connects to installed "harnesses" (the agent backends). While GooeyPi manages the visual interface and project organization, each harness remains responsible for its own model configurations, logins, and session data. Users can switch between different agents seamlessly without interrupting active work in other harnesses.

Who it’s for

Developers who use AI coding agents like Pi, OMP, or Prime Agent and want a professional desktop environment with integrated tools for project management, version control, and browser interaction.

Highlights

  • Unified Agent Workspace: Switch between multiple coding agents in one app while maintaining separate sessions and projects.
  • Bult-in Coding Tools: Integrated Git status/diffs, terminal tabs, and project file browsing.
  • Shared Context Browser: An isolated in-app browser that allows users to annotate page elements or grant agents control over tabs.
  • Automation & Scheduling: Ability to create one-time or recurring schedules for agent tasks.
  • Extensibility: Support for MCP (Model Context Protocol) servers, plugins, and optional computer control via TryCUA.
  • Voice Integration: Prompt dictation and a real-time voice companion with reactive desktop pets.

Related

  • Project
    earendil-works/pi

    A modular agent harness and self-extensible coding agent CLI that provides a unified API for multiple LLM providers and a robust runtime for tool calling.

  • Project
    openteams-lab/openteams

    A local-first AI desktop app that provides a unified workspace for coordinating multiple AI coding agents, allowing them to share context and work within developer-controlled workflows.

  • Project
    xintaofei/codeg

    A multi-agent coding workspace that aggregates various AI coding agents into a single interface, enabling collaboration and collaboration and task management via git worktrees.

  • Project
    getpaseo/paseo

    A unified, self-hosted interface for managing multiple AI coding agents like Claude Code and Copilot across desktop, mobile, and CLI.

  • Project
    wuxiran/cc-pane

    A desktop command center for parallel AI coding that organizes CLI agents, workspaces, and sessions through MCP orchestration and integrated development tools.