Back to directory

GooeyPi

A desktop workspace that gives the Pi, OMP and Prime Agent coding-agent harnesses a shared interface on macOS, Linux and Windows, while leaving each harness in charge of its own models, logins and sessions.

GooeyPi

GooeyPi is a desktop workspace for three coding-agent harnesses in the Pi family, Pi itself, OMP, which adds its own plugins, commands and approval controls, and Prime Agent, which adds Prime's provider integrations and native heartbeats. A switcher moves between Pi Work, OMP Work and Prime Work, and GooeyPi detects which harnesses are installed and shows the ones that are ready; only one harness is required to get started, and switching harnesses does not stop work already running in another.

Within a harness, GooeyPi streams conversations with markdown, reasoning summaries, tool activity, retries and context compaction, lets a user choose a model and reasoning level, queue or steer follow-ups, and paste or drop images into a prompt. It organizes work by local project folders and Git worktrees, letting a user create a branch worktree and open it as a new GooeyPi workspace, and mention another session for parallel work.

A built-in coding workspace reviews Git status and diffs, stages or restores files, and commits without leaving the app, alongside multiple terminal tabs and browser, summary and file panels.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.