greenfield-inc/Pane

Terminal-first, open-source AI agent manager for any CLI agent (agent agnostic), any OS (mac, windows, linux). The Open-Source Agentic Development Environment for running multiple coding agents in parallel. Run locally or self-host Remote Pane to manage agents from desktop or phone. Simplify multi-agent orchestration with the runpane CLI.

What it solves

Pane is a management layer for AI coding agents that eliminates the friction of juggling multiple terminal windows, manual git worktree management, and context switching between different AI tools. It provides a unified workspace where developers can run any CLI-based agent (like Claude Code, Aider, or Codex) in isolated environments without needing specific plugins or SDKs.

How it works

Pane uses a system of "panes" and "tabs." Each pane is tied to a specific git worktree, providing a completely isolated branch and file system for an agent to work in. Inside these panes, users can open multiple tabs for agents, diff viewers, and file explorers. It also includes a runpane CLI that allows agents themselves to operate the workspace—creating new panes or registering repositories—effectively turning the agent into a workspace orchestrator.

Who it’s for

  • Multi-agent users who switch between different AI coding tools depending on the task.
  • Developers on Windows, Linux, and macOS who want a consistent, high-performance experience regardless of their OS.
  • Keyboard-driven developers who want to automate their AI workflow via shortcuts and a command palette.

Highlights

  • Invisible Git Worktrees: Automatically handles the creation and cleanup of worktrees for isolated agent sessions.
  • Pane Chat: A global orchestrator terminal that can coordinate multiple agents across different repositories and worktrees.
  • Remote Pane: Ability to run agents on a remote server or VM while controlling the UI from a desktop or mobile browser.
  • Agent-Operable CLI: A stable CLI contract that allows AI agents to programmatically manage the workspace.
  • Cross-Terminal Context: Use @mention to pull the last 500 lines of one terminal's output into another.
  • Built-in Tooling: Integrated resource monitoring, a built-in browser for dev server previews, and automatic .env secret mirroring.

Related

  • Project
    dcouple/Pane

    A management layer for AI coding agents that provides isolated workspaces via Git worktrees and a unified terminal interface for any CLI-based agent.

  • Project
    awslabs/awsome-distributed-ai

    A collection of reference architectures and examples for deploying and operating distributed AI training and inference on AWS infrastructure.

  • Project
    radareorg/r2ai

    A set of plugins for radare2 that integrates LLMs to assist in reverse engineering tasks such as function explanation, vulnerability discovery, and augmented decompilation.

  • Project
    appium/appium-mcp

    An MCP server that enables AI assistants to automate mobile app testing on iOS and Android using natural language and vision-based element finding.