Overview:
Superset is a desktop code editor designed to orchestrate multiple CLI-based coding AI agents in parallel. It solves the problem of context switching and task interference when running several AI agents simultaneously on a single machine. The tool is built for developers who work with terminal-based coding agents, such as Claude Code or OpenAI Codex CLI. It provides a unified interface for managing isolated agent tasks, monitoring their progress, and reviewing generated changes without leaving the application.
Core Features:
Parallel Execution: Run 10 or more coding agents simultaneously on a local machine.
Worktree Isolation: Each task operates in its own git worktree with a separate branch and working directory, preventing agent interference.
Agent Monitoring: Track agent status and receive notifications when changes are ready for review.
Built-in Diff Viewer: Inspect and edit agent-generated changes directly within the application.
Workspace Presets: Automate environment setup, dependency installation, and teardown via
.superset/config.jsonconfiguration.Universal Compatibility: Works with any CLI-based coding agent that runs in a terminal, including Claude Code, Codex CLI, Cursor Agent, Gemini CLI, GitHub Copilot, and more.
Use Cases:
Developers who need to run multiple AI coding agents, such as Claude Code and Codex, on separate tasks simultaneously without context switching.
Teams that want to isolate each coding task into its own git branch and working directory to prevent agent conflicts and merge issues.
Self-hosters who prefer local worktree-based development over cloud-based agent orchestration, with full control over connections and integrations.
Developers who need to review, edit, and approve changes from multiple agents from a single window, with quick handoff to an external editor.
Why It Matters:
Superset provides a local, terminal-agnostic orchestration layer for multiple AI coding agents, each isolated in its own git worktree. Its open-source availability under Elastic License 2.0 (ELv2) allows developers to inspect and modify the tool. The explicit connection model means users choose which agents and providers to connect, with no automatic telemetry or external cloud dependencies. This makes it a practical foundation for developers who want to scale parallel agent usage while maintaining local data control.
