Overview
Superset is an agentic IDE built around the idea that one developer now supervises many coding agents at once. Instead of juggling terminal tabs and stashes, you open a workspace per task; Superset gives each one its own git worktree so agents never step on each other's changes, and the README describes running 100+ agents in parallel from a single window.
It is agent-agnostic by design: anything that runs as a CLI coding agent works, including Claude Code, Cursor Agent, OpenAI Codex, Gemini CLI and GitHub Copilot, and you bring your own subscription for each. The app itself supplies the surrounding workflow — a terminal with tabs, splits and persistent sessions, a diff viewer for reading and editing what an agent produced, an in-app browser for previewing a dev server, and notifications when an agent finishes or needs input.
Beyond the desktop app there is a standalone CLI and an SDK for scripting runs, plus remote access so you can drive workspaces on another machine through custom hosts. The project is published under the Elastic License 2.0: the desktop app is free for running agents locally and teams may self-host, but reselling Superset as a service is not permitted.
What it does
- Parallel workspaces, each backed by its own git worktree, so concurrent agents never collide on the same checkout
- Works with any CLI-based coding agent — Claude Code, Cursor Agent, OpenAI Codex, Gemini CLI, GitHub Copilot and 20+ more, on your own subscriptions
- Built-in terminal with tabs, splits and persistent sessions that survive restarts
- Diff viewer for reviewing and editing agent changes before they land
- In-app browser for previewing dev servers next to the code
- Agent monitoring with completion notifications, plus a CLI and SDK for scripting and automation
- Remote access to workspaces on other machines via custom hosts
Getting started
Superset targets macOS (an experimental Linux x64 AppImage exists) and requires git. Install the desktop app, or the standalone CLI if you want to script runs.
Install the desktop app
Download the DMG for your Mac from the latest release and drag it to Applications.
# Apple Silicon
https://github.com/superset-sh/superset/releases/latest/download/Superset-arm64.dmg
# Intel
https://github.com/superset-sh/superset/releases/latest/download/Superset-x64.dmgOr install the standalone CLI
The CLI can be installed from the project's install script or from its Homebrew tap.
curl -fsSL https://superset.sh/cli/install.sh | sh
# or
brew install superset-sh/tap/supersetOpen a repo and start agents
Point Superset at a git repository and create a workspace per task. Each workspace gets its own worktree, so you can start another agent on a different branch without waiting for the first to finish. Install the `gh` CLI if you want the pull-request workflow.
Review before you ship
Use the diff viewer to read and edit what each agent changed, and the in-app browser to check the dev server. Completion notifications tell you which workspace needs attention next.
Commands and code are distilled from the project's own documentation — always check the official repo for the latest.
When to use it
- Reach for it when you want several coding agents working different tickets at once without them fighting over one checkout
- Use it to review agent output properly — a real diff viewer and a live preview beside the code, rather than scrollback
- Good when you mix harnesses: Claude Code for one task, Codex or Gemini CLI for another, all under one window and your own subscriptions
- Script repeated agent runs through the CLI and SDK, or drive workspaces on a beefier remote machine
How Superset compares
Superset alongside other open-source ai sdlc automation tools AI/TLDR tracks, ranked by GitHub stars.
| Tool | Stars | What it does |
|---|---|---|
| Multica | ★ 50.4k | Self-hostable workspace where coding agents are assigned issues like teammates: 26 agent CLIs, runtimes you own, a replayable execution log per run, and review gates before anything ships. |
| GPT-Pilot | ★ 33.7k | Autonomous AI developer that breaks down an app description into tasks, writes and runs code incrementally, and asks clarifying questions to produce a working production application. |
| oh-my-codex (OMX) | ★ 33.2k | A workflow layer for the OpenAI Codex CLI that adds agent teams, git-worktree isolation, hooks and HUDs behind a set of canonical plan, code-review and QA commands. |
| Vibe Kanban | ★ 28.1k | Vibe Kanban lets you plan tasks on a kanban board, run coding agents like Claude Code and Codex in isolated workspaces, then review their diffs and ship pull requests. |
| Beads | ★ 27.3k | A Dolt-backed dependency-graph issue tracker for coding agents: hash IDs avoid multi-agent collisions, `bd ready` surfaces unblocked work, and `bd remember` keeps durable project memory. |
| Archon | ★ 23.5k | A workflow engine for AI coding agents: describe plan, implement, validate, review and PR phases as YAML, and every run repeats them in its own git worktree. |
| Keploy | ★ 18.5k | An API testing tool that records real traffic with eBPF — including database and queue calls — and replays it as deterministic tests and data mocks, with no SDK to import and no code changes. |
| Superset | ★ 14.4k | Run 100+ CLI coding agents in parallel, each in its own git worktree |