Best pure multiplexer — 7,386 stars, Apache 2.0, zero telemetry, 512 Product Hunt upvotes, Git worktree isolation. The 'tmux for agents' buyer. desktop-v1.2.1 released 2026-03-18.
Where it wins
7,386 stars — highest among orchestration-layer tools
512 Product Hunt upvotes — strong consumer validation
Apache 2.0 + zero telemetry + BYOK — most developer-trust-friendly
Git worktree isolation — safe parallel agent execution
desktop-v1.2.1 released 2026-03-18 — active release velocity
Dogfooding: 'We use Superset to build Superset'
Where to be skeptical
macOS only — no Linux/Windows support
No issue-tracker integration or Best-of-N
Not in Ry Walker's Tier 1 (notable absence)
Bootstrapped 3-person team — execution risk
Naming collision with Apache Superset
Editorial verdict
Best pure multiplexer. Highest raw community traction among orchestrators (7.2K stars, 512 PH). Privacy-first (Apache 2.0, zero telemetry, BYOK). Simple and focused.
How to get started
Download the latest macOS/Windows/Linux build from GitHub releases (or brew install superset), sign in, and add a repo so Superset creates isolated git worktrees per task. Queue Claude/Codex/Gemini agents from the UI and use the notifications drawer to jump back into each workspace when an agent finishes.
Videos
Reviews, tutorials, and comparisons from the community.
Apache Superset Review 2025: Is It the Best Open-Source BI Tool?
Apache Superset Dashboard Customization: Settings & CSS Guide
Is this FREE tool better than Power BI? | Apache Superset Overview
Related
Claude Code
98Anthropic's official agentic coding CLI. v2.1.81 (Mar 20) shipped `--bare`, smarter worktree resume, and improved MCP OAuth while the repo crossed 82,204 stars and logged ~14 commits/week across 10+ maintainers. Terminal-native, tool-use-driven, with deep file system + shell access, #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue. 8M+ npm weekly downloads. Opus 4.6 with 1M context.
LangGraph
95#1 Python agent framework by production evidence — 40.2M PyPI downloads/month, Fortune 500 deployments (LinkedIn, Uber, Replit, Elastic, Klarna, Cloudflare, Coinbase), ~400 LangGraph Platform companies, LangSmith rated best-in-class observability. Stable v1.x API, model-agnostic, MCP support.
Pydantic AI
95#3 Python agent framework by downloads — 15.6M PyPI/month. Built by the Pydantic team. Runtime type enforcement is a genuine differentiator no other framework offers. V1 shipped with Temporal integration for durable execution and Logfire observability. Emerging pattern: 'Pydantic AI for agent logic, LangGraph for orchestration' (ZenML).
AutoGen (Microsoft)
95⚠️ MAINTENANCE MODE — Microsoft officially confirmed bug fixes and security patches only, no new features (VentureBeat 2026-02-19). 55.9K stars but only 1.57M PyPI/month — DL/star ratio of 28, the most inflated among active frameworks. Being replaced by Microsoft Agent Framework (AutoGen + Semantic Kernel merge, GA targeted ~Q2 2026). Teams on AutoGen should plan migration.
Public evidence
Launch thread explains the multi-worktree orchestration, push notifications when an agent completes, and per-tab isolation so Claude/Codex/Gemini can work simultaneously.
Strong consumer traction. 512 upvotes validates the 'tmux for agents' value proposition among developer-tool buyers.
Independent validation of core multiplexer functionality. Confirms zero-telemetry claims and worktree isolation workflow.
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
Orchestrate swarms of Claude Code, Codex, and more in parallel.<br /> Works with any CLI agent. Built for local worktree-based development.
<br />Download for macOS • Documentation • Changelog • Discord
<br /> </div>Superset orchestrates CLI-based coding agents across isolated git worktrees, with built-in terminal, review, and open-in-editor workflows.
Wait less, ship more.
| Feature | Description |
|---|---|
| Parallel Execution | Run 10+ coding agents simultaneously on your machine |
| Worktree Isolation | Each task gets its own branch and working directory |
| Agent Monitoring | Track agent status and get notified when changes are ready |
| Built-in Diff Viewer | Inspect and edit agent changes without leaving the app |
| Workspace Presets | Automate env setup, dependency installation, and more |
| Universal Compatibility | Works with any CLI agent that runs in a terminal |
| Quick Context Switching | Jump between tasks as they need your attention |
| IDE Integration | Open any workspace in your favorite editor with one click |
Superset works with any CLI-based coding agent, including:
| Agent | Status |
|---|---|
| Amp Code | Fully supported |
| Claude Code | Fully supported |
| OpenAI Codex CLI | Fully supported |
| Cursor Agent | Fully supported |
| Gemini CLI | Fully supported |
| GitHub Copilot | Fully supported |
| OpenCode | Fully supported |
| Pi | Fully supported |
| Any CLI agent | Will work |
If it runs in a terminal, it runs on Superset
| Requirement | Details |
|---|---|
| OS | macOS (Windows/Linux untested) |
| Runtime | Bun v1.0+ |
| Version Control | Git 2.20+ |
| GitHub CLI | gh |
| Caddy | caddy (for dev server) |
Download Superset for macOS
1. Clone the repository
git clone https://github.com/superset-sh/superset.git
cd superset
2. Set up environment variables (choose one):
Option A: Full setup
cp .env.example .env
# Edit .env and fill in the values
Option B: Skip env validation (for quick local testing)
cp .env.example .env
echo 'SKIP_ENV_VALIDATION=1' >> .env
3. Set up Caddy (reverse proxy for Electric SQL streams):
# Install caddy: brew install caddy (macOS) or see https://caddyserver.com/docs/install
cp Caddyfile.example Caddyfile
4. Install dependencies and run
bun install
bun run dev
5. Build the desktop app
bun run build
open apps/desktop/release
All shortcuts are customizable via Settings > Keyboard Shortcuts (⌘/). See full documentation.
| Shortcut | Action |
|---|---|
⌘1-9 | Switch to workspace 1-9 |
⌘⌥↑/↓ | Previous/next workspace |
⌘N | New workspace |