# swe-mux

> Updated 2026-09-27 · type: tool · category: mcp-agents · status: active · rev 1

swe-mux runs many coding agents side by side in one terminal multiplexer with live per-session status and phone access over Tailscale.

- Open source: yes (Apache-2.0)
- Self-hostable: yes
- Pricing model: free
- Best for: A developer running several coding agents at once (Claude Code, Codex) across multiple projects who is tired of juggling windows, hung processes, and SSH-ing in to see which agent needs input — and wants one dashboard, reachable from a phone, without shipping their code to a vendor backend.
- Last verified: 2026-09-27

- **Canonical:** https://gtmstacker.com/registry/tool/swe-mux/
- **Source:** [jatoran · GitHub](https://github.com/jatoran/swe-mux)
- **Tags:** mcp-agents, coding-agents, terminal-multiplexer, self-hostable, python, workflow-automation
- **Repository:** https://github.com/jatoran/swe-mux

## Is swe-mux open source?

Yes, swe-mux is open source under the Apache-2.0 license.

## How much does swe-mux cost?

swe-mux is free to use.

## Can I self-host swe-mux?

Yes, swe-mux can be self-hosted (the source is available under the Apache-2.0 license).

## Alternatives & related

- [AgentRun](https://gtmstacker.com/registry/tool/agentrun/)
- [oh-my-subagents](https://gtmstacker.com/registry/tool/oh-my-subagents/)


---

swe-mux is a terminal multiplexer that runs multiple coding agents (Claude Code, Codex) side by side with live per-session status, reachable from a phone over Tailscale. Open source: yes (Apache-2.0); self-hostable; pricing free. It is Python 3.12+, ships a PyPI wheel, and has 6 stars.

## What it does

swe-mux sits on top of your existing agent CLIs rather than replacing them: you launch Claude Code, Codex, or other agents inside it, and it tracks which session is working, which is idle, and which is waiting on input. Around the sessions it bundles the operator chores that pile up when you run agents in parallel — terminal management, git review, file management, and local previews — in one place. Because it exposes the multiplexer over Tailscale, you can check on and steer long-running agents from a phone instead of SSH-ing into a desktop. Open source: yes (Apache-2.0); self-hostable; pricing free.

## Provenance

- Apache-2.0 per repo; 6 stars; Python 3.12+; published PyPI wheel; CI across Windows, Linux and macOS; Windows installer from v0.1.2; integrates with (not replaces) Claude Code and Codex; self-hostable with a stated no-account, no-backend, no-telemetry posture (WebFetch 2026-09-27).
- Surfaced via studio discovery in the 2026-09-27 pass.
- Anti-hype note — load-bearing: 6 stars and young; the status monitoring and cross-device access are the design, not independently validated.
- Curated from the GTM Stacker signal registry (2026-09-27 pass); license/facts independently verified 2026-09-27.

## Why it matters for a GTM stack

The teams shipping GTM tooling — internal apps, integrations, outbound automations — increasingly do it by running several coding agents at once. The bottleneck stops being any single agent and becomes operator attention: which of six sessions is stuck, which finished, which needs a decision. swe-mux is a control surface for exactly that fan-out — one view of every agent's state, plus git and preview in the same window, reachable from a phone so a stalled run does not wait until you are back at your desk. Open source: yes (Apache-2.0); self-hostable; pricing free. The honest read: it is early (6 stars) and unproven at scale, so treat it as a convenience layer for a workflow you already trust, not as a reliability guarantee.