#4545th of 143 in Coding agents and AI editors

xum

Desktop and server app for running many coding agents in isolated workspaces

Stars
2.1k
License
AGPL-3.0
Last commit
Oct 2026
Last release
Oct 2026
Language
TypeScript
Stars, last 29 weeks+531
31 Mar 2026: 1,526 stars7 Apr 2026: 1,579 stars14 Apr 2026: 1,610 stars21 Apr 2026: 1,639 stars28 Apr 2026: 1,661 stars5 May 2026: 1,676 stars12 May 2026: 1,712 stars19 May 2026: 1,732 stars26 May 2026: 1,758 stars2 Jun 2026: 1,779 stars9 Jun 2026: 1,798 stars16 Jun 2026: 1,817 stars23 Jun 2026: 1,842 stars30 Jun 2026: 1,865 stars7 Jul 2026: 1,882 stars14 Jul 2026: 1,894 stars21 Jul 2026: 1,911 stars28 Jul 2026: 1,928 stars4 Aug 2026: 1,945 stars11 Aug 2026: 1,954 stars18 Aug 2026: 1,965 stars25 Aug 2026: 1,972 stars1 Sept 2026: 1,988 stars8 Sept 2026: 1,999 stars15 Sept 2026: 2,011 stars22 Sept 2026: 2,028 stars29 Sept 2026: 2,036 stars6 Oct 2026: 2,042 stars13 Oct 2026: 2,049 stars20 Oct 2026: 2,057 stars

1,526 on 31 Mar 20262,057 on 20 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

Xum (formerly Mux) is a TypeScript app that runs several coding agents side by side. Each agent gets its own workspace: the local project directory, a git worktree, or a remote host over SSH. It uses a custom agent loop with Claude Code-style Plan/Exec modes and /compact, and shows git divergence, costs and agent status in one UI.

Who it is for: Developers running several coding agents in parallel on git repos

Strengths

  • Three runtimes per workspace: local directory, git worktree, or SSH remote
  • Central git divergence view across parallel agent workspaces
  • Ollama for local models and OpenRouter for long-tail providers
  • Ships a VS Code extension and a responsive server-mode UI for mobile

Weaknesses

  • AGPL-3.0 license may restrict use in proprietary or hosted products
  • Pre-built binaries listed only for macOS and Linux; no Windows build
  • Custom agent loop, so behavior differs from Claude Code despite similar UX
  • README gives no RAM, port or server-mode setup details

What it needs

  • GPU optional
  • Docker + Compose
  • Needs git, SSH (for remote runtime), Ollama (optional), OpenRouter (optional)
  • Models: Anthropic Claude (sonnet-4, opus-4), OpenAI GPT-5, xAI Grok, Ollama, OpenRouter

Also in Coding agents and AI editors

See all 143
Also in Coding agents and AI editors
RankProjectScore
1ArchonYAML workflow engine that runs AI coding agents through fixed dev steps23.7k starsMIT84 out of 100
2claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs195.1k starsMIT83 out of 100
3Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI11.1k starsMIT83 out of 100
#4piTerminal coding agent with extensions, skills, and an SDK117k starsMIT80 out of 100
#5oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory70.3k starscustom license80 out of 100