head to head · open source
agent-framework vs dmux
agent-framework has 14,527 GitHub stars, 2,570 forks, 617 open issues and last shipped yesterday. dmux has 1,815 stars, 138 forks, 39 open issues and last shipped 3 months ago. agent-framework leads on adoption by 700% (14,527 vs 1,815 stars). agent-framework is written in Python under MIT; dmux is written in HTML under MIT. agent-framework has attracted 18% as many forks as stars, dmux 8%. agent-framework was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (ai, orchestration), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 20902 open source comparisons
Side by side
| agent-framework | dmux | |
|---|---|---|
| GitHub stars | ★ 15K | ★ 1.8K |
| License | MIT | MIT |
| Written in | Python | HTML |
| Last push | 2026-11-04 | 2026-08-16 |
| Forks | ⑂ 2.6K | ⑂ 138 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick agent-framework if
- You weight community size — 15K stars and counting
- You want the MIT license terms
- Your stack matches Python
- You value the larger contributor base for long-term maintenance
pick dmux if
- You want the dmux feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches HTML
- You evaluated both and dmux fits your workflow better
About agent-framework
Welcome to Microsoft Agent Framework! Microsoft Agent Framework (MAF) is an open, multi language framework for building production grade AI agents and multi agent workflows in .NET and Python . Microsoft Agent Framework is built for teams taking agents from prototype to production. It provides a consistent foundation for building, orchestrating, and operating agent systems across Python, .NET and Go, while keeping architecture choices open as requirements evolve, and supports a broad ecosystem including Microsoft Foundry, Azure OpenAI, OpenAI, and the GitHub Copilot SDK, with samples and hosting patterns for…
read the full agent-framework overview →
About dmux
Parallel agents with tmux and worktrees Manage multiple AI coding agents in isolated git worktrees. Branch, develop, and merge — all in parallel. Documentation · Getting Started · Issues Language: English 日本語 Install Quick Start Press n to create a new pane, type a prompt, pick one or more agents (or none for a plain terminal), and dmux handles the rest — worktree, branch, and agent launch. On first run, dmux can configure a primary inference provider/model and an optional backup. It discovers models from the provider when possible and supports API key providers, custom OpenAI…
More in Infrastructure & Operations
Related comparisons
More Orchestration & Scheduling projects
Compare either of these against the rest of the Orchestration & Scheduling field.
Frequently asked questions
Is agent-framework or dmux more popular?
agent-framework has 14,527 GitHub stars and dmux has 1,815. agent-framework has the larger community by that measure.
Are agent-framework and dmux free?
Both are open source. agent-framework is licensed under MIT and dmux under MIT. Neither carries a licence fee.
What is the difference between agent-framework and dmux?
agent-framework is written in Python and dmux in HTML. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, agent-framework or dmux?
Choose agent-framework if you want the larger community (14,527 stars) or its MIT licence terms. Choose dmux if its feature set, stack or MIT licence fits better. Both are self-hostable.