← All articles

Coding

NTM Review: The Open-Source Multi-Agent Tmux Orchestrator

7 min read

Updated

Discover how NTM (Named Tmux Manager) wraps tmux with agent-aware orchestration, named sessions, broadcast prompts, and conflict detection.

If you run multiple terminal-based AI agents on a remote server, you already know the pain. You open tmux, split panes, manually tile them, and then spend half your time switching between panes to check which agent has finished. When two agents edit the same file, you get a merge conflict nobody asked for. If your SSH connection drops, you have to hope everything is still running when you reconnect.

NTM (Named Tmux Manager) exists to fix exactly this. It is a free, open-source CLI tool that wraps tmux with agent-aware orchestration: named sessions, broadcast prompts, conflict detection, and a terminal user interface (TUI) dashboard that tracks what your agents are doing.

This review covers what NTM does, where it excels, and where it falls short.

What NTM Does

NTM is a Go binary that turns tmux into a multi-agent command center. You tell it how many agents you want, what type they are, and it handles the session creation, pane tiling, and naming. From there, you can broadcast prompts to all agents of a given type, monitor their status through a dashboard, and detect when two agents are about to step on each other's files.

The basic workflow looks like this:

ntm spawn myproject --cc=3 --cod=1 --gmi=1

That command creates a tmux session called "myproject" with three Claude Code instances, one Codex instance, and one Gemini CLI agent, each in its own named pane, automatically tiled. No manual split-pane commands or guessing which pane is which are required.

NTM supports Claude Code, OpenAI Codex, and Gemini CLI out of the box, and any terminal-based agent can be added.

Key Features

Tiled Panes with Named Agents

Every agent gets a labeled pane. When you have five agents running, you can see at a glance which one is Claude Code instance 2 and which is your Gemini agent. This surfaces visual clarity when running multiple terminal panes.

Broadcast Prompts

ntm send myproject --cc "refactor all error handling in src/api"

This sends a prompt to every Claude Code instance in the session simultaneously. You can target by agent type (--cc, --cod, --gmi) or send to all agents at once. This is useful when you want multiple agents working on different modules but with the same high-level instruction.

Without NTM, you would have to send keys to each pane individually, which is tedious and error-prone when you have more than two agents.

TUI Dashboard

ntm dashboard myproject

The dashboard is a terminal UI that shows status cards for each running agent: whether it is idle, processing, or stuck. Token velocity badges show how fast each agent is consuming tokens, which helps you spot an agent that has gone into a loop versus one that is making steady progress.

The dashboard uses themed layouts to surface status information that you would otherwise have to check pane by pane.

Conflict Detection

When multiple agents work on the same codebase, the biggest risk is two agents editing the same file at the same time. NTM tracks file reservations so agents can claim files before editing. Other agents see what is locked and avoid those files, preventing merge conflicts.

Context Recovery

NTM detects when an agent has hit context compaction (when the agent's context window is full and it starts dropping earlier conversation). When this happens, NTM flags it so you can intervene, start a fresh agent, hand off context, or adjust the task scope.

Persistent Sessions

Because NTM builds on tmux, sessions survive SSH disconnections. Detach from your session, close your laptop, reconnect hours later, and your agents are still running. NTM preserves the orchestration state alongside the tmux session.


Pros and Cons

Pros:

  • Agent-aware spawning and tiling saves setup time
  • Broadcast prompts eliminate repetitive manual commands
  • Conflict detection prevents multi-agent file collisions
  • Context compaction detection catches silent agent degradation
  • Works over SSH with full session persistence
  • Free and open-source (MIT license)
  • Clean TUI dashboard surfaces agent state at a glance

Cons:

  • Early-stage project with a small community
  • Tmux scrolling and text selection can be clunky
  • Requires existing tmux knowledge as a baseline
  • Pure terminal interface with no graphical GUI option
  • Command set has a learning curve beyond basic tmux
  • Limited documentation for advanced use cases

NTM vs cmux vs Plain tmux vs screen

FeatureNTMcmuxPlain tmuxscreen
PlatformAny (tmux-based)macOS onlyAnyAny
Agent SpawningNamed, typed (--cc=3)GUI-basedManual split-paneManual
Broadcast PromptsYes, by agent typeNoManual per paneManual per window
Conflict DetectionFile reservationsNoNoNo
DashboardTUI with token velocityBuilt-in browserStatus bar onlyStatus bar only
Context RecoveryCompaction detectionNoNoNo
SSH PersistenceYesNo (native app)YesYes
GUINoYesNoNo
PriceFree (MIT)Free (beta)FreeFree
MaturityEarly (v1.8)Early (beta)DecadesDecades

The choice between NTM and cmux comes down to your environment. If you are on macOS and prefer a visual terminal with a built-in browser, cmux is a strong fit. If you are SSH'd into a remote server running agents around the clock and need cross-platform support, NTM is the clear choice. Its broadcast prompts and conflict detection provide terminal-centric coordination.

Plain tmux and screen handle the basics of pane management and session persistence, but they have no concept of AI agents, no broadcasting, no file locks, and no specialized dashboards.


Who Is NTM For?

Good fit for:

  • Developers running three or more AI agents in parallel on a regular basis
  • VPS-based workflows where SSH persistence is required
  • Teams where multiple agents touch the same codebase and conflict detection matters
  • Power users who already live in tmux and want agent-aware extensions

Not the best fit for:

  • Single-agent workflows where NTM adds unnecessary overhead
  • macOS users who prefer GUI terminals
  • Developers who are not already comfortable with tmux basics
  • Teams that require highly mature, heavily documented tooling

FAQ

What is NTM?
NTM (Named Tmux Manager) is a free, open-source tool that turns tmux into a multi-agent command center, letting you spawn, tile, and coordinate Claude Code, Codex, and Gemini CLI agents with broadcast prompts and conflict detection.

Is NTM free?
Yes, NTM is free and open-source under the MIT license.

How does NTM compare to cmux?
NTM builds on tmux and works on any OS, featuring broadcast prompts and conflict detection. cmux is a native macOS terminal built on Ghostty with a built-in browser.

Does NTM work over SSH?
Yes, NTM sessions persist through SSH disconnections. You can detach and reattach without losing agent state.


Verdict

NTM solves a real problem for a specific audience. If you are running multiple command-line agents in tmux and managing them by hand, NTM removes a meaningful amount of friction. The broadcast prompts save time, the conflict detection prevents file-overwrite failures, and the dashboard tracks status without pane-switching.

It is still early in its development lifecycle, meaning the community is small and the documentation is thin in places. You will also need to be comfortable with tmux before NTM adds value. However, the tool is free, open-source, and specifically targets the exact pain points of multi-agent terminal workflows.