Spatial canvas for terminal work
Work on an infinite canvas where terminals, agents, editors, diffs, sticky notes, and groups appear as nodes. This makes it easier to keep related work visible instead of switching between stacked windows.
nodeterm
nodeterm is a desktop tool for running terminals and coding agents as live nodes on an infinite canvas. It supports macOS and Linux, with persistent sessions, context linking, and mobile continuation via QR pairing.
What nodeterm is
nodeterm is a desktop environment for working with terminals and coding agents on an infinite canvas. Instead of managing jobs across separate tabs, it lets you place terminals, agents, editors, diffs, and related notes as live nodes in one spatial workspace.
The homepage emphasizes visibility and continuity: agents such as Claude, Codex, and Gemini run as nodes, sessions are backed by persistent tmux, and work can be restored after a reboot. It is positioned for macOS and Linux, with additional workflows for context linking, permissions, and remote session access from a phone.
Core features
Live agent nodes with status badges
Run Claude, Codex, and Gemini as live nodes and watch status changes such as RUNNING or NEEDS YOU directly on the canvas. Subagents also fan out as they spawn, so parallel work stays visible.
Context linking between nodes
Draw edges between agent nodes so one node can read another node’s context on demand. You can also branch a conversation into a fresh node without losing the original thread.
Session persistence and restore
Persist terminal work in tmux-backed sessions so reopening the app after a reboot returns you to the same processes, scrollback, and running agents. The homepage specifically describes restoring multiple sessions after restart.
Inline prompts and permission handling
Handle permissions from the node itself when an agent blocks and requests input, and get a ping when attention is needed. This keeps approvals tied to the exact session that needs them.
Mobile access and voice input
Continue a live session on mobile by pairing with a QR code, and talk to the terminal with a voice flow that uses on-device Whisper. The page says voice never leaves the machine.
Practical use cases
Managing active development work
Keep a project’s terminals, agents, notes, and diffs visible in one workspace so you can follow multiple threads without juggling tabs.
Supervising coding agents
Start an agent task, watch its status, and respond when it asks for permission or input without losing track of the original terminal context.
Branching and coordinating agent conversations
Link one agent’s context to another when a task branches, so follow-up work can read prior context while preserving the original thread.
Resuming work after interruptions
Reopen the app after closing it or rebooting the machine and return to the same tmux-backed sessions, scrollback, and running processes.
Checking in remotely on a session
Continue a live session from a phone by pairing with a QR code when you need to check progress or respond away from your desk.
Pros and Cons
Pros
- Brings terminals and agents into one spatial canvas instead of scattering them across tabs.
- Shows live agent state directly on the workspace with running and attention-needed badges.
- Supports persistent tmux sessions, so work can survive app closure or machine reboot.
- Lets one node read another node’s context, which can help when branching or coordinating agent work.
- Adds mobile continuation through QR pairing, plus voice input with on-device Whisper.
Cons
- The pricing page currently returns a 404 in the supplied sources, so pricing and plan details are not available.
- Several capabilities are only described on the homepage, so details such as supported integrations, APIs, and broader documentation are not confirmed here.
FAQ
What platforms does nodeterm support?
The homepage indicates nodeterm works on macOS and Linux. No other operating-system support is shown in the provided source.
What kinds of nodes can you place on the canvas?
It is designed for terminals and coding agents on an infinite canvas, including live terminal nodes, agent nodes, editors, diffs, sticky notes, groups, and browser-related nodes shown on the homepage.
Which coding agents are supported?
The homepage names Claude, Codex, and Gemini as supported agents running as live nodes. It does not provide a fuller integration list.
Does nodeterm keep sessions after reboot or closing the app?
Yes. The page says every terminal lives in a persistent tmux session, and that reopening nodeterm restores sessions, scrollback, and running agents.
Can you access a session from a phone?
The homepage says you can pair your phone with one QR code and continue the same live session in your pocket over an end-to-end encrypted relay.
Quick Facts
- Category
- Developer Tool
- Platform
- macOS and Linux
- Primary workflow
- Run coding agents and terminals as live nodes on an infinite canvas
- Supported agents mentioned
- Claude, Codex, Gemini
- Source domain
- nodeterm.dev
- Pricing
- Not available in the provided sources; pricing page returns 404
Alternatives à nodeterm
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
Redline
Redline is a budgeting tool for Claude Code that paces sessions to stay within time, token, cost, or plan-percentage limits. It uses Claude Code’s native hooks and statusline to help sessions finish with a usable result instead of stopping abruptly.
SonOf
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.