nodeterm

作者 eneskirca

Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.

1,058
Stars
112
Forks
TypeScript
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/eneskirca/nodeterm

快速入门

使用 nodeterm 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

nodeterm

A node-based terminal manager — your terminals and agents on an infinite canvas.

Multiple real terminals live as draggable nodes on a single pan/zoom canvas, and every project doubles as a Trello-style board of live Claude Code sessions. Built for people with ADHD and scattered workflows: a spatial layout instead of a stack of hidden tabs.

Platform Built with Electron License GitHub stars Latest release

Downloads

Download · Docs · Features · Build from source · Architecture · License

Why nodeterm

Stacked terminal tabs hide context — you lose track of what's running where. nodeterm turns that into a map: every shell is a node you can place, group, label, and zoom into. Sessions are spatial and persistent, so your mental model stays intact across restarts. And because the app is built around a clean service seam, the same canvas runs three ways — as the desktop app for macOS and Linux, as a self-hosted browser app you reach from anywhere (Server Edition), and an iOS companion that attaches to the same live sessions.

📚 Full documentation lives at nodeterm.dev/docs — get started, concepts, agents, remote access, troubleshooting.

✨ Features

Everything is a node

Right-click the canvas to open a terminal — or an AI agent. Each runs in its own persistent tmux session, next to sticky notes (link one to feed an agent context), Monaco editors, diff views, and web/video nodes — arranged spatially, like a map. Quit the app, even restart the machine — every session comes back.

Know when an agent needs you

Hook-driven status — no output scraping: pulsing RUNNING / NEEDS YOU badges, subagent cards with live transcripts, a per-node context meter, and OS notifications. Click the ping, answer the permission prompt right in the node, and get told the moment the turn is done. On a MacBook, agents live in the notch too.

One project, two views

Every project is a canvas — and also a kanban board. Cards are your live sessions: drag them across columns while the agent keeps running, open a card into a live card modal (the real session + members, due date, priority, comments), and assign teammates. Toggle with ⌘⇧B. ▶ Watch the board video with sound

Your sessions, anywhere

Pair your phone with one QR — scan with the nodeterm iOS app — and the same live session continues in your pocket, E2E encrypted over the relay, not just your LAN. The same canvas also runs self-hosted in any browser (Server Edition).

Talk to your terminal

Hold ⌘⌥ and say it. On-device Whisper transcribes locally — review the text, then Send (nothing auto-submits). Your voice never leaves the machine.

Node kinds

🖥 Terminal (xterm + tmux, AI naming) · 🤖 Agent (Claude Code / Codex / Gemini / GitHub Copilot / opencode / Grok / custom) · 📝 Sticky note (link to an agent as context) · 🗂 Group (bind to a git worktree for agent-per-branch) · ✏️ Editor (Monaco, ⌘S) · 🔀 Diff · 🌐 Web / Video

More

  • Session continuity (tmux) — terminals keep running across node remounts and full app restarts, including live processes; machine reboots restore scrollback and resume agent sessions (claude --resume). The macOS app ships its own tmux, so this works with nothing installed; a tmux already on your system is always used in preference to it, and terminals opened before an upgrade stay as they were until you refresh the node.

  • Talk to your terminal — on-device Whisper dictation (hold ⌘⌥): speak, review, send.

  • Agent superpowerscontext links so agent nodes read each other's transcripts on demand; Claude-only branch a conversation and managed accounts for several logged-in Claude identities side by side; agents can drive the canvas (open nodes, spawn teams, verify each other's work) via the built-in canvas-control CLI.

  • Remote / SSH projects — open a project on a remote host over SSH; terminals, files, git, and even the board run there while the canvas stays local.

  • Source control — VS Code-style stage/unstage, discard, branch switch/create, commit, push/sync/publish, worktrees, and gh sign-in — backed by system git.

  • GitHub Issues on Kanban – opt-in issue cards, exact label-to-column mapping, All / GitHub / Sessions filtering, and two-way move, close, and reopen sync. See setup and security details.

  • AI commit messages & terminal names — bring-your-own local agent CLI run read-only on the staged diff or captured output.

  • Your sessions, in your pocketnodeterm mobile (iOS) attaches to the same live tmux sessions: watch an agent work, answer a "needs you", or type into any terminal from your phone — plus push notifications and a mobile board view.

  • Power & sleep — while an agent is working, nodeterm keeps the machine from idle-sleeping, and lets go the moment it finishes (on by default; toggle in the setup tour or Settings → Behavior). No app can hold a machine awake through a closed lid — for overnight runs keep the laptop open and plugged in, or run the agents on a box that doesn't sleep via the Server Edition.

  • Command palette (⌘K), file explorer (⌘⇧E), markdown view (⌘M), undo/redo, and a native macOS dark UI.

  • Auto-update & in-app announcements — the app checks a self-hosted feed and surfaces a "Restart to update" banner and product news.

🌍 Server Edition — nodeterm in your browser

The same canvas runs headless on a Linux (or macOS) host and is used from any browser — so your terminals, editors, source control, board, and agents live on a server you reach from anywhere. Single-user auth (password + secure cookie), a WebSocket bridge, and the exact same renderer as the desktop app.

npm run server:dev     # build + serve; open http://127.0.0.1:8443 and set a password

Terminals, files/editor/diff, the full git panel, the kanban board, and agent-status badges all work in the browser today. See docs/SERVER.md for the quickstart, security model, and current limitations.

🔔 Get push notifications from any SSH host

The same server also runs headless as a background notification host: install it on any Linux box you SSH into, and your phone gets RUNNING / NEEDS YOU push + Live-Activity coverage for the agents running there — with zero open ports (the hook server stays loopback-only and push goes out over HTTPS under a grant your phone drops over SSH).

curl -fsSL https://raw.githubusercontent.com/eneskirca/nodeterm/main/scripts/install-server.sh | bash

One line installs, builds, and runs it as a systemd service (NODETERM_HEADLESS=1); re-run it to update. See the headless notification host section for details.

📦 Download

Grab the latest build from nodeterm.dev — the download button detects your platform. Everything is also listed at nodeterm.dev/releases:

  • macOS.dmg f

常见问题

What is nodeterm?

nodeterm is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by eneskirca. Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition. It has 1,058 GitHub stars.

Is nodeterm safe to use?

nodeterm returned warnings in SkillsLLM's automated security scan. It has no critical vulnerabilities, but review the flagged issues in the Security Report section before adding it to your workflow.

How do I install nodeterm?

Clone the repository with "git clone https://github.com/eneskirca/nodeterm" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is nodeterm written in?

nodeterm is primarily written in TypeScript. It is open-source under eneskirca on GitHub, so you can review or fork the full source.

Are there alternatives to nodeterm?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh nodeterm against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情