Agents overview
An agent node is a terminal preset that launches a coding-agent CLI as its startup command, then tracks what the agent is doing on the node’s header. Under the hood it’s a real terminal like any other — see Node types — but nodeterm layers extra behavior on top, gated per agent by what that agent can actually report.
Built-in agents
Section titled “Built-in agents”nodeterm ships with four built-in agents. Creating an agent node runs the agent’s launch command once, as a one-shot startup command, and then clears it — the agent is never double-launched on the same node.
| Agent | Launch command | Brand color |
|---|---|---|
| Claude Code | claude | Clay (#d97757) |
| Codex | codex | Green (#10a37f) |
| Gemini | gemini | Blue (#4285f4) |
| opencode | opencode | Violet (#a78bfa) |
Add one from the pane right-click menu, the dock +, or the command palette (⌘K). Because
an agent node is just a terminal with a preset command, everything you already know about
terminals — persistence, scrolling, copy — still applies.
Capabilities by agent
Section titled “Capabilities by agent”Not every agent can do everything, so nodeterm turns features on per agent rather than assuming they all behave alike. The UI only offers what the agent supports.
| Capability | Claude Code | Codex | Gemini | opencode |
|---|---|---|---|---|
| Hooks-based status detection | Yes | Yes | Yes | Yes |
| Resume after reboot | Yes | Yes | Yes | Yes |
| Context link | Yes | Yes | Yes | Yes |
| Subagent visualization | Yes | — | — | — |
| Branch conversation | Yes | — | — | — |
| Chat nodes | Yes | — | — | — |
| Managed accounts | Yes | — | — | — |
| Permission modes | Yes | — | — | — |
| Usage indicator | Yes | — | — | — |
The Claude-only rows aren’t hardcoded specialness — they’re simply the features the other CLIs don’t yet expose the hooks or interfaces for. As Codex, Gemini and opencode grow those, the same UI lights up for them.
Custom agents
Section titled “Custom agents”You can define your own agents in Settings → Agents. A custom agent spawns like any built-in and shows process and terminal-title status — nodeterm knows whether the process is running and reads its terminal title — but it has no hook integration, so none of the richer behaviors above (status detection, subagents, branch, and so on) apply. Point it at any CLI you want to run as a node.
How status detection works
Section titled “How status detection works”nodeterm does not parse an agent’s output to guess what it’s doing. Instead, each agent’s own hook system posts to a small loopback HTTP server inside nodeterm whenever something happens — a turn starts, a tool runs, the agent finishes or waits for you. The header badge you see is driven entirely by those events.
See Agent status & notifications for what those states look like and how they reach you.