Skip to main content
Traycer has two terminal-looking surfaces with very different roles. One is an agent using the Terminal interface; the other is a plain shell. Throughout this page, “Terminal Agent” is shorthand for an agent you interact with through the Terminal interface. It is not a separate kind of entity from the agents in the Agents panel - it is one of the two interfaces those agents can use. They can look similar because both use a terminal surface. The difference is that a Terminal Agent is still a Traycer agent, while a Terminal is just a shell.

​
Terminal Agents

A Terminal Agent runs a coding agent in a PTY, but Traycer still wraps that session with Task context. Terminal Agents can receive:
  • Traycer’s system prompt
  • the Task id and agent identity
  • artifact instructions for specs, tickets, stories, and reviews
  • guidance for creating or updating artifacts as markdown files
  • Traycer skills and planning/execution instructions
  • agent-to-agent instructions and tools, as far as the coding agent supports them
That means a Terminal Agent is not the same as opening the coding-agent CLI yourself. Traycer prepares the session so the agent understands the Task, the artifact model, and the multi-agent environment.

​
Coding Agents That Support The Terminal Interface

The Terminal interface currently works with: This table is about which coding agents can run on the Terminal interface. It is a different question from which of them can receive agent-to-agent messages; see Agent-to-Agent. For the full compatibility matrix, see Agents & Models.

​
Plain Terminals

A Terminal is a shell session. Use it to run commands yourself: package scripts, tests, dev servers, logs, local debugging, or one-off shell work. A plain Terminal does not receive Traycer’s agent prompt, does not use Traycer skills, does not create artifacts by itself, and does not take part in agent-to-agent communication. It is not an agent session.

​
Start A Terminal

In a Task, click New terminal (+) in the Terminals panel.
  1. Choose the host the terminal runs on.
  2. Choose a folder: one of the Task’s workspace folders or worktrees on that host.
  3. Click Launch, or press ⌘↩ / Ctrl+Enter.
If the Task has no folders, the terminal starts in the Task’s own folder on that host, ~/.traycer/epics/<task-id>. The shell program comes from Terminal shell in Shell settings; you can’t pass a command when you launch. Terminals can also live outside a Task, in the terminal panel on the start page. Open it with ⌘J / Ctrl+J, or choose Terminal in its New tab chooser. See Panels.

​
Launch Setup

When you create an agent on the Terminal interface, you choose its launch setup:
  • workspace folder or worktree
  • coding agent
  • model, when supported
  • thinking effort, when supported
  • Terminal interface CLI arguments, when supplied
Those choices stay fixed after launch. Start a new Terminal Agent when you need a different workspace folder, worktree, coding agent, model, thinking effort, or argument set. Worktree choices are covered in Worktrees. Default CLI arguments for each coding agent are set in Providers. Traycer also keeps the upstream coding-agent session id for the Terminal Agent. When the app or host restarts and the same Terminal Agent is reopened on its original host, Traycer resumes the underlying coding-agent session instead of starting from scratch. Plain Terminals do not have a coding agent, model, thinking effort, or artifact behavior. They only need a host and a folder. In Start a new agent, choose Switch to Terminal, configure the launch, then click Start.

​
Agent-To-Agent Communication

Terminal Agents take part in agent-to-agent work, but referencing, reading transcripts, and messaging are separate capabilities, and what a Terminal Agent can do depends on its coding agent. The rules are in Agent-to-Agent. Traycer reads a Terminal Agent’s transcript from the coding agent’s own session history rather than terminal scrollback, so the record survives the terminal closing. Every Terminal Agent appears in the Task’s agent hierarchy either way, so you can always see where delegated terminal work came from. Multi-agent defaults are configured in Settings > Agent selection. Supported coding agents are listed in Agents & Models. If you are looking for a terminal-style coding agent, create an agent on the Terminal interface from the Agents panel. If you are looking for a shell you operate yourself, use Terminals.