Termic runs several agents in one window, so you’re not juggling a pile of terminal tabs and losing track of which is which.
Three kinds of parallel
There are three ways to run agents in parallel:
Many tasks, many branches. Open three worktree tasks, each on its own branch with its own agent, each working on something different. They can’t collide because each is a separate checkout on disk. Use this when the tasks are independent: fix a bug here, add a feature there, bump a dependency in a third.
Many agents, one branch. Inside a single task, ⌘T opens another tab. You can run a second agent (even a different CLI) against the same working tree. Useful when you want one agent implementing while another reviews, or when you’re comparing how claude and codex each approach the same file.
Many agents, one prompt. An agent race fires the same prompt at several agents at once, each in its own fresh worktree on its own branch. You compare them side by side when they finish and adopt one into your main checkout. Use it when the approach is the open question rather than the task.
Forking an attempt
When an agent is partway through something and you want to try a different direction without losing its progress, use Duplicate worktree from the task menu. It seeds a new task from the current branch tip, so you get a second agent starting from exactly where the first one is. Let both run and keep the better result.
Keeping track of them
The work-done indicator shows which agent needs you: a blue dot lands on a tab the moment its agent finishes a turn, and an orange bell appears when an agent is blocked waiting for your input. You glance at the sidebar, see what’s done and what’s stuck, and go to the one that needs attention. Optional desktop notifications tell you even when Termic isn’t focused.
The sidebar keyboard navigation is built for this: ⌥⌘↑ / ⌥⌘↓ hop between tasks, ⌘[ / ⌘] move through them in sidebar order, and ⌥↑ / ⌥↓ walk every visible row including each task’s tabs. See Keyboard shortcuts.
Ask everyone at once
When you want the same thing from multiple agents, Broadcast (⇧⌘B) sends one prompt to every agent in a task concurrently. It’s built for comparison: ask a question, let three agents answer, read the differences.
Running them safely
Run unattended agents with the sandbox on. Each agent then runs in its own macOS Seatbelt cage with a network allowlist, and Termic skips its per-action permission prompts, since the OS cage enforces the limits instead. None of them can read your secrets or reach a host you didn’t allow.
When parallelism pays off
Parallel agents help when you have independent work, or when comparing approaches is worth the tokens. They don’t make one task finish faster.
Related
- Tasks & worktrees: the isolation that makes parallel safe.
- Work-done & notifications: knowing which agent needs you.
- Agent races: one prompt, several agents, several branches, one winner.
- Broadcast: one prompt, many agents.
- Scheduled messages & Ralph-style loops: keep one agent moving across several turns.