TRMNLY · Sales deck · October 2026
A native terminal with an agent built in. It reaches the whole machine — hosts, containers, ports, the browser — not just the repository, runs on your own models, and asks before it does anything you have not allowed.
← → to move · F for fullscreen
The discount was applied after tax. I moved it ahead of applyTax(); rerunning the checkout suite to confirm.
of developers use or plan to use AI tools, up from 76% a year earlier[1]
of developers using AI agents have security or privacy concerns about them[1]
trust AI for important decisions; about half trust it only when they can verify the result[2]
The work agents are asked to do keeps growing, but what they can reach usually stops at the repository. A failing deploy, a port conflict or a dead container is outside it, and the safety controls teams want either do not exist or are a single on/off switch.
The terminal is Ghostty[7], with its emulation and GPU rendering unchanged. Your shell, tmux and key bindings behave as they always have. The agent, projects, connections, files and browser sit in sidebars you can hide.
The discount was applied after tax. I moved it ahead of applyTax(); rerunning the checkout suite to confirm.
Read any pane, run commands you can watch, queue work across splits and tabs.
Your saved hosts, port-forward presets and file transfers.
Docker and a built-in microVM engine, with shells into either.
Find what is listening, reserve ports per project, kill a stuck listener.
An in-app browser the agent can drive, with its console and network log.
Parallel worktrees per branch, diffs, review comments and PRs.
Projects, and every tab with the agent it is running and its status.
Ghostty, unchanged. The agent reads the pane that failed and runs in it.
Agent, prompts, queue, files and browser; each folds away when you don't need it.
TRMNLY does not ask anyone to give up the agent they love. Its MCP server gives Claude Code, Codex and Gemini CLI the same tools and approval gates as the built-in agent, and launches them on the subscriptions you already pay for. The built-in agent runs on Anthropic, OpenAI, Google, OpenRouter or a local model through Ollama; keys stay in the macOS Keychain.
Most-loved AI tool among engineers[3]
Ask, plan or auto-accept, switched with one key and kept across restarts.
Every tool is tagged, so approvals can be broad for reads and narrow for writes.
Allow a command on staging and still be asked on production.
It fires even on auto-accept. So does any tool you mark always-ask.
See what ran and revert a file the agent changed.
Blocks keyboard and mouse input and covers the screens while an agent works.
sudo systemctl restart apiPair an iPhone with your Mac and drive panes and agents over an encrypted tunnel. Approve a risky command from your pocket. Public beta on TestFlight.
A real Linux machine with a real shell, files kept between sessions, and the agent toolchain installed. It bills by the minute only while a terminal is open on it.[8]
| Cursor | ||||
|---|---|---|---|---|
| What it is | Native terminal + agent | Agentic terminal | Mac agent orchestrator | AI code editor |
| Terminal core | Ghostty | Rebuilt from scratch | None | Editor-embedded |
| Agent reach | Whole machine | Terminal and repo | Repo worktrees | Repo |
| Models | Your keys or CLIs, no markup | Credits; own key optional | Your CLIs | Usage at API rates |
| Entry price | $99 a seat, renew $69/yr; cloud $0.50/hr[8] | $20/mo Build[4] | Free; Pro $50[5] | $20/mo Pro[6] |
Competitor descriptions are our reading of their public pages on the dates listed under Sources. Product names and logos belong to their owners; no endorsement is implied.
TRMNLY is available today on macOS, with early-access accounts approved as they come in. A demo starts with an infrastructure problem of yours, not a toy repo.
Figures as of 19 October 2026.