Blog
What’s new in TRMNLY
What shipped, why, and what it means for the terminal you work in. Every claim links to its source.

Guide ·
The Best Terminal for Claude Code in 2026: iTerm2, Ghostty, Warp, Kitty, WezTerm, cmux and TRMNLY Compared
An honest roundup of terminals for Claude Code: what works out of the box, what needs setup, and which one fits one session, many parallel agents, or a team. TRMNLY included, with its catches.

Guide ·
Ghostty vs Warp: An Honest Terminal Comparison From the Team Building TRMNLY on Ghostty
Ghostty is a fast, free, standards-first terminal with no AI. Warp is an AI-first agentic environment with accounts and paid plans. Here's how they differ, who each suits, and where TRMNLY fits.

Guide ·
How to Run Docker on a Mac Without Docker Desktop: Colima, OrbStack, Apple's container and the TRMNLY Terminal
Four ways to run containers on macOS without Docker Desktop, with the install commands for each: Colima, OrbStack, Apple's container CLI, and the engine built into the TRMNLY terminal.

Guide ·
How to Use Claude Code From Your iPhone: Three Ways to Control Your Mac's Terminal Remotely, Including TRMNLY
Claude Code runs on your computer, but you can drive it from an iPhone. Here's how with Anthropic's Remote Control, with SSH and tmux, and with the TRMNLY terminal's iPhone remote.

Guide ·
How to Run Multiple Claude Code Agents in Parallel With Git Worktrees (in Any Terminal, or TRMNLY)
Give each Claude Code session its own git worktree so parallel agents never edit the same files. Step-by-step commands, the gotchas, and how the TRMNLY terminal automates it.

Perspective ·
TRMNLY Is an Agentic Development Environment. Here's What That Means in Practice.
An agentic development environment needs a gate on what agents run, a way to run several at once, tools that reach the whole machine, and a way to follow the work when you walk away. This is how TRMNLY does each.

Perspective ·
ADE vs. IDE: What Changes When the Agent Does the Typing
An IDE is built to help you write code. An agentic development environment is built to help you direct, check and run agents that write it. Here is where the two differ, point by point.

Perspective ·
From IDE to ADE: Why Development Environments Are Being Rebuilt Around Agents
For fifty years the development environment was built around a person typing. Coding agents changed who types, and a new kind of tool, the agentic development environment, grew up around them.

Models ·
Bring Your Own Model. We Don't Touch Your Tokens, and We Don't Mark Them Up.
TRMNLY's agent runs on Anthropic, OpenAI, Gemini, OpenRouter, any OpenAI-compatible server or a local model through Ollama. With your own key, a turn costs no TRMNLY credits.

Containers ·
You Can Run a Container on Your Mac Without Installing Docker. TRMNLY Does It Itself.
On macOS 26 with Apple silicon, TRMNLY's built-in engine runs each container as its own lightweight microVM. Docker Desktop, OrbStack and Colima still work too, all in one list.

Workflow ·
Five Agents, Five Branches, One Repo. Nobody Steps on Anybody.
TRMNLY gives each agent its own git worktree, and Fleet lets a pool of them work your task board while you decide what lands.

Integrations ·
Claude Code in Your Terminal Just Got More Than 400 New Tools
TRMNLY's MCP server hands every tool its own agent has to Claude Code, Codex and any other MCP client, behind the same approval gates. One command connects it.

Safety ·
Approving Everything Isn't a Safety Model. Here's What TRMNLY Does Instead.
TRMNLY's agent approvals come in three postures, with READ and WRITE tags on every tool, rules scoped to a host or folder, a destructive-command gate that fires even on Auto-accept, a signed audit log and per-write snapshots you can revert.

Safety ·
Hands Off the Keyboard: TRMNLY Can Lock Your Mac While the Agent Drives It
Agent Lock blocks your keyboard and mouse and covers every screen while an agent run is in progress. If TRMNLY crashes mid-run, a separate watchdog process locks the real macOS screen.

Agent ·
Your Terminal's AI Can Google Things Now, and It Has to Show Its Work.
Every TRMNLY chat has a web search toggle as of 0.1.103. Claude chats use Anthropic's own search and list numbered sources, other providers fall back through your search keys, and none of them return a silent "no results".

Workflow ·
We Put a Kanban Board Inside Your Terminal. Your AI Agents Use It Too.
TRMNLY projects have task boards that people and agents share. As of 0.1.106 you can tick off a card's checklist from any shell with `trmnly task tick`.

Privacy ·
Our App Phones Home When It Breaks. Here's Exactly What It Will Never Send.
TRMNLY 0.1.105 and 0.1.108 widened error reporting to hangs, crashes and failed stores, and added a test button that shows what happened to the last report. Prompts, replies and terminal output never leave your machine.

Cloud ·
Close Your Laptop. Your Claude Code Session Keeps Going.
TRMNLY can move a running Claude Code session from your Mac into a cloud workspace, with the same conversation and your uncommitted files. As of 0.1.104 it also leaves your secrets behind.

Security ·
Your iPhone Can Now Type Into Your Mac's Terminal. Here's Everything We Did So Nobody Else Can.
TRMNLY 0.1.104 hardened the iPhone remote with per-device scopes, expiring invites, a who's-connected list and a single kill switch. Here's what changed and why.

Under the hood ·
Your AI Agent Was Paying for 94,000 Tokens Before You Typed a Word. We Cut It to 7,000.
TRMNLY's agent used to send every tool's schema with every request. As of 0.1.103 it sends only the tools the conversation needs, so each turn is cheaper and leaves more room for you.

Release notes ·
We Found About 300 Bugs in Our Own AI Agent. Here's What Was Hiding in There.
A fourth audit of TRMNLY's agent sidebar turned up about 300 bugs, from deny rules that sudo could slip past to an approval that answered the wrong message. All of them are fixed in 0.1.108.