ace drives Claude Code, Codex, Cursor and the other CLIs you already use, and tells you which one needs you.
ace starts each CLI the way you would in a terminal. Logins and subscriptions stay with the CLI. ace never asks for or stores a key.
Any agent that speaks ACP works too, including
A thread's status covers every subagent and background command it started. If a subagent still runs, the thread says Waiting, not Done.
Code is half the job. Agents open the page, click through your Mac's apps and test on iOS and Android, while you watch and keep the controls.
Agents open your dev server in ace's browser, click through it and read the console and network log. You watch the same tab and can take over at any moment.
Tools: browser_openbrowser_snapshotbrowser_actbrowser_logs
Agents work in your Mac's apps in the background, without taking your mouse or keyboard. Each session shows who is in control, with Take over and Stop beside it.
Tools: screen_appsscreen_statescreen_act
Run iOS Simulators and Android emulators inside ace. Tap, type and rotate them yourself, or hand a device to an agent to test your app.
Tools: sim_listsim_startsim_uisim_act
Give a thread its own git worktree and its changes stay apart. Comment on a line, send the comment to the agent, then commit and push from the same panel.
Run agents on your laptop, a build server and a workstation, and steer all of them from whichever screen is closest.
Agents on your laptop can start threads and open browsers on your build server, and every thread shows in one list.
Pair a phone, tablet or browser with a link or QR code. Choose view only or view and act, and how long access lasts.
Connect over your local network, Tailscale, or an end-to-end encrypted relay you can host yourself.
ace runs an MCP server for each agent session. Whichever CLI runs the agent, it gets the same tools, and your CLI's own permission mode decides what runs.
Start agents on any provider or machine and wait for them
delegatewaitagents_statusagent_messageOpen, read and drive pages you can watch
browser_openbrowser_snapshotbrowser_actbrowser_logsUse Mac apps in the background
screen_appsscreen_statescreen_actDrive iOS Simulators and Android emulators
sim_listsim_startsim_uisim_actFind work, start threads and keep project notes
contextthread_startthreads_findnote_addPut pages, images and alerts in front of you
html_renderimage_shownotifySchedule prompts and run them on demand
automation_putautomation_runA small daemon lives next to your code. It owns the agent processes, terminals and worktrees. Provider credentials never pass through it.
Move a thread from Claude to Codex with its context, or send one task to several agents and keep the best result.
Open them as full pages, link them to the thread that wrote the code, and merge once checks pass.
Run a prompt on a schedule, like a nightly flaky-test sweep. Each run gets its own thread to read in the morning.
Agents post charts, diagrams and interactive pages straight into the thread, and they replay with it later.
Open a shell in the thread's worktree, watch the commands an agent left running, and stop them from the composer.
ace is a desktop app for running coding agents. It starts the agent CLIs you already have installed, such as Claude Code, Codex and Cursor, gives each task its own thread, optionally in its own git worktree, and shows which threads are working, waiting or need you.
No. ace runs each agent through its own logged-in CLI, so your existing subscriptions and logins keep working. ace never asks for, stores or proxies provider credentials.
Claude Code, Codex, Cursor, OpenCode, Antigravity and Pi are built in. Any agent that speaks the Agent Client Protocol (ACP) also works, including Gemini CLI, GitHub Copilot, goose, Amp and Qwen Code.
Yes. Agents drive ace's built-in browser, use Mac apps in the background through computer use, and run iOS Simulators and Android emulators from the devices hub. You watch each one live and can take over or stop it.
ace runs an MCP server for every agent session, so Claude Code, Codex, Cursor and the others all get the same tools: start and wait on other agents, drive the browser, apps and simulators, show pages and images in the thread, and schedule automations. Your CLI's own permission mode decides what runs.
Fleet links your machines and devices. Linked machines let agents start threads and use browsers on each other, and paired phones, tablets and browsers can follow and steer agents. Machines connect over your local network, Tailscale, or an end-to-end encrypted relay.
ace runs on your own machine and is never hosted. Your code goes only where your agent CLI already sends it. When you pair another device, it connects through an end-to-end encrypted relay that you can host yourself.
Yes. Start each thread in its own git worktree and the agents never overwrite each other's files. You review each thread's diff, comment on lines, and commit and push from the same panel.
ace runs on macOS with Apple silicon. Download the disk image, open it and drag ace to Applications. The app checks for new releases and updates itself.
Yes. ace is open source under the Apache-2.0 license. You pay only for the agent subscriptions you already have.
ace is Apache-2.0. Install the Mac app, point it at a project, and start a thread with any agent you have logged in.