Agentbox并行管理编程代理

A desktop GUI for running dozens of Claude Code and Codex agents in parallel, each in its own git worktree. Answer them like email, or us…

Agentbox Give your agents an inbox. Run dozens of Claude Code and Codex agents in parallel, each in its own git worktree, and only hear from the ones that need you. Get it · How it works · Priorities · Keys · Privacy · GPL-3.0 Free and open source. A Mac app, or in your browser on any platform with npx agentbox-app, on the Claude Code or Codex plan you already have. No server, no account, no extra subscription. Install There are two ways to run it: in the browser, or as a Mac app. Both need Node 22 and Claude Code or Codex installed and signed in. In your browser. One command, nothing to install first: npx agentbox-app It starts on your machine and opens a tab. On Linux that open goes through xdg-open. Nothing is hosted: it listens only on 127.0.0.1, and the address carries a key that is new every run. Add --help to see the options. --no-open prints the address and leaves the browser to you. From a checkout, build the screen once, then start it the same way. The install links the checkout's own command, so npx runs this copy rather than looking for agentbox on your PATH: npm install npm run build npx agentbox-app As a desktop app. Build it from this repo. npm start is the desktop command on Omarchy and on a Mac: git clone https://github.com/savannahfeder/agentbox.git cd agentbox npm install npm start On Linux, npm install puts agentbox on ~/.local/bin and adds the app to the launcher. The entry is $XDG_DATA_HOME/applications/agentbox.desktop (~/.local/share/applications when that variable is unset), and it runs agentbox. That command starts this checkout, and it is written before Electron has downloaded its binary, so the first launch off the launcher does that download. Open the app from the launcher. Two of this repo's dependencies need an install script to work: node-pty, which is the terminal, and esbuild. package.json names them in allowScripts, by name rather than pinned to a version, so a dependency bump does not need re-approving. electron-winstaller is denied there: it is only for packing a Windows installer, which this repo does not do. npm 11 and newer print anything in neither list on every install, and npm approve-scripts --allow-scripts-pending lists them. npm start builds the app and opens it. On first run it walks you through connecting Claude Code or Codex and choosing a folder to work in. On macOS, the system may ask to let Terminal find devices on your local network. Agentbox does not need that, so Don't Allow is fine. The chat window is the bottleneck Today you run agents in chat windows and terminals, and you wait for each one to finish before you prompt it again. So the number of agents you can run is limited by the number of windows you can keep track of. Models are now good enough that most tasks do not need watching. They need someone to review the work at the right moment. Agentbox drops the chat window and gives each agent a row in an inbox instead, so you can run far more of them than you could ever watch and only deal with one when it actually needs you. How it works 1. File the work Paste a list, send over a board of issues, or type one task. Each item becomes its own row, and each row is its own agent, already working in its own git worktree and on its own branch, so no two agents touch the same files. 2. Walk away Nothing needs you while they run. Go to lunch. A row only comes back to you when its agent is done or stuck, so a hundred agents working is as quiet as one. 3. Come back to an inbox Every row opens with what the agent did and what it wants from you, in two lines you can read at a glance. Most of the time the answer is yes. Press 1 and it merges, and the next one is already in front of you. 4. Answer however fits Pick a design. Ask for options before anything is built, and agents come back with versions drawn in your actual app. Pick one and that one gets built. Send it back. When none of the options is right, type a sentence. The agent picks up where it left off, and the row comes back to you when it is done. 5. Stay the person in the loop Your job stops being watching agents work. It becomes reviewing what they made and deciding whether it is good enough. This agent got a failing test to pass by editing the test instead of the code, which is exactly the moment you want to be asked. Code changes open right beside the row. What matters most goes first Twenty agents means twenty things competing for your attention and for a limited number of running sessions. Agentbox keeps one order and uses it for both. Tag a task Urgent, High, Medium or Low, when you file it or later from ⌘K or Ctrl+K. Rank your projects once by dragging them into order. A project's place counts for more than any single task's tag, so your most important project never waits behind a side one. The order decides who starts. When there are more tasks than session slots, the queue starts the most important first. An answer you have already given wins a tie against new work, so replies never pile up. Urgent rises to the top. Urgent rows sit above everything else in the inbox under their own heading. Only your tags count. An agent cannot promote its own work. If it says its task is urgent, that is ignored. Any row's priority is a ⌘K or Ctrl+K away. Built for the keyboard Key Does J K or arrows Move through the inbox Enter Open a row E Approve the recommendation, or mark a row done 1 2 3 Pick an option an agent offered R Reply N New thread L Later: put a task off until a time you pick S Show or hide the summary, in an open task Z Undo ⌘K or Ctrl+K Everything else Fifteen skins, each in light and dark, from plain slate to woodblock and riso prints. Press ⌘K or Ctrl+K and type "theme". Ctrl+K is the same palette on Linux, where there is no Command key. Runs on the plan you already have Agentbox drives Claude Code and Codex on your own machine, signed in with your own subscription. When you first open it, it finds the agents you have already set up and offers to bring them in. There is no