Start
Start a task the moment you think of it
Type or dictate it, pick any agent CLI, and it starts in a workspace of its own while you keep working.
Your attention is the bottleneck, not the agents.
Komla shows you which agent needs you next.
“I've tried so many different orchestrators, and I've not resonated with a single one until Komla. I typically sling 10+ terminal sessions across 4-5+ projects — I'm now moving all that to Komla.”
Start a task the moment you think of it, step in only where you're needed, and get straight back to what you were doing.
Focus
Every card shows whether its agent is working, done or waiting on you. When one asks a question you get a sound and a notification, and ⌘⇧A jumps straight to it.
Start
Type or dictate it, pick any agent CLI, and it starts in a workspace of its own while you keep working.
Switch
⌘P finds any workspace by title, branch or description, starting with the ones that need you. Each one keeps its terminals and tabs just as you left them.
Remote
Run them on any Linux or macOS host over SSH. Komla still shows every diff, agent and dev server as if they ran on your laptop.
Claude Code in one workspace, Codex in the next. Komla has presets for the popular ones, and any agent that runs in a terminal works too.
Komla runs the real CLI, not a chat wrapper, so every new model, flag and slash command works right away, the way its makers designed it.
You need Git and an agent CLI, such as Claude Code or Codex.
Coming from another tool? See how Komla compares with Conductor, cmux and the Codex app.
Agents create workspaces, start agents and open previews.
Run an agent on a schedule, each run in its own workspace.
Bundle status items, sidebar panels and hooks into one integration you turn on or off.
Add your own tab beside Diff and Files, fed by a command or a plugin.
Agents and scripts add live items to the bar, with links and popovers.
Dev servers open beside the agent, even over SSH.
Run your own commands when an agent finishes, needs input, or a workspace starts, on this computer or the SSH host.
Save shell commands and agent prompts, then run them in any workspace from the tab bar.
See each workspace's pull request, CI checks and tags at a glance.
Review an agent's changes in a split or unified view, roll back a block or edit a line in place.
Check on agents and answer them from your phone, tablet or another computer over your own Tailscale network, with a push notification when one needs you.
Dictate prompts offline, in 25 languages.
⌘P or Ctrl+Shift+P searches every workspace, command and shortcut, and finds files by name or content with ripgrep.
Every workspace in one inbox, the ones that need you first.
Pull, rebase, push and open pull requests from one menu.
Run a desktop app on a Linux host with komla desktop run, and use it
over VNC or in a browser tab.
Add a VM or container as an SSH host, and let agents skip permission prompts away from your own files.
Sync an SSH workspace to this computer to run desktop and mobile apps locally.
Copy files, install dependencies and run commands when a workspace is created. Your agent can read the repo and propose the steps.
Edit Markdown as rich text that saves back only what you changed, and draft prompts in per-workspace notes kept out of the repo.
Describe the look you want and an agent builds the theme, or pick one like Catppuccin or Dracula.
Link workspaces from different repos so one agent can read and edit across them.
Browse a workspace's commits as a graph and see the changes in each one.
See who last changed each line, and click through to that commit.
See every commit that changed a file, including across renames.
Browse and edit files in a built-in Monaco editor, with optional Vim mode. Open files update as the agent rewrites them.
Terminals, browsers and notes in tabs and split panes, arranged by drag and drop.
Archive, stop or delete workspaces in bulk, sort by activity, and filter by project or host.
Open several windows and move workspaces between them.
Change any shortcut, or reset them to the defaults.
Tabs work for two or three agents. Past that, the hard part is knowing which one is waiting on you, and keeping them out of each other's changes: Komla gives each task its own git worktree and shows on every card which agents need you.
It runs your real agent CLI in a real terminal, on your laptop or over SSH.
Side by side: Conductor, cmux and the Codex app.
Your code stays on your machine, and the agents talk to their own APIs, as they would in any terminal. Komla's two AI helpers are optional and send only this:
That text goes through OpenRouter to Google, OpenAI or Mistral, which don't train on it, and Komla doesn't store it. Turn either helper off or use your own key in settings.
Any agent that runs in a terminal. Claude Code, Codex CLI, OpenCode and Antigravity CLI come with one-click notifications and the Komla skill. Komla also has presets for Gemini CLI, Cursor CLI, GitHub Copilot CLI, Amp, Qwen Code, Mistral Vibe, Goose and more. Any other agent can set up its own notifications with a self-integration skill, or you can add it as a custom command.
Yes. Each workspace is a normal folder on disk. Open it in VS Code, Cursor, Windsurf or Xcode with one click, or point any other editor at it.
The macOS app is signed and notarized by Apple. Komla downloads new versions in the background and installs them the next time you quit it. On Linux that works when you run the AppImage file itself; otherwise Komla tells you a new version is out.
Archive a workspace to hide it, or delete it to remove the worktree and branch from disk. They're standard git worktrees, so you can also manage them with git.