qcode

The approach

The container is what keeps the work apart.

• A container per agent

  Each agent runs in a container built from an image made for it. It sees the project folder and, if you allow it, the project's assets folder and the network.

• Free to work

  Because the container keeps the work away from your machine, the agent is set up to work without stopping to ask for permission.

• One login, a copy per project

  A profile signs in through the agent's own flow, once. Each project gets its own copy of the login, so chat history, memory and settings never leak from one project into another.

• Stopped when you are done

  When the last qcode closes, the containers it started stop. An optional background service does the same after a crash. Containers you started yourself are never touched.

• Podman or Docker

  Either engine works. qcode finds it, says when it is missing or not running, and shows the command that installs or starts it. It never installs anything and never raises its own rights.

• Nothing extra on your machine

  A git address is cloned inside a container, and files open in the project's own small base container, so neither git nor an editor has to be installed.

• Tabs that can hand each other work

  An agent in one tab can ask the agent in another for something and hear back. You approve the first message between two tabs, a tab without the network can never send to one that has it, and an exchange stops after six messages. What arrives waits on a line in the other tab until you pass it on.

• English and Turkish

  Every word on screen comes from a language file. More languages are welcome; the framework already carries nine.