agentic-kanban 0.0.3

Kanban board for managing AI agent sessions

kanban

A kanban board for managing AI agent sessions. Each ticket is bound to an agent session (Claude Code, pi/Ollama, …) running inside its own git worktree, executed in the target repository's existing devcontainer. The active harness is selected globally in the app's settings.

Run

SOURCE=$HOME/code
docker run -d --name kanban \
  --restart unless-stopped \
  -p 127.0.0.1:7474:7474 \
  -p 13000-13099:13000-13099 \
  -v $XDG_RUNTIME_DIR/docker.sock:/var/run/docker.sock \
  -v $HOME/.claude:$HOME/.claude \
  # Agent config dir. Claude Code reads ~/.claude; for other harnesses
  # (e.g. pi/Ollama) substitute or add the relevant path.
  -v $SOURCE:$SOURCE \
  -v $HOME/.local/share/kanban:$HOME/.local/share/kanban \
  -e HOME=$HOME \
  -e XDG_RUNTIME_DIR=$XDG_RUNTIME_DIR \
  -e KANBAN_DATA_DIR=$HOME/.local/share/kanban \
  -e GH_TOKEN=$(gh auth token) \
  lahmanja/kanban:latest

Open http://localhost:7474.

Build

cd kanban
docker build -t kanban:dev .

Per-task ports

Optional <worktree>/.kanban.toml associates .vscode/tasks.json labels with container ports:

[[task]]
label = "Start Frontend"
container_port = 3000

[[task]]
label = "Start Backend"
container_port = 8080

When a task with an associated port runs, kanban allocates a host port from 13000-13099 and runs a TCP proxy.