work

A self-hosted web GUI for agentic dev workspaces — on desktop and as a mobile PWA. Spin up multi-repo worktree workspaces, run coding agents (Claude Code, Codex, Copilot, Cursor, Grok) or plain shells in real terminals, review diffs and send feedback to agents, and watch PR status — from any device.

• Workspaces — named directories of git worktrees (one per GitHub repo, cloned from a shared bare-repo cache), all on a generated branch. Create, add/remove repos, archive/restore, delete.
• Sessions — real CLIs in tmux, mirrored to the browser over WebSocket (xterm.js). Sessions survive server restarts and phone locks; agent hooks surface working / waiting / idle state at a glance.
• Review — a fast diff view across every repo in the workspace, with line comments you can send straight into an agent session.
• Mobile-first PWA — installable, with a touch-tuned terminal (sticky keyboard toggle, d-pad for arrows/tab/ctrl-c, momentum scrolling).

Install (bare machine)

One command on a fresh Linux or macOS box — installs the system tools (git, tmux, a compiler for node-pty), mise + node, the published package, and the background service (systemd/launchd):

curl -fsSL https://cdn.jsdelivr.net/npm/@dylanpiercey/work/install.sh | bash

Already have node (and git/tmux)? npm i -g @dylanpiercey/work && work setup does the same minus the system tools. Update later with work update (or re-run the installer).

Develop

Requires Linux or macOS with git, tmux, gh (authenticated), and Node 22+. The bootstrap script installs everything via mise, offers the agent CLIs, and runs pnpm install:

./scripts/bootstrap.sh

Run

pnpm dev                  # http://localhost:7171

For a production build plus a background service (systemd on Linux, launchd on macOS):

./scripts/setup-prod.sh   # build + install + start the service

# While hacking on work itself, point the background service at a checkout
# (and back at the npm install when done):
cp scripts/work-source.sh ~/.local/bin/work-source && chmod +x ~/.local/bin/work-source
work-source local          # this tree (or: work-source local /path/to/work)
work-source rebuild        # rebuild + restart without rewriting the unit
work-source prod           # global @dylanpiercey/work again
work-source                # status
./scripts/run-prod.sh     # or: build with --no-service and run manually
./scripts/update.sh       # later: pull latest, rebuild, restart

To reach it from other devices, put it behind something that terminates TLS and authenticates — e.g. a Cloudflare Tunnel with Access, or Tailscale. Everything (pages, API, and the /term websockets) serves from the single app port, so route the whole hostname to it. Set WORK_ALLOWED_HOSTS=your.domain so the dev server accepts the hostname.

Upgrading from the two-port layout: older setups routed /term/* to a separate terminal port (7172). That port no longer exists — remove the /term rule from your tunnel/proxy config and send all traffic to the app port, or terminals will fail to connect.

Configuration

| Variable | Default | Purpose | | -------------------- | ----------------------- | ------------------------------------ | | WORK_ROOT | ~/work | Workspaces root (+ .cache bare repos) | | WORK_DATA_DIR | ~/.local/share/work | sqlite db and server state | | WORK_APP_PORT | 7171 | HTTP server (app, assets, and /term websockets) | | WORK_ALLOWED_HOSTS | — | Extra dev-server hostnames (comma-separated) | | WORK_USER / WORK_HOST | current user/host | Branch-name prefix parts | | WORK_BRANCH_PREFIX | <user>-<host> | Whole branch-name prefix, overriding the parts |

Ports and paths can be exported before scripts/setup-prod.sh to bake them into the service. For settings that should outlive an update, put them in an untracked .env.local at the repo root instead — scripts/run-prod.sh reads it on every start (the dev server does not), only WORK_* names apply, and the surrounding environment still takes precedence:

WORK_BRANCH_PREFIX=rturnq

The usage panel (and work usage) reads plan/quota windows straight from each agent CLI's own credentials on disk — Claude, Codex, Cursor, Grok, and Copilot (via gh's token). Providers you are not signed into simply say so.

Running more than one work (a laptop and a desk box, say)? Settings → Appearance gives each a name and an accent colour: the tab title, home-screen icon, notifications, and the app's chrome all take them, so two windows or two installed apps stop looking identical.

PR chips refresh by polling GitHub (faster for a few minutes after a local push via repo-pushed). No inbound GitHub webhooks are required.

Layout on disk

• ~/work/<slug>-<id>/ — a workspace: one worktree per repo + generated AGENTS.md (and CLAUDE.md symlink) encoding the conventions
• ~/work/.cache/github.com/<owner>/<repo>.git — shared bare-repo cache
• ~/.local/share/work/work.db — sqlite database (authoritative state)

Terminals live in a dedicated tmux server (tmux -L work), kept alive by a transient systemd unit so app restarts never kill your sessions.