dev-30

---

What using it looks like

Write a task → get a worktree → an agent works in it → you watch → you review → it merges

Six steps. You write the first one and approve the last; the middle four happen on the board.

1. Write a task, pick who does it

You describe the work and choose the agent. Claude Code, Codex, Gemini, Cursor Agent, opencode — or several at once, each in its own pane of the same task.

2. dev-3.0 builds the sandbox

A fresh git worktree off your base branch, a tmux session inside it, your per-project setup script, and — if you asked for them — free ports reserved for that task's dev server. Heavy directories like node_modules or .venv are copy-on-write cloned, so the sandbox costs near-zero disk and appears instantly.

Nothing the agent does can collide with another task. That is the whole reason ten of them can run at once.

3. Watch without opening anything

Hover a card and the live terminal comes to you. No clicking in, no losing your place on the board.

The card also carries the state you actually need at a glance: which agent and model, priority, memory use, a bell when the agent wants you, and a red badge when it asked a question.

4. Several agents on one task, side by side

Split panes in the same worktree — one writes, one reviews, one runs the tests. Or three independent variants of the same task on separate branches when you want to see which approach wins.

5. Read the diff before anyone merges it

The built-in review panel shows the whole branch diff with syntax highlighting, per-file read state, and inline comments on any line range. When you are done, one click copies the review back into the agent's terminal as a prompt.

Markdown, Mermaid and images render as a preview instead of raw diff lines, and the preview reviews like the rest of the diff: select any text and comment on it. The comment lands on the same source lines a gutter comment would, marks the block it belongs to, lists under the file, and joins the same review export.

Not sure the diff is safe? Launch a pack of read-only bug hunters — several agents that comb the same branch diff in parallel, each seeded to look somewhere different, and report only what they can prove.

6. Ship

The agent opens the PR and enables auto-merge. The card then shows the PR number and live CI state, so a red build finds you instead of you going looking for it.

---

What else is in there

Your whole day on one screen

Every project, every running agent, one Activity view.

One click away: what the fleet actually got done. Tasks shipped, lines changed, velocity, completion rate, active-day streak and average task lifetime — each against last week.

Spaces, when one flat list of projects stops working

Group projects into Spaces — Client work, Products, Infra — and the dashboard groups itself, with a rail that filters it down to one space. A project can sit in several spaces at once; nothing moves on disk and every project keeps its own board. Define no spaces and the dashboard is exactly the screen it was.

The board is yours to shape

Add your own columns — AI Review, PR Review, On Hold, whatever your pipeline actually is — and attach an agent to a column so that dropping a card there starts the work. Drag a task into AI Review and a reviewer agent spins up on its own.

It runs headless, and your phone is a client

dev3 remote

Serves the full UI to any browser over a Cloudflare tunnel, your LAN, or an SSH forward. Scan the QR once and your phone stays connected for 8 hours. Same board, same terminals, same live previews — on a dev box you never sit in front of.

Keyboard-first, because you switch tasks all day

⌘K jumps between projects, ⇧⌘P runs any action, ⌥Tab cycles live tasks with a preview of each.

A CLI the agents themselves use

dev3 is not a side door — it is how agents talk back to the board. They set the task overview, leave notes for whoever picks the task up next, ping you when blocked, show you an image or an interactive HTML report, start a peer task, or peek at another task's terminal without disturbing it.

dev3 attention "Need a decision on the schema"    # red badge on the card
dev3 show-image before.png --caption "the bug"    # in-app image viewer
dev3 peek --task seq:1383                         # read-only look at a peer's terminal
dev3 message --task seq:1383 --in 30m --subject "status check" "status?"   # type into a live agent, now or later
dev3 doctor --worktrees --prune-orphans           # reclaim disk from dead worktrees

An agent can hand you a document instead of scrollback

dev3 show-artifact report.html puts a self-contained interactive page into the task — charts, filters, sortable tables, its own light/dark switch. It opens beside the terminal that produced it, stays attached to the task, and downloads as a ZIP. No server, no upload, nothing external.

And the small things

Dark and light themes · a hand-tuned 16-color ANSI palette so agents look right in both · English / Russian / Spanish · one-click dev server per task with auto-assigned ports · labels and full-text search · sparse checkout for monorepos · scheduled and recurring agent runs · drag-and-drop files and pasted screenshots straight into a prompt · multi-window, one per monitor.

---

Why it works this way

AI writes the code now. It commits, opens PRs, reviews. Your job changed — from writing to commanding a fleet of agents across more tasks and projects than any one head can hold. The bottleneck moved: it's not your editor anymore, it's your focus. Everything above is built around that. Two things we optimize for, above all:

1. Your speed — as one person. dev-3.0 optimizes a single developer: you. The unit is always the individual, never the org. It works fine on a team — but it's not a tool for managing other people; it's a tool for each person to command their own fleet and hit their own top speed. Everyone focuses on themselves, and the whole moves faster.

2. Beautiful, and built around you. A cockpit you stare at all day should be fast, gorgeous, and keyboard-first — and it should bend to your way of working, not force one on you. Great tooling doesn't just make you productive; it makes the work fun again. We sweat the polish.

And what we refuse: dev-3.0 is not an IDE — and won't become one.

• The code is the agent's job. No embedded editor; one click to your real VS Code or Cursor when you truly need it — and the goal is to need it less.
• Git is the agent's job too. No manual staging, no hand-written commits.
• Integrate through your agent. Claude Code, Codex & co. already speak MCP to Linear, Jira, and the rest. dev-3.0 is the cockpit; your agent is the adapter.

Which is for you?

Other tools in this space are great — if you want to live in an editor. dev-3.0 makes a different bet. Pick by your goal, not a feature checklist:

If you want to…	Reach for…