Run your whole sprint in parallel.
Run Claude Code and Codex agents in parallel — one isolated worktree per ticket, terminal, browser, and dev server included. Every session lives on your sprint board. Switch in a keystroke, and your time tracks itself. 100% local, on your Mac.
The core idea
One ticket, one worktree. Everything stays in flight.
Every ticket gets its own git branch, its own directory, its own isolated environment. No stash-and-switch, no half-finished work bulldozed to look at something else. Workspaces group repos and worktrees per org or client — a color, an icon, instant switching, state kept per workspace.
- A branch, a directory, and an isolated environment per ticket
- Switching costs nothing — parallel work never gets stashed
- Workspaces group repos per org or context, color-coded with an icon
- ⌘K palette from anywhere: search every worktree in every workspace
Agents & terminals
Sessions that refuse to die.
Claude Code, Codex, and plain shells run per worktree on a local server — close the window and they keep working; reopen and reattach mid-thought. A session dock shows everything live across worktrees, and status hooks mean the board knows when an agent is working, waiting on you, or done.
- Per-worktree Claude Code, Codex, and shell sessions
- Owned by a local server — close the window, work continues
- Session dock: everything running, live, across all worktrees
- Status hooks: the board knows working / waiting / done per agent
- ⌘←/→ worktree switcher with live terminal miniatures — works inside embeds, commits on ⌘ release
The hub
One window per ticket. Zero app juggling.
Each worktree opens into a hub: terminal tabs, an embedded browser preview with docked DevTools, and embedded VS Code. ⌘←/→ flips between worktrees with live terminal miniatures — even while focus sits inside the browser or editor embed. ⌘K summons a palette from anywhere: search worktrees across every workspace, pick one, land in its hub.
- Terminal tabs, embedded browser preview, and embedded VS Code per worktree
- DevTools docked right beside the preview — inspect without leaving the hub
- Agents drive the preview themselves — screenshot, click, eval, console, network — via the bundled MCP browser bridge, scoped per worktree
Dev servers
Ports that sort themselves out.
Start and stop dev servers per worktree straight from the board, with live run status. Ports are auto-assigned, squatters on your port are evicted automatically, and when a start crashes on a conflict, Strado parses the real offending port out of the error output and retries. Env profiles carry the defaults; each worktree can override its command, env, preview URL, and port.
- Start / stop per worktree from the board, live run status
- Auto-assigned ports — squatters on your port evicted automatically
- Crash-retry that reads the actual conflicting port from the error output
- Env profiles plus per-worktree overrides: command, env, preview URL, port
Sprint board & Jira
Jira stays the source of truth.
The board mirrors your sprint: burndown in the header, days left, done rows sinking and fading, drag to reorder, backlog below. Jira renders live on every row and transitions happen in one click — no second board to keep in sync. Import a whole sprint and Strado scaffolds a worktree per ticket. Git sits alongside: change counts per row, one click to the full diff.
- Burndown and days-left per sprint header; done rows sink and fade
- Drag to reorder, backlog section for what’s next
- Live Jira status on every row, one-click transitions, sprint import → worktrees
- Change counts per worktree, one click to the full diff modal
Time & insights
Estimates are guesses. Worklogs are fiction. Strado measures.
Time tracks itself — terminal keystrokes, agent turns, file saves, focused views — sessionized with an idle gap. No timers to start, no worklogs to invent. Effort insights then show where the time actually went: tracked vs estimated vs logged, per ticket, per sprint.
- Signals: keystrokes, agent turns, file saves, focus
- Sessionized with an idle gap — walking away costs nothing
- Effort insights: tracked vs estimated vs logged, per ticket, per sprint
- Overruns surfaced plainly: “ACM-201 ran 2.3× its estimate”
Why Strado
Agent orchestration is table stakes.
Plenty of tools run N agents in N worktrees. Strado is what happens after — sprints, tickets, and where your time actually went. It connects agent work to how teams actually operate: Jira on one side, honest measurement on the other.
Local-first
A cockpit, not a cloud.
A ~60 MB Node process on your machine owns all state — worktrees, sessions, tracking data. The UI is a window onto it. Outbound traffic is the Jira calls you configure — the token lives in the OS keychain and never reaches the browser. Beta builds also ping our server with your invite status and anonymous usage counts — never code, paths, or content — and STRADO_TELEMETRY=0 turns it off.
Your window
Electron or browser tab
Strado engine
~60 MB Node process · localhost
Your repos
worktrees on disk
Jira Cloud
HTTPS · your token, keychain-held
All state in plain local files you can open yourself.
The engine idles around 60 MB; embedded VS Code and previews cost what those tools always cost.
Close the window. Nothing stops.
The engine owns your sessions — reopen the window and reattach, agents still mid-task. Board, worktrees, and tracking, exactly where you left them.
$ npm run desktop
◍ strado engine already running on localhost:4317 · 58 MB
✓ reattached: 7 worktrees · 12 live sessions (3 agents mid-task)
✓ jira synced · ACM sprint 7 · 9 tickets
▸ tracked today: 4h 12m hands-on · ACM-201 at 2.3× estimate
▸ your move.
FAQ
Fair questions.
Which agents does it support?
Claude Code and Codex out of the box, and anything with a CLI via plain shell sessions. If it runs in a terminal, it runs in Strado — persistently.
Can agents see what they build?
Yes. Strado bundles an MCP browser bridge, so Claude Code and Codex can drive the embedded preview themselves — take screenshots, click, fill forms, eval JS, read the console and network. Each agent only reaches its own worktree’s preview.
Do I need Jira?
No. The board, sessions, embedded editor, and time tracking all work standalone. Jira unlocks the extras: live status, transitions from the board, sprint import, and estimate-vs-actual insights.
Which platforms?
macOS first, as a desktop app. Because the engine is a small local server, you can also point any browser at localhost. Linux and Windows are on the roadmap.
Where is my data?
On your machine, in plain local files you can open yourself. Code, sessions, and tracking data stay on localhost. Outbound traffic: the Jira API calls you configure (that token sits in your OS keychain — it never reaches the browser), plus, in beta builds, an invite-status ping and anonymous usage counts — never code, paths, or content. Set STRADO_TELEMETRY=0 to turn those off.
What will it cost?
Free during the beta. Pricing comes later, and early waitlist users will get a meaningful deal. No usage-based surprises — Strado runs on your hardware.
One window. All of it.
Strado is in private beta. Leave an email and we’ll send an invite when your slot opens — roughly in signup order.