DeckSpaceLiveRun up to 16 AI coding agents at once — each isolated on its own git worktree — while a board feeds the work and you read every diff from a single window. New in 2.0: Jarvis, a voice copilot that runs the deck for you — and tests what it builds in a real browser. Bring your own key — no usage markup. Your code never leaves your machine.
› worktree ready — pick a task below› awaiting taskDeckSpace 2.0 is the biggest upgrade yet: a voice copilot that actually runs the workspace, autonomous missions that test what they build in a real browser, and panels that spread across every monitor you own.
Hold ⌘⇧J and say it: "open the board", "spawn Claude on the login bug", "start a mission to build the landing page". Jarvis acts inside DeckSpace and across your Mac — and talks back when it's done.
Missions now end with a real end-to-end browser test — the DeckTest engine ships inside DeckSpace Pro. A failing test sends the agent back to work automatically.
Pop the browser, editor, board — any panel — into its own window and drag it to any display. Your multi-monitor layout is remembered per workspace.
Capture a region, a window or the whole screen straight into your workspace — and Jarvis can see the screen too ("click the blue Open button").
DeckSpace now updates itself in the background — signed, verified, one click to restart. This is the last version you'll ever download by hand.
Warp-style command history you can click to jump back through, ⌘F search in any pane, drag files onto terminals, drag Skills onto panes — in 27 themes.
Building usually scatters across terminals, tabs and half-finished prompts. DeckSpace gives each part of the job a room — all sharing the same agents, board and memory.
A grid of up to 16 real terminal panes (native PTYs, xterm + WebGL) with layout presets. Launch an agent into any pane and watch its status live.
Decompose one goal into a team — a git worktree per agent, true isolation — then launch, watch, and merge each result behind a review gate.
Side-by-side diffs, stage & commit, inline comments, and a verification verdict — you decide what ships.
A living markdown knowledge graph with [[wikilinks]], force-directed view and backlinks — shared with every agent over MCP.
Push-to-talk dictation, and Jarvis — a voice agent that opens rooms, spawns agents, files board tasks, starts missions and takes screenshots on command. It answers out loud when it's done.
Hand off a mission and DeckLoop designs, ships and fixes in a loop — then proves the result with a real end-to-end browser test (DeckTest engine, built into Pro).
Every parallel task runs on its own branch and git worktree, so agents never trip over each other's files. Fill the whole deck, watch it move at once, and merge each result when it's ready — one at a time, on your terms.
The point isn't to hide the work — it's to keep the moving parts visible enough to steer. A verification gate runs tests, lint and a secret scan before anything merges, and every write is confined to the repo.
DeckSpace launches the CLI agents you already have installed and authenticated — mix and match models across panes. No new accounts, no lock-in. Bring your own key; DeckSpace never sees or stores it.
claude
codex
gemini
aider
opencode
cursor-agent
droid
copilot
DeckSpace is a native desktop app (Tauri + Rust) — small, fast and offline-capable. The terminal, editor, board and memory all run locally. The only network calls are the ones your own agent CLIs make to your own model provider.
Use the CLIs you already pay for. DeckSpace never meters or marks up your model usage — you pay your provider directly. DeckSpace itself is a flat subscription, never per-token.
Confine an agent's writes to the repo, reroute destructive commands to a recoverable trash, and snapshot before every action.
Block cloud-metadata endpoints and SSRF. Telemetry is off by default — nothing about your code goes anywhere.
Up to 16 terminal panes, each able to host an agent — real native PTYs, not a toy sandbox. Launch one, or fill the deck and watch every pane move at once. Each parallel task gets its own git worktree so they never collide.
Eight CLI agents today: Claude Code, Codex, Gemini, Aider, OpenCode, Cursor Agent, Droid and Copilot CLI. DeckSpace detects whichever ones you have on your PATH and lets you mix models across panes.
Bring your own key. You authenticate the agent CLIs once, the way you already do — DeckSpace never sees, stores, meters or marks up your usage; you pay your model provider directly. DeckSpace itself is a flat subscription — $24/mo (or $228/yr), and it starts with a 7-day free trial (card on file, cancel anytime before day 7 and you're not charged). Team is a custom arrangement — talk to us.
No. The terminal, editor, board and memory all run locally and offline. The only outbound calls are the ones your own agent CLIs make to your own model provider. Telemetry is off by default.
Jarvis is DeckSpace's voice agent (Pro). It knows the app: say "open the board", "create a task called fix login", "spawn Claude on the checkout bug", "what's pane 2 doing?", "start a mission to build a landing page and test it" — and it acts, then answers out loud. It can also see your screen and operate other Mac apps, with a spoken confirmation before anything risky.
Yes. Pro bundles the DeckTest engine: missions can finish with a real end-to-end test in a real browser — sign-ups, clicks, assertions. A failing test automatically sends the agent back to fix it.
macOS, Windows and Linux. It's a native Tauri + Rust app — not an Electron shell — so it stays small, fast and offline-capable.
DeckSpace for macOS is live — start your 7-day free trial and cancel anytime. Bring your own key; no usage markup.