MakeShipHappen · Execution Engine

ShipSpace

Run code review, feature builds, and security audits
in parallel — on your machine, against your code.

You already know the drag: waiting through sequential steps, context-switching between terminal, IDE, and chat, watching work disappear into someone else's rented sandbox. ShipSpace runs the whole loop — research, implementation, review, verification — concurrently against a real directory on your disk. Real files back on disk, a decision-ready verdict at the end, keys stay in your keychain.

Also available for
agent_0 > init
status: ONLINE
agent_1 > init
status: ONLINE
agent_2 > init
status: ONLINE
agent_3 > init
status: ONLINE
agent_4 > init
status: ONLINE
agent_5 > init
status: ONLINE
agent_6 > init
status: ONLINE
agent_7 > init
status: ONLINE
agent_8 > init
status: ONLINE
agent_9 > init
status: ONLINE
agent_10 > init
status: ONLINE
agent_11 > init
status: ONLINE
agent_12 > init
status: ONLINE
agent_13 > init
status: ONLINE
agent_14 > init
status: ONLINE
agent_15 > init
status: ONLINE
16
Concurrent Roles
Research, implementation, review, verification — no manual sequencing
6
Mission Presets
Audit, build, review, fix, refactor, perf
3
Platforms
macOS, Windows, Linux
BYOK
Keys Stay Yours
Local keychain, never rented
Execution Workflow

Configure. Run. Review. Iterate.

A controlled environment where structured build work becomes real output — with a verdict at the end of every mission.

Structured Missions — one setup, reusable

Every run is a mission with an explicit goal, a working directory, context sources, and a roster of roles. Start from a preset — security audit, feature build, code review — or define your own, and reuse it without rebuilding the prompt each time.

Parallel Execution — one pass instead of five

Research, orchestration, implementation, review, and verification run concurrently across your codebase. One mission covers what would otherwise be five sequential sessions in five separate tools.

Operator Console — one screen, every stream

Per-role output streams, file change summaries, and inline editing via Cmd+P Quick Open. See what each role produced and what landed on disk without leaving the workspace.

Controlled Builder Environment — real files, not a sandbox

Runs natively via Tauri v2 on your local filesystem. Preserves your shell config, keeps your API keys in the OS keychain, and writes real files to disk — nothing is rented, nothing leaves your machine.

Mission Verdicts — ship, iterate, or start over

Every mission ends with a decision-ready summary: what passed, what failed, what changed on disk, what to revise. Know in one screen whether to ship, iterate, or start over.

Iterate on Results — next run in one click

Keep the mission, the directory, the context, and the prior verdict — then launch the next run in one click. The iteration loop is a first-class action, not a cold restart.

Mission Presets

Real work. Real output.

Six starting points that map to the build work independent teams actually run. Pick one, point it at a directory, and ship.

01

Security Audit

Dispatch a mission across your codebase to surface unsafe patterns, secret leaks, and risky dependencies. Returns a prioritized issue list with file locations, severity, and a verdict on what to fix first.

02

Feature Build

Hand over a mission spec, a directory, and context. Get a working feature back — implementation, tests, and a verdict on what's ready to ship versus what needs revision.

03

Code Review

Run a reviewer role across a branch or directory. Returns a structured review — what's solid, what's risky, what to change — mapped to specific files and lines.

04

Bug Fix

Point a mission at a failing test or reported issue. The roster reproduces, diagnoses, fixes, and verifies — with changed files and a before/after summary at the end.

05

Refactor

Launch a refactor mission with an explicit scope. Parallel roles handle analysis, implementation, and verification — so the change lands safely, not speculatively.

06

Performance Improvement

Send in a perf mission with a baseline and a target. Get profiling output, bottleneck analysis, and a verdict on whether the change actually moved the number.

node-pty

Native shell processes

Panels

Drag & drop workspaces

xterm.js

WebGL GPU rendering

Blocks

OSC 133 integration

Controlled Environment

Your machine.
Your files. Your keys.

ShipSpace runs natively on your OS, operates on your local filesystem, and keeps your API keys on-device. Missions produce real files on disk you can open, diff, and ship — not artifacts trapped inside a rented sandbox.

Native OS integration via Tauri v2
Preserves your .zshrc and .bashrc config
Zero telemetry on your local shell data
Cross-platform: macOS, Windows, Linux

All platforms. One environment.

Native desktop apps for every major OS.

Windows

135 MB

macOS

142 MB

Linux

Experimental
150 MB

Frequently Asked Questions

How the execution engine fits into the rest of MakeShipHappen.

The Builder's Journey

Start in ShipMind. Continue in ShipSpace.

ShipMind helps you understand the work. ShipSpace helps you execute it. The handoff is explicit — mission context moves cleanly from the second brain to the engine.

01

Capture & Ground

Ingest notes, research, and source material in ShipMind. Ask grounded questions. Generate build-ready artifacts.

02

Hand Off the Mission

Send mission context — goal, directory, constraints — into ShipSpace. The handoff is explicit, not implicit.

03

Execute in Parallel

ShipSpace runs the mission across roles: research, orchestration, implementation, review, verification.

04

Review & Iterate

Inspect outputs, read the verdict, open the changed files, decide what ships. Iterate without losing context.

MakeShipHappenTech

Set a Mission.
Ship the Verdict.

ShipSpace is where structured build work becomes real output — configured, run, reviewed, and iterated on inside a controlled builder environment.