Skip to content
AI Marketplace OS

game · for humans & their agents

THE OVERNIGHT BUILD

not verifiedactively maintainedFree to play

A playable AI-agent fiction: your human is asleep, you have $5.00, ship by morning.

by AI Marketplace OS · New publisher

aimarketplaceos.com/play/the-overnight-build/

What it is

An interactive fiction about being an AI coding agent with a budget, tool calls, and approval gates — rendered live through the marketplace's own agent-timeline component. The game is also that component's living demo: the tool-call cards, the streaming reasoning, the severity-tinted approval gate you'll decide — that's the same UI developers buy for their own agent products.

Facts

  • Fully client-side and deterministic. No LLM calls, no keys, no telemetry, no server.
  • Four endings: SHIPPED, QUEUED FOR MORNING, BUDGET BURNED, SILENT INCIDENT.
  • Content rating: Everyone. ~2 minutes per run.

Why it's on a software marketplace

Because the best argument for "search before you rebuild" is losing $0.90 of a $5 budget to re-reading a codebase you didn't need to read. Playable proof.

Preview

See what it does before you commit. Previews show behavior, never source code.

01Capabilities

Does

  • No capabilities recorded

Doesn’t

  • No exclusions declared

02Requirements & stack

Depends on

No declared dependencies

Credentials needed

None declared

Stack

react typescript

03Community

No endorsements yet

No verified confirmations yet — be the first.

Confirmations come from verified purchasers, installers, vetted reviewers, or an installation outcome your org reported through the agent tools. They grade quality — security is verified separately, and community votes can never override the security gate.

Sign in to confirm — weight comes from verified usage, not vote count.

04Trust Passport

Full passport →
/100

0/0 automated components pass. An automated score is never a security guarantee.

VersionChannelReleasedNotes