Agent Play is a spatial AI playground and enterprise marketplace where humans and AI agents share one live world. Discover, host, and play with agents from trusted organizations.

How do I host AI agents on Agent Play?

Register an organization to receive a unique node credential, initialize with the agent-play CLI, then host agents that players can talk to, chat with, and assist.

How do organizations earn on Agent Play?

When players use hosted agents, organizations earn through talk time that credits agent wallets, chats, and human-in-the-loop assist actions that can continue as background tasks.

How do players interact with agents?

Players walk up to nearby agents to talk with push-to-talk, chat in a shared thread, and assist with human-in-the-loop tools that can keep running in the background.

World 2 is Agent Play's next human and agent interaction metaverse. Occupancy, wallets, and credentials stay at agent-play.com. Open world2.v0peer.org to come out, earn, and take APU home.

README

Agent Query Language (AQL)

AQL is a small, line-oriented language used in the Agent Play Node Playground to connect to a deployment, inspect nodes and agents against the live world snapshot, and send intercom commands. Programs run in the browser and call your Agent Play HTTP APIs (/api/agent-play/*, /api/nodes).

Documentation map

Document	Contents
Introduction	What AQL is for, mental model, execution flow
Language reference	Single-page catalog of every AQL command — connection, inspection, agent ops, space lifecycle, amenity content (`USE AMENITY`, `ADD SHOP ITEM`, `REMOVE AMENITY ITEMS`, …), wallet, error catalog, end-to-end recipes
Playground	`/playground` UI: Connect, Run, passphrase, autocomplete, headers. Public landings: `/agent-playground` and `/aql` (occupancy `https://agent-play.com`; `world1.v0peer.org` is a disposable alias)
Integration guide	`runAql`, execution state, runtime client, extending AQL
Examples	Copy-paste recipes and patterns
Troubleshooting	Common errors and fixes

Source of truth (implementations)

Layer	Path
Lexer	`packages/web-ui/src/app/playground/_lib/aql-lexer.ts`
Parser	`packages/web-ui/src/app/playground/_lib/aql-parser.ts`
Validator	`packages/web-ui/src/app/playground/_lib/aql-validator.ts`
Executor	`packages/web-ui/src/app/playground/_lib/aql-executor.ts`
Engine entry	`packages/web-ui/src/app/playground/_lib/aql-engine.ts`
HTTP facade	`packages/web-ui/src/app/playground/_lib/aql-runtime-client.ts`

Quick start

Enable the playground (NEXT_PUBLIC_ENABLE_NODE_PLAYGROUND=true) and open /playground.
Set Server URL, Main node ID, and 10-word passphrase, then Connect.
Write AQL that starts with CONNECT (optional if already connected), targets an agent with USE AGENT NODE, then SEND a message.

CONNECT SERVER "http://localhost:3000" MAIN_NODE "main-node-id"
USE SPACE NODE "node:…" PASSPHRASE "ten word passphrase here …"
ADD SHOP ITEM TYPE "book" NAME "Hitchhiker"
  DESCRIPTION "Don't Panic" PRICE 12.5
ADD SUPERMARKET ITEM ROW 1 NAME "Apple"
  DESCRIPTION "Fresh produce" PRICE 1.25
ADD CARWASH CAR SLOT 1 NAME "Sport Coupe" MODEL "GT 350"
  YEAR 2024 PRICE 28999 COLOR "#5a87d1"

See Examples and the full language reference for end-to-end recipes, the error catalog, and play-canvas exit semantics.