Worlds Together
Worlds Together is multiplayer AI for finding the pieces you’re missing, and starting something together.
Core trick
Matches people on complementary private context, sharing selected pieces into a room only after both sides approve each contribution.
Description
Worlds Together is multiplayer AI for finding the pieces you’re missing, and starting something together.
People bring knowledge, interests, ambitions, images and sounds into a private world, then choose what others may discover. AI looks for complementary contributions, not just similar profiles: your community knowledge might connect with someone else’s research experience.
Both people approve before selected context enters a shared workspace. They can refine a first task, ask an agent to prepare a practical draft, review its sources and build on each other’s contributions. A separate creative path lets fans and artists combine words, images and sound into evolving shared worlds.
The prototype includes opt-in matching, shared rooms, human-approved AI proposals, multimedia composition and source attribution
README excerpt
# Worlds Together A standalone experiment in private personal context and multiplayer creation. Add pieces of your life, knowledge or imagination. Let Astra suggest which pieces could contribute to an encounter. Review them, share only those pieces, and build something together. Every creation keeps links to the pieces that shaped it. ## What works - Rotatable dimensional collection with image pieces and source traces. - Twin private/shared worlds, a hovering selected piece, and in-place drafting and sharing review. - Member-scoped agent proposals grounded in explicitly selected shared pieces; only the requesting member can approve their agent's contribution. - Private room-scoped person matching from 1–8 deliberately selected personal pieces and other participants' shared context. Each result identifies the exact pieces, complementary contribution, and a concrete first artifact. - Cross-world discovery before any shared room: explicit text-only opt-in, AI matching across up to twenty recently updated discovery profiles, source previews, and a recipient-approved invitation. Neither sender nor agent can accept for the recipient. - Mutual acceptance atomically creates one room containing the exact previewed text pieces. Changing discovery permissions invalidates pending invitations; stopping discovery does not delete existing shared rooms or recall copies. - Permission-gated connection → share → agent draft → human approval, inside the globes. Search itself does not share or