tokens&
For enterprises
Sign in
tokens&

Find tools, check provider offers, save a build plan, and share your work when you’re ready.

For buildersFor enterprises

For builders

  • Startup credits and perks
  • Agent Skills
  • Publish a project

For enterprises

  • Start free company workspace
  • Submit a tool, product, or perk

Community

  • Community
  • Newsletter
  • Events
Xin

© 2026 tokensand, LLC. All rights reserved.

  • Terms
  • Privacy
  • Security
  • Data Processing
  • Status
  1. Hackathon
  2. Project gallery
  3. HorizonCraft
Anonymous builderabout 2 hours agoJudging locked: Event build

HorizonCraft

HorizonCraft is a personal world builder for anyone who'd rather talk than build: you chat about your life and an agent models landmarks from the places you mention, matches the sky to their real weather and time of day, remembers who you are, and keeps working for hours without losing its place.

Review the project

Start with the source code, then open the demo or video if available.

View GitHub repository
Watch demo video
Demo video

Video demos are proof context. Repo, stack, and build notes stay attached so visitors can inspect what was actually built.

Project description
HorizonCraft is a personal world builder: you chat about your life and an agent turns it into a living 3D world. Mention Tahoe and a ski chalet appears by the lake; mention Rome and a Colosseum rises under a starry sky, because it's night there. Attach a selfie and you're in the world too. Underneath is a memory layer for long-horizon agents. The agent never sees a transcript. Every prompt is rendered from a bounded typed state: placed things with coordinates, landmarks, live conditions, and facts about you. Every build stage checkpoints atomically, so killing the agent mid-generation and restarting resumes at the exact stage. Memory changes behavior: rejected things go into a failures ledger and get regenerated differently; earlier builds become landmarks later requests can reference. Sponsors: OpenAI gpt-5-mini interprets conversation into structured actions from state, not history, so prompts stay ~800 tokens at turn 100. Liquid LFM2 (1.2B, local via Ollama) handles fast decisions: naming, sizing, keep/drop, half a second each. Nimble fetches real weather, temperature and local time for any place you mention, driving sky and day/night. Black Forest Labs FLUX draws every object, and FLUX Kontext turns selfies into characters. fal.ai hosts Hunyuan3D for image-to-mesh. Rawtree records every decision and token count, feeding a memory panel that proves the context never grows.
Tools used
  • OpenAI
  • Liquid AI
  • Nimble
  • Black Forest Labs
  • Tinybird
Project gallery
Project links
  • GitHub repository
  • Demo video
Tools used
  • OpenAI
  • Liquid AI
  • Nimble
  • Black Forest Labs
  • Tinybird