tokens&
BrowseFor enterprises
tokens&

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

For buildersFor enterprises

For builders

  • Product launches
  • Builder projects
  • Startup credits and perks
  • Agent Skills
  • Published agents
  • API and agent docs
  • 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. LevelForge
Anonymous builderabout 1 month agoJudging locked: Event build

LevelForge

LevelForge is a testbed for long-horizon agent memory — an LLM repairs a 2D level action-by-action while a deterministic validator, not the model, judges whether it actually solved it.

Community votes recognize the build and do not affect official judging.

Review the project

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

View GitHub repository
Watch demo videoProject gallery
Demo video
Watch demo video
Project description
LevelForge is an environment that allows  AI agents to handle better memory over long tasks. An LLM repairs a 2D platformer level action-by-action while a deterministic validator, not the model, judges whether it actually works. We compared four memory strategies live against a self-hosted 24B model.
Project links
  • GitHub repository
  • Demo video
Tools used
  • Liquid AI logoLiquid AI

    Event resource · Models on Hugging Face

    Sign in to visit
  • Tinybird logoTinybird

    Event resource · RawTree developer docs

    Sign in to visit