Mindket

AI projects from Hugging Face

Categories and filters
Filters
Clear filters

Listings

WARC

third-intelligence · Kit

A 35M-parameter world model for ARC-AGI-3 games that predicts the next game frame from the last three frames and an action, and keeps training itself while an…

New

Answers questions about an image as choices, yes/no probabilities or rubric levels in one pass, and can play simple games from screen pixels, with 201M paramet…

New

UI-TARS-1.5-7B

ByteDance-Seed · Kit

An open multimodal agent model that reads screenshots and decides what to do in apps, browsers, phones and games. For developers building computer-use and GUI…

New

GameScaling

THUSI-Lab · Kit

A small vision-language model built on Qwen3.5-0.8B from a research project on continued pre-training for embodied agents in many virtual game worlds. For rese…

New

TripoSplat by VAST-AI

VAST-AI · Kit

Turns a single 2D image into a variable number of 3D Gaussians for asset creation, AR and VR, games and simulation. A model from VAST-AI for 3D creators and de…

New

Make24

jacklinquan · Kit

Solves make-24 number puzzles in a Gradio page, using a small solver module, for puzzle fans, teachers and students who like arithmetic games.

New

A LoRA from TawusGames that, going by its name, handles texture inpainting and outpainting for Qwen Image 2.1. The page gives no further description.

New

Murder.Ai

MCP-1st-Birthday · Kit

Plays a detective game where you question AI suspects, gather evidence and solve generated murder mysteries, for fans of interactive mystery games.

New

Outsmart

ed-donner · Kit

Pits AI models against each other in a turn-based game of negotiation and strategy, and ranks them across games. It suits anyone curious how language models ba…

New