RepoAlerts
SponsorGet alerts

THUSI-Lab/GameScaling

Agent

Get alerts like thisView on GitHubWebsiteShare on X

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 13 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence OK

    Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

Inference client and system-prompt template for GameScaling, a set of Qwen3.5 vision-language models with continued pre-training on keyboard-and-mouse gameplay. Given the current frame and recent history, the models predict the next 200 ms of keyboard and mouse actions for…

Who it's for

Researchers and developers building game-playing embodied agents on vision-language models

How to use it

Install

pip install "vllm>=0.17"

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up THUSI-Lab/GameScaling in my project. Follow its README: https://github.com/THUSI-Lab/GameScaling. Explain each step and check it is safe before running anything.

Star curve

290From 0 to 290 stars between 10 Oct 2026 and 23 Oct 2026.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

19,378 GitHub repos watched and ranked every hour. Figures as of 23 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![THUSI-Lab/GameScaling on RepoAlerts](https://repoalerts.com/badge/THUSI-Lab/GameScaling.svg)](https://repoalerts.com/repo/THUSI-Lab/GameScaling?ref=badge)
Share on X
  • VAST-AI-Research/EdenLive

    Real-time generative renderer that turns a reference video from an interactive program into detailed frames, guided by a target first frame and a text prompt. Provides 5B and 14B model weights, stream

    Creative toolsPython · 328 stars · +247 this week · 11 days old

  • apple-aiml-research/ml-rsi-inference-bench

    A long-horizon benchmark for coding agents that improve the inference stack of large language models in vLLM or SGLang. Tasks cover supporting a model on day 0, optimizing it after launch, and repairi

    AI agentsPython · 112 stars · +112 this week · 7 days old

  • zzzz7788990213-ops/EvoVLM

    Research code for LLM-guided evolutionary search over vision-language inference programs. It mutates prompts, image preprocessing, generation budgets and answer extraction for a frozen Qwen3-VL-2B mod

    Models & inferencePython · 5 stars · 21 days old

  • lucwj/ai-agent-3d-prompts

    A prompt set for rebuilding a browser-based 3D office where six simulated AI agents (orchestrator, PM, researcher, engineer, QA, reviewer) visibly collaborate on a software task. The client-side UI an

    AI agents43 stars · +43 this week · 4 days old

  • VecSzn/PolyStrata

    Runs large open-weight language models locally on an NVIDIA GPU, with OpenAI- and Anthropic-compatible API endpoints served on localhost. Includes a second, experimental inference engine for several m

    AppModels & inferenceC++ · 402 stars · +246 this week · 17 days old

  • openJiuwen-ai/jiuwenswarm

    A multi-agent system in which a Leader agent decomposes complex tasks and coordinates specialized agent teams, with skill self-evolution and tool invocation driven by natural language. Runs on one mac

    AgentAI agentsPython · 7,960 stars · +1,039 this week · 232 days old