Gamer
Gamer combines cross-game pre-training, task-conditioned learning, and low-latency inference for long-horizon interaction.
Gamer launched on 30 October 2026. It ranked #43 on Daily Launch on 20 November 2026 with a Launch Score of 43, from +270 stars today on GitHub. It moved up 53 places from the day before.
What is Gamer?
We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D graphical interfaces and complex 3D simulated worlds. We first continue pre-training on a dataset of tens of thousands of hours of device-level keyboard and mouse interaction. These trajectories span simulated games and embodied environments, allowing the model to learn environmental dynamics across both physical and virtual domains.
From its README on GitHub
Gamer is a repo by RainBowLuoCS on GitHub. It is released under the Apache-2.0 license.
How to get Gamer
Get it from its repository on GitHub.

Screenshot of mihoyo-gamer.github.io
In its own words
Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents
From its GitHub repository
Launch timeline
Launch Score, last 7 days
#98 of 226 in the roundup for the week of 16-22 November 2026.