I turn text into graphs and graphs into videos by bossing around NPCs in game engines, then make video models watch them. Ahem… with attention.
Pinned Loading
-
mtasa-blue-gest
mtasa-blue-gest PublicForked from multitheftauto/mtasa-blue
GEST-Engine: native D3D9 multi-modal capture (RGB, segmentation, depth). Fork of mtasa-blue.
C++
-
mta-sim
mta-sim PublicGEST-Engine: executes Graphs of Events in Space and Time in GTA San Andreas, producing multi-actor videos with dense ground-truth annotations.
Lua
-
multiagent_story_system
multiagent_story_system PublicGEST-Engine: graph generation and batch orchestration. Procedural and LLM generators, local and VMware fleet runners.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



