Pinned Loading
-
rail
rail PublicSelf-hosting language that trains AI to write itself. 3,865 lines compile to 646K ARM64. Compiler-as-oracle flywheel. Zero C dependencies.
Haskell
-
nanoversight
nanoversight PublicAutonomous oversight for any system. One file, one loop, one LLM. Zero dependencies.
Python
-
sluice
sluice PublicPriority-queue LLM router for Apple Silicon. Prevents GPU OOM by serializing inference. Zero dependencies.
Python
-
agent-command-center
agent-command-center PublicRTS-inspired command center for real hardware. Train models, deploy services, manage fleet — every action is real compute producing real assets. Red Alert meets your GPU.
JavaScript
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.