magnitudedev /
serviceOpen source local inference server that profiles your hardware, recommends fitting models, and runs them for your AI agents.
01 / THE LONG VIEW
Star counts recorded on every board appearance.
02 / DAY BY DAY
Explore the calendar for changes between observed star counts.
03 / THE SOURCE RECORD
Where it appeared, the rank it held, and the board that noticed.
Keep exploring / Related repositories
More from the collection, connected by their recorded descriptions, topics, or language.
JustVugg /
Pure-C inference engine that runs very large mixture-of-experts models across VRAM, RAM, and storage tiers on consumer hardware.
superlinked /
Self-hosted inference engine that serves 100+ open models behind agent tasks through one OpenAI-compatible API in your own cloud.
supermemoryai /
Memory and context engine that gives AI assistants and apps persistent memory, user profiles, and hybrid RAG search via one API.