ome-projects/ome 520
oil-oil/wolfcha 739 +1 today
wolfcha seats one human against an AI table, and its license and version disagree
NVlabs/QeRL 527
QeRL uses quantization noise as an exploration mechanism
NVIDIA/TensorRT-Edge-LLM 601
TensorRT Edge-LLM: NVIDIA's C++ Runtime for Running LLMs on Jetson, DRIVE and DGX Spark
NVIDIA/OpenShell 19.8k +515 today
NVIDIA OpenShell: a policy-gated runtime for autonomous agents
nrwl/nx 29.4k +5 today
Nx: Incremental Builds and Task Caching for TypeScript Monorepos
NetManAIOps/ChatTS 486
ChatTS: A Time Series LLM That Keeps the Numbers
NarimanN2/ollama-playground 543
ollama-playground: A Video Companion Repo, Not a Library
MuLabPKU/TransArch 513
TransArch: A Monorepo of Attention-Rewrite Methods, Not a Single Tool
mozilla-ai/otari 736 +1 today
Otari: a self-hosted OpenAI-compatible gateway with virtual keys and pre-dispatch budget checks
Mirrowel/LLM-API-Key-Proxy 557
Mirrowel/LLM-API-Key-Proxy: an OpenAI and Anthropic compatible gateway with a separate key-rotation library
mikexcohen/ML4LLM_book 539 +1 today
ML4LLM_book: a companion repository for 50 hands-on transformer internals projects
microsoft/vattention 526
vAttention: KV-Cache Memory Management That Keeps Attention Kernels Unmodified
microsoft/agent-framework 14.3k +10 today
Microsoft Agent Framework: A Multi-Language SDK for Agents You Intend to Operate, Not Just Demo
memex-lab/memex 804 +3 today
Memex: A Local-First AI Journal That Turns Fragments Into Markdown Cards
mem-eval-suite/LoCoMo_refined 674
LoCoMo Refined: a stricter judge and a cleaned QA set for long-conversation memory
lucasjinreal/Crane 511
Crane: a Rust and Candle inference engine for LLM, VLM, TTS and OCR workloads
llmmanorg/llmman 569
llmman: agents pointed at models stored as OCI images
langfuse/langfuse-python 501