LLM & Model Fondasi
GLM-5
zai-org/GLM-5
GLM-5: From Vibe Coding to Agentic Engineering
★ 6,8K⑂ 848—
ToolAI.io · Kanal GitHub
Proyek AI yang sedang tren di GitHub
Lacak repositori AI open source aktif dalam topik LLM, agen, MCP, RAG, dan coding, lengkap dengan jumlah bintang serta informasi proyek yang terverifikasi.
Data repositori publik
Indeks proyek
Visi komputer
PaddleClas
PaddlePaddle/PaddleClas
A treasure chest for visual classification and recognition powered by PaddlePaddle
★ 5,8K⑂ 1,2KPython
AI Multimodal
TRELLIS.2: image-to-3D assets with materials
microsoft/TRELLIS.2
Microsoft’s 3D generation project with image-to-3D inference, PBR texturing and GLB export for GPU-equipped asset workflows.
★ 11,2K⑂ 1,4KPython
Agen & Multi-Agen
UFO
microsoft/UFO
UFO³: Weaving the Digital Agent Galaxy
★ 9,3K⑂ 1KPython
Inferensi, Deployment & Runtime
TensorRT
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
★ 13,2K⑂ 2,4KC++
RAG & sistem pengetahuan
llm-app
pathwaycom/llm-app
Application templates for RAG, search and AI pipelines using live data sources.
★ 58,9K⑂ 1,5KJupyter Notebook
Inferensi, Deployment & Runtime
checkpoint-engine
MoonshotAI/checkpoint-engine
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
★ 982⑂ 100Python
Visi komputer
face_recognition
ageitgey/face_recognition
Face detection and recognition interfaces for Python and the command line.
★ 56,7K⑂ 13,7KPython
AI Applications & Automation
PaddleX
PaddlePaddle/PaddleX
All-in-One Development Tool based on PaddlePaddle
★ 6,2K⑂ 1,2KPython
AI Multimodal
HunyuanImage-3.0
Tencent-Hunyuan/HunyuanImage-3.0
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
★ 3,2K⑂ 175Python
Agen & Multi-Agen
OpenRoom
MiniMax-AI/OpenRoom
A browser-based desktop where AI Agent operates every app through natural language.
★ 1,2K⑂ 162TypeScript
Visi komputer
DINOv2: visual features for classification and retrieval
facebookresearch/dinov2
Meta’s self-supervised vision models provide pretrained backbones and task heads for feature extraction, visual retrieval and downstream adaptation.
★ 13,3K⑂ 1,3KPython
Halaman 22 / 26 · 305 proyek