Multimodal AI
UniRL
Tencent-Hunyuan/UniRL
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
★ 854⑂ 56Python
ToolAI.io · GitHub Channel
New AI Projects on GitHub
Discover newly added open-source AI projects on GitHub with repository facts, setup notes, licenses and related resources.
Public repository data
Project index
LLM & Foundation Models
ERNIE
PaddlePaddle/ERNIE
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
★ 7.7K⑂ 1.4KPython
AI Coding & Developer Tools
openai-python
openai/openai-python
The official Python library for the OpenAI API
★ 31.2K⑂ 5KPython
AI Coding & Developer Tools
symphony
openai/symphony
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
★ 26.2K⑂ 2.7KElixir
Agents & Multi-Agent
openai-agents-js
openai/openai-agents-js
A lightweight, powerful framework for multi-agent workflows and voice agents
★ 3.5K⑂ 871TypeScript
Computer Vision
sam2
facebookresearch/sam2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
★ 19.6K⑂ 2.5KJupyter Notebook
Inference, 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++
Evaluation, Observability & Safety
SkillSpector
NVIDIA/SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.
★ 13.8K⑂ 1.1KPython
Agents & Multi-Agent
skills
NVIDIA/skills
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
★ 2.7K⑂ 304Python
Inference, Deployment & Runtime
Model-Optimizer
NVIDIA/Model-Optimizer
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
★ 3.3K⑂ 513Python
Data Engineering & Pipelines
aistore
NVIDIA/aistore
AIStore: scalable storage for AI applications
★ 1.9K⑂ 277Go
Fine-tuning, Training & Data
generative-ai-for-beginners
microsoft/generative-ai-for-beginners
21 Lessons, Get Started Building with Generative AI
★ 113.5K⑂ 60.9KJupyter Notebook
Page 11 / 25 · 295 projects