Computer Vision
ultralytics
ultralytics/ultralytics
Training and inference tools for object detection, segmentation and pose estimation models.
★ 61.3K⑂ 11.7KPython
ToolAI.io · GitHub Channel
AI Project Directory on GitHub
Browse the complete ToolAI directory of open-source AI projects on GitHub, organized by topic, language and license.
Public repository data
Project index
Computer Vision
yolov5
ultralytics/yolov5
A PyTorch-based object detection project with training, inference and export workflows.
★ 58K⑂ 17.5KPython
Fine-tuning, Training & Data
ColossalAI
hpcaitech/ColossalAI
Distributed training and inference tools for parallelism and memory management in large-model workloads.
★ 41.4K⑂ 4.5KPython
Speech, Audio & Voice
ChatTTS
2noise/ChatTTS
Conversational Chinese and English speech generation with speaker and prosody controls; released model weights are noncommercial.
★ 39.8K⑂ 4.2KPython
Robotics & Edge AI
mediapipe
google-ai-edge/mediapipe
On-device ML libraries, models, and tools for vision, text, and audio across supported platforms.
★ 36.9K⑂ 6.2KC++
Inference, Deployment & Runtime
hal0
hal0ai/hal0
An open-source, self-hosted home AI inference platform designed to turn a Linux box into an OpenAI-compatible inference appliance, with native optimization for AMD Strix Halo hardware.
★ 68⑂ 7Python
LLM & Foundation Models
DeepSeek-Coder — Code generation models
deepseek-ai/DeepSeek-Coder
DeepSeek Coder: Let the Code Write Itself
★ 24.2K⑂ 2.9KPython
Agents & Multi-Agent
NemoClaw — Agent runtime and deployment tooling
NVIDIA/NemoClaw
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
★ 22.2K⑂ 3KPython
LLM & Foundation Models
gpt-oss — Open-weight language model tooling
openai/gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
★ 20.3K⑂ 2.1KPython
Inference, Deployment & Runtime
tiktoken — Fast tokenization
openai/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
★ 19K⑂ 1.6KRust
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
Inference, Deployment & Runtime
LocalAI
mudler/LocalAI
A local inference engine for self-hosting models and AI services.
★ 48.9K⑂ 4.4KGo
Page 3 / 4 · 47 projects