Repo AI đang lênCập nhật hằng ngày từ GitHub

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets & Edge Functions for AI Toys, Desk Companions and Devices

Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)

Robust realtime face and facial landmark tracking on CPU with Unity integration

Connect your company's data, let an agent draft an ontology over it, and load it into HelixDB as one graph you can explore and ask questions of. Hosted at foundry.helix-db.com, or run it on your own machine.

ChatWiki 微信公众号的AI知识库工作流Agent平台，RAG大模型AI客服机器人，致力于成为垂直领域的coze、n8n。

On-device, real-time multimodal AI with features similar to GPT-Live

Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.

Reinforcement Learning environments based on the 1993 game Doom :godmode:

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

Seamless integration between Claude Code AI assistant and Neovim

Completely free, private, UI based Tech Documentation MCP server. Designed for coders and software developers in mind. Easily integrate into Cursor, Windsurf, Cline, Roo Code, Claude Desktop App

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

Implementation of EfficientNet model. Keras and TensorFlow Keras.

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

Everything about federated learning, including research papers, books, codes, tutorials, videos and beyond

An iOS OCR Server Using Apple’s Vision Framework

Benchmark datasets, data loaders, and evaluators for graph machine learning

[DEIMv2] Real Time Object Detection Meets DINOv3

Deep and online learning with spiking neural networks in Python

The ultimate zero-install, portable local AI environment. Run high-quality, uncensored LLMs (Gemma, Qwen, NemoMix) directly from any USB drive or SSD. Fully air-gapped, cross-platform (Win/Mac/Linux), and privacy-first with persistent chat history.

Monoscope lets you ingest and explore your logs, traces and metrics. We store these in S3 compatible buckets. Query in natural language via LLMs.

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

Audio generation using diffusion models, in PyTorch.

OneBot：统一的聊天机器人应用接口标准

[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

Monitors your RAM and reports any "quite terrible" unused capacity directly to the CEO of OpenAI.

Production-grade C++ edge AI engine for video analytics and on-device VLM across Sophon, Rockchip RKNN, and x86, with visual orchestration, real-time OSD, events, and reproducible benchmarks.

Flowframes Windows GUI for video interpolation using DAIN (NCNN) or RIFE (CUDA/NCNN)

Russian GPT3 models.

AgentFlow: In-the-Flow Agentic System Optimization

An End-To-End, Lightweight and Flexible Platform for Game Research

Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK. Python, C# and JS(WASM) bindings available.

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

One-click Portable ComfyUI with EZi Desktop - install, manage and customize ComfyUI in one place. 🔹 Nvidia GPU support 🔹 Pixaroma Community Edition

A colab gradio web UI for running Large Language Models

Extract structured data and insights from documents using LLMs and decision models

A log viewer for Kubernetes troubleshooting

🤖 The most comprehensive list of AI agents, frameworks & tools in 2026. 300+ resources · 20+ categories · Updated monthly.

EPUB to audiobook converter, optimized for Audiobookshelf, WebUI included

A deep learning package for many-body potential energy representation and molecular dynamics

A Python package for Bayesian forecasting with object-oriented design and probabilistic models under the hood.

llama and other large language models on iOS and MacOS offline using GGML library.

NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

DSH × Blender 直连插件 v3.0.6：15 个模型工具让 AI 驱动 GUI Blender（视口 / 自定义视角 / 无头 worker / 作业层 / 事务回滚 / 配方库），34 family / 228 op 契约层；npm 安装 + addon zip，GUI 优先、无头备用；dsh-TUI 选中 chip / @ 提及 / /blender，随包建模 skill，支持 WSL / Windows / macOS。

The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.