huoyijie

pyarmor. A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.

mediamtx. Ready-to-use Media-over-QUIC / SRT / WebRTC / RTSP / RTMP / LL-HLS / MPEG-TS / RTP live media server and media proxy that allows to read, publish, proxy, record and playback real-time video and audio streams.

sqlmodel. SQL databases in Python, designed for simplicity, compatibility, and robustness.

sqlalchemy. The Database Toolkit for Python

streamlit. Streamlit — A faster way to build and share data apps.

reflex. 🕸️ Web apps in pure Python 🐍

lite.ai.toolkit. 🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉

pywt. PyWavelets - Wavelet Transforms in Python

BabelDOC. Yet Another Document Translator

PDFMathTranslate. [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

awesome-datascience. :memo: An awesome Data Science repository to learn and apply for real world problems.

jupyter-ai. An open source extension that connects AI agents to computational notebooks in JupyterLab.

superset. Apache Superset is a Data Visualization and Data Exploration Platform

altair. Declarative visualization library for Python

vega-lite. A concise grammar of interactive graphics, built on Vega.

pandas. Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

statsmodels. Statsmodels: statistical modeling and econometrics in Python

dash. Data Apps & Dashboards for Python. No JavaScript Required.

plotly.js. Open-source JavaScript charting library behind Plotly and Dash

plotly.py. The interactive graphing library for Python :sparkles:

AVA. 🤖 AI-native Visual Analytics framework build for agents.

G6VP. G6VP is an online visual analysis tool for graphs and a low-code platform for building graph applications.

seaborn. Statistical data visualization in Python

matplotlib. matplotlib: plotting with Python

Rath. Next generation of automated data exploratory analysis and visualization platform.

graphic-walker. An open source alternative to Tableau. Embeddable visual analytic

pygwalker. PyGWalker: Turn your dataframe into an interactive UI for visual analysis

pandas-ai. Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

scikit-learn. scikit-learn: machine learning in Python

auto-sklearn. Automated Machine Learning with scikit-learn

Search-o1. 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]

mcpadapt. Unlock 650+ MCP servers tools in your favorite agentic framework.

phoenix. AI Observability & Evaluation

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

open_deep_research. Python

DB-GPT. open-source agentic AI data assistant for the next generation of AI + Data products.

Qwen3-Coder. Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

crewAI. Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

autogen. A programming framework for agentic AI

OpenHands. 🙌 OpenHands: AI-Driven Development

OpenManus. No fortress, purely open ground. OpenManus is Coming.

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

gpt-researcher. An autonomous agent that conducts deep research on any data using any LLM providers

playwright. Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

anything-llm. Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

tabby. Self-hosted AI coding assistant

ktransformers. A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

openai-python. The official Python library for the OpenAI API

SenseVoice. Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

CosyVoice. Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

helium. Lighter web automation with Python

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

DeepSeek-R1.

openhaystack. Build your own 'AirTags' 🏷 today! Framework for tracking personal Bluetooth devices via Apple's massive Find My network.

firmware. The official firmware for Meshtastic, an open-source, off-grid mesh communication system.

DeepSeek-V3. Python

facenet-pytorch. Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

EMO-AffectNetModel. Dynamic and static models for real-time facial emotion recognition

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

tailscale. The easiest, most secure way to use WireGuard and 2FA.

frp. A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

inference. Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

FastGPT. FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex question-answering systems without the need for extensive setup or configuration.

OpenLLM. Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

ten-framework. Open-source framework for conversational voice AI agents

faiss. A library for efficient similarity search and clustering of dense vectors.

MinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

OpenSearch. 🔎 Open source distributed and RESTful search engine.

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

langgraph. Build resilient agents.

searxng. SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

Flowise. Build AI Agents, Visually

lancedb. Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

chroma. Search infrastructure for AI

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

weaviate. Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

dify. Production-ready platform for agentic workflow development.

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

haystack. Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

neo4j. Graphs for Everyone

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

llama_index. LlamaIndex is the leading document agent and OCR platform

langchain. The agent engineering platform.

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

fastai. The fastai deep learning library

IOPaint. Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

DeepSolo. The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting"

Awesome-Table-Recognition. A curated list of resources dedicated to table recognition

awesome-table-structure-recognition. A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

AdvancedLiterateMachinery. A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Document-AI-Recommendations. Algorithms, papers, datasets, performance comparisons for Document AI.

awesome-key-information-extraction. A curated list of papers about key information extraction.

AlphaPose. Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

doctr. docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Vary-tiny-600k. Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)

sparrow. Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM

pix2struct. Python

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

FunCodec. FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music generation et.al.

Pytorch_Retinaface. Retinaface get 80.99% in widerface hard val using mobilenet0.25.

TCN. Sequence modeling benchmarks and temporal convolutional networks

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

tortoise-tts. A multi-voice TTS system trained with an emphasis on quality

voicebox-pytorch. Implementation of Voicebox, new SOTA Text-to-speech network from MetaAI, in Pytorch

vall-e. PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

encodec. State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

FunASR. Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

audiolm-pytorch. Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

vall-e. An unofficial PyTorch implementation of the audio LM VALL-E

VALL-E-X. An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

PaddleSpeech. Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

VITS-fast-fine-tuning. This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

naturalspeech2-pytorch. Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

bert. TensorFlow code and pre-trained models for BERT

s3prl. Self-Supervised Speech Pre-training and Representation Learning Toolkit

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

espnet. End-to-End Speech Processing Toolkit

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Bert-VITS2. vits2 backbone with multilingual-bert

vits_chinese. Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!

ultimatevocalremovergui. GUI for a Vocal Remover that uses Deep Neural Networks.

hifi-gan. HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

contentvec. speech self-supervised representations

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

vits2. VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

TTS. :robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

bark. 🔊 Text-Prompted Generative Audio Model

EmotiVoice. EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

GPT-SoVITS. 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

MeloTTS. High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

OpenVoice. Instant voice cloning by MIT and MyShell. Audio foundation model.

Real-Time-Voice-Cloning. Clone a voice in 5 seconds to generate arbitrary speech in real-time

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

GPEN. Jupyter Notebook

GFPGAN. GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

CodeFormer. [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

InstantID. InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

inswapper. One-click Face Swapper and Restoration powered by insightface 🔥

BlendFace. [ICCV 2023] BlendFace: Re-designing Identity Encoders for Face-Swapping https://arxiv.org/abs/2307.10854

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

PixArt-sigma. PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

faceswap. Deepfakes Software For All

SimSwap. An arbitrary face-swapping framework on images and videos with one single trained model!

DDAMFN. Python

pytorch-grad-cam. Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

gemma. Gemma open-weight LLM library, from Google DeepMind

llama3. The official Meta Llama 3 GitHub site

insightface. State-of-the-art 2D and 3D Face Analysis Project

openface. Face recognition with deep neural networks.

paz. Hierarchical perception library in Python for pose estimation, object detection, instance segmentation, keypoint estimation, face recognition, etc.

onnx. Open standard for machine learning interoperability

facetorch. Python library for analysing faces using PyTorch

retinaface. RetinaFace: Deep Face Detection Library for Python

deepface. A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

commonjs. TypeScript

bottlejs. TypeScript

ink-web. JavaScript

orm. Go

sqlbuilder. Go

sqlc. Generate type-safe code from SQL

sq. sq is a type-safe data mapper and query builder for Go.

jet. Type safe SQL builder with code generation and automatic query result data mapping

stone. Go

testify. A toolkit with common assertions and mocks that plays nicely with the standard library

swag. Automatically generate RESTful API documentation with Swagger 2.0 for Go.

go-i18n. Translate your Go program into multiple languages.

godotenv. A Go port of Ruby's dotenv library (Loads environment variables from .env files)

air. ☁️ Live reload for Go apps

ink.schema.

cloudbase-framework. 腾讯云开发云原生一体化部署工具 🚀 CloudBase Framework：一键部署，不限框架语言，云端一体化开发，基于Serverless 架构

starter-workflows. Accelerating new GitHub Actions workflows

faas. OpenFaaS - Serverless Functions Made Simple

cds. Enterprise-Grade Continuous Delivery & DevOps Automation Open Source Platform

fn. The container native, cloud agnostic serverless platform.

ink. Go

sqlx. general purpose extensions to golang's database/sql

migrate. Database migrations. CLI and Golang library.

casdoor. An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

authelia. The Single Sign-On Multi-Factor portal for web apps, now OpenID Certified™

go-oidc. A Go OpenID Connect client.

cockroach. CockroachDB — the cloud native, distributed SQL database designed for high availability, effortless scale, and control over data placement.

mage. a Make/rake-like dev tool using Go