Discover Python

< More Languages

Discover the top trending Python repositories and projects on Github. Explore the latest trends in Python development.

30 days 90 days All time

professional-programming

A collection of learning resources for curious software engineers

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

magika

Detect file content types with deep learning

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.

fabric

fabric is an open-source framework for augmenting humans using AI.

MediaCrawler

小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频｜评论爬虫、微博帖子｜评论爬虫

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

dspy

DSPy: The framework for programming—not prompting—foundation models

yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

OLMo

Modeling, training, eval, and inference code for OLMo

stable-diffusion-webui

Stable Diffusion web UI

transformer-debugger

dust3r

DUSt3R: Geometric 3D Vision Made Easy

LLaMA-Factory

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

langchain

⚡ Building applications with LLMs through composability ⚡

crewAI

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

ml-mgie

excelCPU

16-bit CPU for Excel, and related files

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

supervision

We write your reusable computer vision tools. 💜

moondream

tiny vision language model

Depth-Anything

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

WARP-Clash-API

该项目可以让你通过订阅的方式使用Cloudflare WARP+，自动获取流量。This project enables you to use Cloudflare WARP+ through subscription, automatically acquiring traffic.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

MetaGPT

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

QAnything

Question and Answer based on Anything.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

SUPIR

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

public-apis

A collective list of free APIs

grok

yt-dlp

A feature-rich command-line audio/video downloader

stable-diffusion-webui-forge

privateGPT

Interact with your documents using the power of GPT, 100% privately, no data leaks

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Fooocus

Focus on prompting and generating

ml-engineering

Machine Learning Engineering Open Book

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

nanoGPT

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

gradio

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

surya

OCR and line detection in 90+ languages

sherlock

🔎 Hunt down social media accounts by username across social networks

generative-models

Generative Models by Stability AI

TTS

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

llama

Inference code for LLaMA models

posthog

🦔 PostHog provides open-source product analytics, session recording, feature flagging and A/B testing that you can self-host.

marker

Convert PDF to markdown quickly with high accuracy

WhisperFusion

WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.

langflow

⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.

fastapi

FastAPI framework, high performance, easy to learn, fast to code, ready for production

mergekit

Tools for merging pretrained large language models.

codellama

Inference code for CodeLlama models

instructor

structured outputs for llms

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

tiktoken

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

GaLore

faster-whisper

Faster Whisper transcription with CTranslate2

trt-llm-rag-windows

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

chroma

the AI-native open-source embedding database

chatgpt-on-wechat

基于大模型搭建的微信聊天机器人，同时支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/GLM-4/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

lama-cleaner

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.

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

apprise

Apprise - Push Notifications that work with just about every platform!

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

streamlit

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

cbscript

CBScript for Minecraft

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

flash-attention

Fast and memory-efficient exact attention

searxng

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

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

DynamiCrafter

DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

lit-gpt

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

lightning-thunder

Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

rembg

Rembg is a tool to remove images background

LlamaGym

Fine-tune LLM agents with online reinforcement learning

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

lm-evaluation-harness

A framework for few-shot evaluation of language models.

pyvideotrans

Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言，并添加配音

gpt-researcher

GPT based autonomous agent that does online comprehensive research on any given topic

img2img-turbo

One-Step Image-to-Image with SD-Turbo

localllm

core

🏡 Open source home automation that puts local control and privacy first.

Ciphey

⚡ Automatically decrypt encryptions without knowing the key or cipher, decode encodings, and crack hashes ⚡

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

openai-python

The official Python library for the OpenAI API

llama-cpp-python

Python bindings for llama.cpp

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

memray

Memray is a memory profiler for Python

frigate

NVR with realtime local object detection for IP cameras

MonoGS

[CVPR'24] Gaussian Splatting SLAM

Miracode

A sharp, readable, vector-y version of Monocraft, the programming font based on Minecraft

haystack

🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

llm

Access large language models from the command-line

http-garden

Differential testing and fuzzing of HTTP servers and proxies

facebookresearch

Python, Jupyter Notebook, C++

microsoft

C#, Python, TypeScript

donnemartin

openai

Python, Jupyter Notebook, JavaScript

public-apis

huggingface

Python, Jupyter Notebook, Rust

google

Python, C++, Go

vinta

Python, JavaScript, HCL

TheAlgorithms

Python, HTML, TypeScript

jackfrued

Python, HTML, Objective-C

pytorch

Python, C++, Jupyter Notebook

tensorflow

Python, Jupyter Notebook, TypeScript

PaddlePaddle

Python, C++, Jupyter Notebook

AUTOMATIC1111

C#, Python, C++

ytdl-org

THUDM

Python, Jupyter Notebook, C++

lucidrains

Python, Nim, Others

google-research

Python, Jupyter Notebook, C++

tiangolo

Python, Shell, TypeScript

521xueweihan

Python, HTML, CSS

pallets

psf

Python, HTML, Dockerfile

NVlabs

Python, Jupyter Notebook, C++

open-mmlab

Python, Jupyter Notebook, C++

google-deepmind

Python, Jupyter Notebook, C++