Discover the top trending Python repositories and projects on Github. Explore the latest trends in Python development.
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.ragflow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)torchtune
A Native-PyTorch Library for LLM Fine-tuningOpen-Sora
Open-Sora: Democratizing Efficient Video Production for AllQAnything
Question and Answer based on Anything.searxng
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.langchain
⚡ Building applications with LLMs through composability ⚡penzai
A JAX research toolkit for building, editing, and visualizing neural networks.WireViz
Easily document cables and wiring harnesseslangflow
⛓️ 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.aiXcoder-7B
official repository of aiXcoder-7B Code Large Language ModelcrewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.dspy
DSPy: The framework for programming—not prompting—foundation modelsstable-diffusion-webui
Stable Diffusion web UIMediaCrawler
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instructor
structured outputs for llmsrecurrentgemma
Open weights language model from Google DeepMind, based on Griffin.nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.whisper
Robust Speech Recognition via Large-Scale Weak Supervisiontransformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.yt-dlp
A feature-rich command-line audio/video downloaderpublic-apis
A collective list of free APIsdocker-android
Android in docker solution with noVNC supported and video recordingMetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programmingmanim
A community-maintained Python framework for creating mathematical animations.PurpleLlama
Set of tools to assess and improve LLM security.LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.gradio
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!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.pyreft
ReFT: Representation Finetuning for Language ModelsEasyContext
Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.posthog
🦔 PostHog provides open-source product analytics, session recording, feature flagging and A/B testing that you can self-host.attorch
A small subset of PyTorch's neural network modules, written purely in Python using OpenAI's Triton.llm-action
本项目旨在分享大模型相关技术原理以及实战经验。DeepFaceLive
Real-time face swap for PC streaming or video callsInternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4Vipex-llm
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with llama.cpp, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc.dust3r
DUSt3R: Geometric 3D Vision Made EasyFooocus
Focus on prompting and generatinggaussian-opacity-fields
Gaussian Opacity Fields for Efficient and Compact Surface Reconstruction in Unbounded Scenesvideo-subtitle-remover
基于AI的图片/视频硬字幕去除、文本水印去除,无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API,本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.privateGPT
Interact with your documents using the power of GPT, 100% privately, no data leakschroma
the AI-native open-source embedding databasesurya
OCR and line detection in 90+ languagesllm2vec
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topicreflex
🕸 Web apps in pure Python 🐍manim
Animation engine for explanatory math videosmarker
Convert PDF to markdown quickly with high accuracypcb2blender
KiCad to Blender 3D model workflowlama-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.lm-evaluation-harness
A framework for few-shot evaluation of language models.OmniLMM
Large Multi-modal Models for Strong Performance and Efficient Deploymentfaster-whisper
Faster Whisper transcription with CTranslate2qiling
A True Instrumentable Binary Emulation Frameworksparrow
Data extraction with ML and LLMPython
All Algorithms implemented in Pythonllama
Inference code for LLaMA modelsTTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and productiontext-generation-inference
Large Language Model Text Generation Inferencemergekit
Tools for merging pretrained large language models.rembg
Rembg is a tool to remove images backgroundMiniGPT4-video
flowmap
Code for "FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent" by Cameron Smith*, David Charatan*, Ayush Tewari, and Vincent SitzmannChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型gdb-dashboard
Modular visual interface for GDB in Pythondescript-audio-codec
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.gorilla
Gorilla: An API store for LLMsfastapi
FastAPI framework, high performance, easy to learn, fast to code, ready for productionfilesystem_spec
A specification that python filesystems should adhere to.moondream
tiny vision language modelflash-attention
Fast and memory-efficient exact attentionasitop
Perf monitoring CLI tool for Apple SiliconminGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) trainingchatgpt-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。frigate
NVR with realtime local object detection for IP camerastrl
Train transformer language models with reinforcement learning.DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.streamlit
Streamlit — A faster way to build and share data apps.stable-audio-tools
Generative models for conditional audio generationgenerative-models
Generative Models by Stability AIpyinfra
pyinfra automates infrastructure super fast at massive scale. It can be used for ad-hoc command execution, service deployment, configuration management and more.LLMSurvey
The official GitHub page for the survey paper "A Survey of Large Language Models".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)codellama
Inference code for CodeLlama modelspeft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型Douyin_TikTok_Download_API
🚀「Douyin_TikTok_Download_API」是一个开箱即用的高性能异步抖音、快手、TikTok、Bilibili数据爬取工具,支持API调用,在线批量解析及下载。supervision
We write your reusable computer vision tools. 💜typer
Typer, build great CLIs. Easy to code. Based on Python type hints.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.SWE-bench
[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?SUPIR
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the WildWingetUI
WingetUI: A better UI for your package managerskitty
Cross-platform, fast, feature-rich, GPU based terminalDrissionPage
基于python的网页自动化工具。既能控制浏览器,也能收发数据包。可兼顾浏览器自动化的便利性和requests的高效率。功能强大,内置无数人性化设计和便捷功能。语法简洁而优雅,代码量少。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.facebookresearch
Python, Jupyter Notebook, C++microsoft
C#, Python, TypeScriptdonnemartin
Python, C++, Javaopenai
Python, Jupyter Notebook, JavaScriptpublic-apis
Pythonhuggingface
Python, Jupyter Notebook, Rustvinta
Python, JavaScript, GoTheAlgorithms
Python, TypeScript, HTMLpytorch
Python, C++, Jupyter Notebookjackfrued
Python, HTML, Objective-CPaddlePaddle
Python, C++, Jupyter Notebooktensorflow
Python, Jupyter Notebook, C++AUTOMATIC1111
C#, Python, C++ytdl-org
PythonTHUDM
Python, Jupyter Notebook, C++lucidrains
Python, Nim, Othersgoogle-research
Python, Jupyter Notebook, C++tiangolo
Python, Shell, TypeScript521xueweihan
Python, HTML, CSSpallets
Python, HTMLpsf
Python, HTML, TypeScriptNVlabs
Python, Jupyter Notebook, C++google-deepmind
Python, Jupyter Notebook, C++open-mmlab
Python, Jupyter Notebook, C++Love Open Source and this site? Check out how you can help us