从爬虫到AI:GitHub 2025Python趋势综合榜项目(收藏)

327 阅读15分钟

GitHub 2025Python趋势综合榜项目(收藏)

日期项目starsfork描述
2025/10/4google / tunix1,338118A JAX-native LLM Post-Training Library
2025/10/4microsoft / agent-framework1,802188A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
2025/10/4dataease / SQLBot3,560349🔥 基于大模型和 RAG 的智能问数系统。Text-to-SQL Generation via LLMs using RAG.
2025/10/4airweave-ai / airweave3,635446Airweave lets agents search any app
2025/10/4imputnet / helium4,20757Private, fast, and honest web browser
2025/10/4HKUDS / AutoAgent7,453994AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework
2025/10/4HKUDS / RAG-Anything7,975902RAG-Anything: All-in-One RAG Framework
2025/10/4Physical-Intelligence / openpi8,057935
2025/10/4hsliuping / TradingAgents-CN8,5191,979基于多智能体 LLM 的中文金融交易框架 - TradingAgents 中文增强版
2025/10/4ollama-python8,606829Ollama Python library
2025/10/4emcie-co / parlant13,3101,067LLM agents built for control. Designed for real-world use. Deployed in minutes.
2025/10/4onyx-dot-app / onyx15,3252,047Open Source AI Platform - AI Chat with advanced features that works with every LLM
2025/10/4Alibaba-NLP / DeepResearch15,3451,131Tongyi DeepResearch, the Leading Open-source DeepResearch Agent
2025/10/4lukas-blecher / LaTeX-OCR15,6961,253pix2tex: Using a ViT to convert images of equations into LaTeX code.
2025/10/4pathwaycom / pathway44,3241,356Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
2025/10/4harry0703 / MoneyPrinterTurbo45,5756,371利用 AI 大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
2025/10/4CorentinJ / Real-Time-Voice-Cloning57,8739,293Clone a voice in 5 seconds to generate arbitrary speech in real-time
2025/10/4commaai / openpilot58,18910,289openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
2025/10/4yt-dlp / yt-dlp129,49910,376A feature-rich command-line audio/video downloader
2025/10/3anthropics / claude-agent-sdk-python1,992252
2025/10/3shiyu-coder / Kronos6,7851,416Kronos: A Foundation Model for the Language of Financial Markets
2025/10/3Lightricks / LTX-Video8,197731Official repository for LTX-Video
2025/10/2YILING0013 / AI_NovelGenerator2,196445使用 ai 生成多章节的长篇小说,自动衔接上下文、伏笔
2025/10/2bytedance / Dolphin7,229580The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
2025/10/2TheAlgorithms / Python209,74048,295All Algorithms implemented in Python
2025/10/1Byaidu / PDFMathTranslate28,1472,483PDF 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
2025/10/1Shubhamsaboo / awesome-llm-apps70,9149,081Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
2025/10/1bregman-arie / devops-exercises78,81017,797Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions
2025/10/1fastapi / fastapi90,1647,978FastAPI framework, high performance, easy to learn, fast to code, ready for production
2025/9/30knownsec / aipyapp2,494211AI-Powered Python & Python-Powered AI (Python-Use)
2025/9/30WECENG / ticket-purchase3,672487大麦自动抢票,支持人员、城市、日期场次、价格选择
2025/9/30jsvine / pdfplumber8,585792Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
2025/9/30frappe / erpnext29,2069,461Free and Open Source Enterprise Resource Planning (ERP)
2025/9/29QuentinFuxa / WhisperLiveKit7,322661Real-time & local speech-to-text, translation, and speaker diarization. With server & web UI.
2025/9/29microsoft / qlib31,4704,846Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with github.com/microsoft/R… to automate R&D process.
2025/9/28Olow304 / memvid9,424778Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
2025/9/28resemble-ai / chatterbox13,4671,722SoTA open-source TTS
2025/9/28roboflow / supervision35,3062,902We write your reusable computer vision tools. 💜
2025/9/28ytdl-org / youtube-dl138,15710,506Command-line program to download videos from YouTube.com and other video sites
2025/9/27HKUDS / DeepCode7,213997DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)
2025/9/27exo-explore / exo31,4982,090Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
2025/9/27ultralytics / ultralytics46,4088,991Ultralytics YOLO 🚀
2025/9/27donnemartin / system-design-primer321,22752,459Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
2025/9/26confident-ai / deepeval11,180965The LLM Evaluation Framework
2025/9/26Asabeneh / 30-Days-Of-Python50,1049,56130 days of Python programming challenge is a step-by-step guide to learn the Python programming language in 30 days. This challenge may take more than100 days, follow your own pace. These videos may help too: www.youtube.com/channel/UC7…
2025/9/26microsoft / markitdown80,0724,411Python tool for converting files and office documents to Markdown.
2025/9/25aliasrobotics / cai4,237583Cybersecurity AI (CAI), the framework for AI Security
2025/9/25MODSetter / SurfSense8,134616Open Source Alternative to NotebookLM / Perplexity, connected to external sources such as Search Engines, Slack, Linear, Jira, ClickUp, Confluence, Notion, YouTube, GitHub, Discord and more. Join our discord: discord.gg/ejRNvftDp9
2025/9/25laramies / theHarvester14,5612,309E-mails, subdomains and names Harvester - OSINT
2025/9/25virattt / ai-hedge-fund41,3707,276An AI Hedge Fund Team
2025/9/25freqtrade / freqtrade42,9628,702Free, open source crypto trading bot
2025/9/25django / django85,15433,006The Web framework for perfectionists with deadlines.
2025/9/24HKUDS / AI-Researcher2,894335[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: novix.science/chat
2025/9/24sentient-agi / ROMA3,393469Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
2025/9/24X-PLUG / MobileAgent5,773563Mobile-Agent: The Powerful GUI Agent Family
2025/9/24google-research / timesfm6,321551TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
2025/9/24Kludex / uvicorn9,745850An ASGI web server, for Python. 🦄
2025/9/24OpenBMB / MiniCPM-V21,9121,638MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and Video Understanding on Your Phone
2025/9/24EbookFoundation / free-programming-books370,08364,287📚 Freely available programming books
2025/9/23lllyasviel / Fooocus46,5517,487Focus on prompting and generating
2025/9/23AUTOMATIC1111 / stable-diffusion-webui156,68329,065Stable Diffusion web UI
2025/9/229001 / copyparty30,7161,214Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps
2025/9/22mindsdb / mindsdb36,0205,786AI's query engine - Platform for building AI that can answer questions over large scale federated data. - The only MCP Server you'll ever need
2025/9/21OpenMind / OM145997Modular AI runtime for robots
2025/9/21ml-explore / mlx-lm2,381255Run LLMs with MLX
2025/9/21unslothai / unsloth45,9143,752Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
2025/9/21odoo / odoo45,95029,652Odoo. Open Source Apps To Grow Your Business.
2025/9/20NVIDIA / garak5,942628the LLM vulnerability scanner
2025/9/20facebookresearch / detectron233,2477,806Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
2025/9/19PaddlePaddle / PaddleOCR54,7828,663Turn 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 80+ languages.
2025/9/17Plachtaa / seed-vc3,172371zero-shot voice conversion & singing voice conversion, with real-time support
2025/9/17ccxt / ccxt38,7138,199A cryptocurrency trading API with more than 100 exchanges in JavaScript / TypeScript / Python / C# / PHP / Go
2025/9/16Cinnamon / kotaemon24,2181,976An open-source RAG-based tool for chatting with your documents.
2025/9/15Arindam200 / awesome-ai-apps5,768691A collection of projects showcasing RAG, agents, workflows, and other AI use cases
2025/9/15deepset-ai / haystack22,4912,360AI 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.
2025/9/15unclecode / crawl4ai53,1055,291🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: discord.gg/jP8KfhDhyN
2025/9/14fla-org / flash-linear-attention3,244252🚀 Efficient implementations of state-of-the-art linear attention models
2025/9/14Azure / azure-sdk-for-python5,3163,115This repository is for active development of the Azure SDK for Python. For consumers of the SDK we recommend visiting our public developer docs at learn.microsoft.com/python/azur… or our versioned developer docs at azure.github.io/azure-sdk-f….
2025/9/14huggingface / transformers149,69530,386🤗 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.
2025/9/12mxrch / GHunt17,5811,484🕵️‍♂️ Offensive Google framework.
2025/9/12agno-agi / agno33,1794,224High-performance runtime for multi-agent systems. Build, run and manage secure multi-agent systems in your cloud.
2025/9/11weaviate / elysia1,587207Python package and backend for the Elysia platform app.
2025/9/11ahujasid / blender-mcp13,2961,257
2025/9/111Panel-dev / MaxKB18,2222,367🔥 MaxKB is an open-source platform for building enterprise-grade agents. MaxKB 是强大易用的开源企业级智能体平台。
2025/9/10Vector-Wangel / XLeRobot2,807264XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
2025/9/10hiroi-sora / Umi-OCR36,8743,646OCR software, free and offline. 开源、免费的离线 OCR 软件。支持截屏/批量导入图片,PDF 文档识别,排除水印/页眉页脚,扫描/生成二维码。内置多国语言库。
2025/9/8coleam00 / ottomator-agents4,0201,439All the open source AI Agents hosted on the oTTomator Live Agent Studio platform!
2025/9/8microsoft / BitNet21,7141,652Official inference framework for 1-bit LLMs
2025/9/7oraios / serena11,653807A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)
2025/9/7apache / airflow42,14315,542Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
2025/9/5socfortress / Wazuh-Rules980243Advanced Wazuh Rules for more accurate threat detection. Feel free to implement within your own Wazuh environment, contribute, or fork!
2025/9/5eriklindernoren / ML-From-Scratch27,9444,860Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
2025/9/5crewAIInc / crewAI37,5634,953Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
2025/9/5ansible / ansible66,24724,073Ansible is a radically simple IT automation platform that makes your applications and systems easier to deploy and maintain. Automate everything from code deployment to network configuration to cloud management, in a language that approaches plain English, using SSH, with no agents to install on remote systems. docs.ansible.com.
2025/9/4vllm-project / vllm57,1149,880A high-throughput and memory-efficient inference and serving engine for LLMs
2025/9/3IBM / mcp-context-forge2,289261A Model Context Protocol (MCP) Gateway & Registry. Serves as a central management point for tools, resources, and prompts that can be accessed by MCP-compatible LLM applications. Converts REST API endpoints to MCP, composes virtual MCP servers with added security and observability, and converts between protocols (stdio, SSE, Streamable HTTP).
2025/9/2hao-ai-lab / FastVideo2,143158A unified inference and post-training framework for accelerated video generation.
2025/9/2willccbb / verifiers2,837309Verifiers for LLM Reinforcement Learning
2025/9/2denizsafak / abogen3,244163Generate audiobooks from EPUBs, PDFs and text with synchronized captions.
2025/9/2HunxByts / GhostTrack5,306608Useful tool to track location or mobile number
2025/9/2microsoft / mcp-for-beginners10,1742,968This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.
2025/9/1paperless-ngx / paperless-ngx31,3281,915A community-supported supercharged document management system: scan, index and archive all your documents
2025/8/29santinic / audiblez5,067328Generate audiobooks from e-books
2025/8/28OpenPipe / ART6,176386Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
2025/8/27OpenBB-finance / OpenBB51,4134,836Investment Research for Everyone, Everywhere.
2025/8/26spotDL / spotify-downloader21,4731,892Download your Spotify playlists and songs along with album art and metadata (from YouTube if a match is found).
2025/8/25QwenLM / Qwen3-Coder12,659866Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
2025/8/24NVIDIA-NeMo / RL754112Scalable toolkit for efficient model reinforcement
2025/8/23frappe / hrms6,4961,590Open Source HR and Payroll Software
2025/8/22langchain-ai / open_deep_research8,2171,087
2025/8/22tadata-org / fastapi_mcp9,440723Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
2025/8/21laude-institute / terminal-bench491137A benchmark for LLMs on complicated tasks in the terminal
2025/8/21hesreallyhim / awesome-claude-code11,757632A curated list of awesome commands, files, and workflows for Claude Code
2025/8/20LMCache / LMCache4,874531Supercharge Your LLM with the Fastest KV Cache Layer
2025/8/20awslabs / mcp5,882760AWS MCP Servers — helping you get the most out of AWS, wherever you use MCP.
2025/8/20bytedance / UI-TARS7,240502
2025/8/16manycore-research / SpatialLM3,705284SpatialLM: Training Large Language Models for Structured Indoor Modeling
2025/8/16microsoft / magentic-ui7,241739A research prototype of a human-centered web agent
2025/8/16budtmo / docker-android12,0491,440Android in docker solution with noVNC supported and video recording
2025/8/16datalab-to / marker27,7251,816Convert PDF to markdown + JSON quickly with high accuracy
2025/8/3Huanshere / VideoLingo14,5241,482Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix 级字幕切割、翻译、对齐、甚至加上配音,一键全自动视频搬运 AI 字幕组
2025/8/3Genesis-Embodied-AI / Genesis26,9042,442A generative world for general-purpose robotics & embodied AI learning.
2025/8/2TideDra / zotero-arxiv-daily2,4162,251Recommend new arxiv papers of your interest daily according to your Zotero libarary.
2025/8/1kijai / ComfyUI-WanVideoWrapper3,639273
2025/8/1SkyworkAI / SkyReels-V23,878489SkyReels-V2: Infinite-length Film Generative model
2025/8/1Alibaba-NLP / WebAgent5,480398🌐 WebAgent for Information Seeking built by Tongyi Lab: WebWalker & WebDancer & WebSailor arxiv.org/pdf/2507.02…
2025/8/1getzep / graphiti15,5761,333Build Real-Time Knowledge Graphs for AI Agents
2025/8/1NanmiCoder / MediaCrawler34,6008,116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、百度贴吧帖子 | 百度贴吧评论回复爬虫 | 知乎问答文章 | 评论爬虫
2025/7/31mikf / gallery-dl14,6371,163Command-line program to download image galleries and collections from several image hosting sites
2025/7/27BerriAI / litellm26,2523,618Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
2025/7/24QwenLM / Qwen323,0011,558Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
2025/7/24yeongpin / cursor-free-vip32,8574,062[Support 0.49.x](Reset Cursor AI MachineID & Bypass Higher Token Limit) Cursor Ai ,自动重置机器 ID , 免费升级使用 Pro 功能: You've reached your trial request limit. / Too many free trial accounts used on this machine. Please upgrade to pro. We have this limit in place to prevent abuse. Please let us know if you believe this is a mistake.
2025/7/23p1ngul1n0 / blackbird4,021485An OSINT tool to search for accounts by username and email in social networks.
2025/7/14landing-ai / agentic-doc1,117107Python library for Agentic Document Extraction from LandingAI
2025/7/13snap-stanford / Biomni1,493161Biomni: a general-purpose biomedical AI agent
2025/7/13ocrmypdf / OCRmyPDF30,1962,078OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
2025/7/13psf / black40,5662,606The uncompromising Python code formatter
2025/7/6megadose / toutatis2,687399Toutatis is a tool that allows you to extract information from instagrams accounts such as e-mails, phone numbers and more