101.opendatalab / MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
+2,057 stars
from 80,890 · score 7.63
Trending repositories
Ranked by Attention Score: stars gained over the last 30 complete days
101–200 of 2,988 by Attention Score · Oct 4, 2026 – Nov 2, 2026 (UTC)
102.wshobson / agents
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
+2,013 stars
from 40,068 · score 7.61
103.asgeirtj / system_prompts_leaks
Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.
+1,999 stars
from 68,597 · score 7.60
104.karpathy / autoresearch
AI agents running research on single-GPU nanochat training automatically
+1,983 stars
from 97,040 · score 7.59
105.openai / whisper
Robust Speech Recognition via Large-Scale Weak Supervision
+1,959 stars
from 109,773 · score 7.58
106.sickn33 / agentic-awesome-skills
2,884+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection and plan preview. CLI, MCP and plugins.
+1,929 stars
from 47,060 · score 7.57
107.Jakeschincariol / linkedin-agent-skill
Eleven free Claude skills that run a LinkedIn account: posts off 21 hook formulas, comments, replies, profile score, weekly plan, and a humanizer that strips the AI fingerprint and scores the draft before it goes out.
+1,928 stars
from 1,106 · score 7.56
108.MaxLiu22 / Motion2MixamoRig
Retarget human motion from video to an Adobe Mixamo-rigged 3D character.
+1,911 stars
from 10 · score 7.56
109.unslothai / unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
+1,903 stars
from 77,023 · score 7.55
110.shareAI-lab / learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
+1,896 stars
from 77,788 · score 7.55
111.langchain-ai / langchain
The agent engineering platform.
+1,881 stars
from 146,958 · score 7.54
112.huggingface / 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.
+1,872 stars
from 166,548 · score 7.54
113.mem0ai / mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
+1,840 stars
from 66,402 · score 7.52
114.bobeff / open-source-games
A list of open source games.
+1,810 stars
from 15,499 · score 7.50
115.mukul975 / Anthropic-Cybersecurity-Skills
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
+1,790 stars
from 33,614 · score 7.49
116.topoteretes / cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
+1,769 stars
from 31,218 · score 7.48
117.docling-project / docling
Get your documents ready for gen AI
+1,758 stars
from 68,212 · score 7.47
118.MiniMax-AI / MiniMax-H3
No description provided by the repository host.
+1,742 stars
from 9,405 · score 7.46
119.jingyaogong / minimind
🧠 Train a 64M-parameter LLM from scratch in just 2h!
+1,718 stars
from 63,016 · score 7.45
120.alirezarezvani / claude-skills
380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.
+1,708 stars
from 27,414 · score 7.44
121.langchain-ai / langgraph
Build resilient agents.
+1,707 stars
from 42,579 · score 7.44
122.sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+1,692 stars
from 36,656 · score 7.43
123.ZhuLinsen / daily_stock_analysis
LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.
+1,690 stars
from 65,703 · score 7.43
124.Z4nzu / hackingtool
ALL IN ONE Hacking Tool For Hackers
+1,658 stars
from 79,919 · score 7.41
125.PaddlePaddle / 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.
+1,650 stars
from 90,428 · score 7.41
126.bytedance / deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
+1,649 stars
from 83,190 · score 7.41
127.bregman-arie / devops-exercises
Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions
+1,635 stars
from 84,683 · score 7.40
+1,609 stars
from 10,386 · score 7.38
129.StartLuxLabs / StartLux-Decision
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
+1,573 stars
from 59 · score 7.36
130.ithtelab / workbuddy-manager
腾讯 CodeBuddy 账号池管理控制台，内置 OpenAI 兼容反代网关：扫码批量纳管账号、定时签到与保活、密钥分组分发、IP 与模型白名单、调用日志与用量统计；支持带签名校验的一键更新。
+1,565 stars
from 698 · score 7.36
131.3b1b / manim
Animation engine for explanatory math videos
+1,563 stars
from 94,411 · score 7.36
132.wanshuiyin / Auto-claude-code-research-in-sleep
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
+1,561 stars
from 16,887 · score 7.35
133.pytorch / pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
+1,543 stars
from 103,527 · score 7.34
134.nanaism / yomiyasu
AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese
+1,530 stars
from 1,264 · score 7.33
135.smicallef / spiderfoot
SpiderFoot automates OSINT for threat intelligence and mapping your attack surface.
+1,522 stars
from 22,699 · score 7.33
136.soxoj / maigret
🕵️♂️ Collect a dossier on a person by username from 6K websites
+1,474 stars
from 38,132 · score 7.30
137.VectifyAI / PageIndex
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
+1,468 stars
from 38,473 · score 7.29
138.jaredpalmer / kev
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
+1,452 stars
from 8,301 · score 7.28
139.deepopen-com / deepopen
非自回归System 1决策引擎，专为结构化类型决策场景设计 DeepOpen Multilingual, non-autoregressive System 1 decision engine.
+1,441 stars
from 1,654 · score 7.27
140.bojieli / ai-infra-book
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
+1,437 stars
from 5,783 · score 7.27
141.sixtysevenlf / dsh-blender-plugin
DSH × Blender 直连实时插件 v2.6.1：15 个模型工具让 AI 驱动 GUI Blender；支持 dsh-TUI（选中 chip / 页脚状态 / @ 提及 / /blender），活动状态置顶并可一键暂停 AI，原生选中/集合/子元素直送 DSH，随包建模 skill，支持 WSL / Windows / macOS。
+1,432 stars
from 100 · score 7.27
142.mitmproxy / mitmproxy
An interactive TLS-capable intercepting HTTP proxy for penetration testers and software developers.
+1,427 stars
from 45,115 · score 7.26
143.freqtrade / freqtrade
Free, open source crypto trading bot
+1,414 stars
from 54,869 · score 7.25
144.geeklee / srt-whiteboard-animation
将 SRT 字幕做成暖米黄纸张底的流式笔迹白板手绘动画 skill：mask 分区遮罩编排 + stream 连续笔迹（ink→color）。
+1,361 stars
from 3,892 · score 7.22
145.bilibili / Index-Translate
A Multilingual, Multimodal Translation Model Family
+1,356 stars
from 492 · score 7.21
146.ZJU-REAL / Easel
An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的 AI 社交媒体智能体——发现热点趋势、创作内容、一键发布至各大平台，并学习分析哪些内容真正有效，覆盖小红书、抖音、知乎、哔哩哔哩等平台。
+1,355 stars
from 2,939 · score 7.21
147.Robbyant / lingbot-map
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
+1,343 stars
from 17,170 · score 7.20
148.paperless-ngx / paperless-ngx
A community-supported supercharged document management system: scan, index and archive all your documents
+1,336 stars
from 46,197 · score 7.20
149.anthropics / claude-quickstarts
A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
+1,320 stars
from 17,757 · score 7.19
150.KittenML / KittenTTS
Open-source State-of-the-art TTS model which runs on a CPU 😻
+1,312 stars
from 15,453 · score 7.18
151.ace-step / ACE-Step-1.5
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
+1,299 stars
from 12,978 · score 7.17
152.openbq-org / OpenBB
Open Data Platform for analysts, quants and AI agents.
+1,290 stars
from 73,709 · score 7.16
153.searxng / searxng
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
+1,252 stars
from 37,843 · score 7.13
154.HarnessRouter / harnessrouter
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP), an open standard. Your keys, your infrastructure.
+1,251 stars
from 2,582 · score 7.13
155.bmad-code-org / BMAD-METHOD
Breakthrough Method for Agile Ai Driven Development
+1,234 stars
from 53,629 · score 7.12
156.crewAIInc / crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
+1,184 stars
from 59,209 · score 7.08
+1,169 stars
from 58,312 · score 7.06
158.frappe / erpnext
Free and Open Source Enterprise Resource Planning (ERP)
+1,145 stars
from 39,690 · score 7.04
159.ATH-MaaS / Pixelle-Video
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
+1,142 stars
from 28,515 · score 7.04
160.langflow-ai / langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
+1,140 stars
from 155,090 · score 7.04
161.abi / screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
+1,127 stars
from 79,841 · score 7.03
162.HKUDS / nanobot
Your lightweight open-source personal agent.
+1,125 stars
from 48,607 · score 7.03
163.oraios / serena
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
+1,121 stars
from 29,870 · score 7.02
164.PSRben / VisionHOPE
Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.
+1,121 stars
from 244 · score 7.02
165.Usagi-org / ai-goofish-monitor
基于 Playwright 和AI实现的闲鱼多任务实时/定时监控与智能分析系统，配备了功能完善的后台管理UI。帮助用户从闲鱼海量商品中，找到心仪产品。
+1,095 stars
from 14,605 · score 7.00
166.agentskills / agentskills
Specification and documentation for Agent Skills
+1,084 stars
from 25,766 · score 6.99
167.titanwings / distilly
Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.
+1,083 stars
from 25,197 · score 6.99
168.getzep / graphiti
Build Real-Time Knowledge Graphs for AI Agents
+1,057 stars
from 31,357 · score 6.96
169.karpathy / llm-council
LLM Council works together to answer your hardest questions
+1,053 stars
from 25,085 · score 6.96
170.harvard-edge / cs249r_book
Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
+1,036 stars
from 28,727 · score 6.94
171.0x4m4 / hexstrike-ai
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
+1,032 stars
from 12,245 · score 6.94
172.ashishpatel26 / 500-AI-Agents-Projects
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, and more.
+1,002 stars
from 38,217 · score 6.91
173.Jakeschincariol / arena-skill
When Claude keeps giving you bad answers, make 100 versions of it fight to the death. Same task, 100 different strategies, a bracket, one answer left. Free Claude Code skill.
+1,001 stars
from 186 · score 6.91
+999 stars
from 507 · score 6.91
175.rommapp / romm
A beautiful, powerful, self-hosted ROM manager and player.
+994 stars
from 13,201 · score 6.90
176.repowise-dev / repowise
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
+988 stars
from 7,102 · score 6.90
177.chenxiachan / textfold
Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text.
+988 stars
from 0 · score 6.90
178.langchain-ai / deepagents
The batteries-included agent harness.
+985 stars
from 29,879 · score 6.89
179.google-research / timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
+982 stars
from 34,013 · score 6.89
180.maxrave-dev / kotlin-footguns
Battle-tested agent skills mapping the footguns of Kotlin, Compose Multiplatform and the desktop JVM — mined from a production music app, not from documentation.
+978 stars
from 880 · score 6.89
181.TheAlgorithms / Python
All Algorithms implemented in Python
+974 stars
from 224,779 · score 6.88
182.scenario-labs / blender-plugin
Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.
+974 stars
from 13 · score 6.88
183.ScrapeGraphAI / Scrapegraph-ai
Python scraper based on AI
+969 stars
from 31,453 · score 6.88
184.Leonxlnx / cinetic
Cinematic launch films and motion design from code, directed by your coding agent.
+962 stars
from 9 · score 6.87
185.HKUDS / RAG-Anything
"RAG-Anything: All-in-One RAG Framework"
+961 stars
from 23,416 · score 6.87
186.MemPalace / mempalace
The best-benchmarked open-source AI memory system. And it's free.
+955 stars
from 59,269 · score 6.86
187.swisskyrepo / PayloadsAllTheThings
A list of useful payloads and bypass for Web Application Security and Pentest/CTF
+946 stars
from 81,338 · score 6.85
188.ManimCommunity / manim
A community-maintained Python framework for creating mathematical animations.
+946 stars
from 41,167 · score 6.85
189.phone-harness / phone-harness
let your agent control your phone
+946 stars
from 3,107 · score 6.85
190.ADWMC / helm-d
DeepSeek Harness 破甲一体化安全分析插件：Android · Web · Native · Protocol · Malware · AI-Security 全领域聚合（9 bundle + 1 preset）
+935 stars
from 17 · score 6.84
191.d2l-ai / d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
+932 stars
from 81,264 · score 6.84
192.ultralytics / ultralytics
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
+932 stars
from 62,086 · score 6.84
193.onyx-dot-app / onyx
Open Source AI Platform - AI Chat with advanced features that works with every LLM
+923 stars
from 32,229 · score 6.83
194.ant-research / AntOmniEvo
An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.
+918 stars
from 303 · score 6.82
195.google / skills
Agent Skills for Google products and technologies
+917 stars
from 20,852 · score 6.82
196.CloakHQ / CloakBrowser
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed.
+916 stars
from 31,762 · score 6.82
197.karpathy / nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
+905 stars
from 63,434 · score 6.81
198.88lin / workbuddy-auto-signin
自动领取 WorkBuddy / Qoder CN 每日签到积分与成长中心全部奖励 —— Buddy 旅行礼物、派 Buddy、开盲盒、领任务、连登兑换、断登补签全覆盖。无需额外安装依赖，一句话让 AI 自动配好 Windows / macOS 定时任务，零 Token 静默运行。
+902 stars
from 923 · score 6.81
199.z91772524-ai / pojia-next
十五个 AI 客户端的内置提示词一键替换：双击即用、可自证、改前备份、一键还原。v8.26：一键破甲全程托管（自动结束进程+注入+自动拉起）、注入步骤实时提示、写后自检回滚、托盘常驻。免装 Python 单文件 exe，完全免费开源。
+896 stars
from 84 · score 6.80
200.MetaCubeX / mihomo
A simple Python Pydantic model for Honkai: Star Rail parsed data from the Mihomo API.
+895 stars
from 34,531 · score 6.80