1HKUDS / DeepTutor
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
+10,965 stars
from 42,673 · score 9.30
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
1–100 of 520 by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2google / elephant-goldfish-model
Open-source skills for designing and reviewing software with AI agents
+7,956 stars
from 984 · score 8.98
3Graphify-Labs / graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
+5,300 stars
from 135,226 · score 8.58
4interplains / Zero-Breach-Toolkit
Free, open-source check for traces of mercenary spyware (Pegasus, Predator, Graphite, Candiru and more) on computers, Android phones and iPhone backups. Double-click apps for Windows, Mac and Linux, in 27 languages.
+5,075 stars
from 1 · score 8.53
5TauricResearch / TradingAgents
TradingAgents: Multi-Agents LLM Financial Trading Framework
+4,941 stars
from 114,582 · score 8.51
6microsoft / TokenEconomizer
Experience-Driven Black-Box Cost Control for Coding Agents
+3,653 stars
from 226 · score 8.20
7deepseek-ai / DeepInfer
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
+2,424 stars
from 22,386 · score 7.79
8google-research / harness2
No description provided by the repository host.
+2,282 stars
from 19,605 · score 7.73
9NVIDIA / SkillSpector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
+2,260 stars
from 21,603 · score 7.72
10Edge0-AI / Edge0
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
+1,750 stars
from 7,178 · score 7.47
11anthropics / knowledge-work-plugins
Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork
+1,388 stars
from 32,973 · score 7.24
12usestrix / strix
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
+1,348 stars
from 71,883 · score 7.21
13google / artemis
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
+1,296 stars
from 14,791 · score 7.17
14anthropics / claude-plugins-official
Official, Anthropic-managed directory of high quality Claude Code Plugins.
+1,159 stars
from 44,558 · score 7.06
15agentscope-ai / agentscope
Build and run agents you can see, understand and trust.
+1,132 stars
from 33,993 · score 7.03
16Yuan1z0825 / nature-skills
符合nature论文学术表达和科研绘图的Skill
+1,121 stars
from 50,574 · score 7.02
17HKUDS / CLI-Anything
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
+927 stars
from 57,109 · score 6.83
18Murea-Labs / InWorld
No description provided by the repository host.
+828 stars
from 205 · score 6.72
+782 stars
from 115 · score 6.66
20headroomlabs-ai / headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
+754 stars
from 77,813 · score 6.63
21Shubhamsaboo / awesome-llm-apps
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
+627 stars
from 143,047 · score 6.44
22vllm-project / vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
+593 stars
from 95,485 · score 6.39
23OpenMOSS / MOSS-Image
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
+585 stars
from 1,838 · score 6.37
24interplains / zero-breach
Zero Breach — local, read-only scanner that checks a computer for indicators of the AdFection / Candiru ad-delivered spyware campaign. No network, no admin, no dependencies.
+561 stars
from 549 · score 6.33
25patch-gg / anymove
Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out.
+542 stars
from 0 · score 6.30
26NandhaKishorM / laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
+511 stars
from 34,302 · score 6.24
27datalab-to / indra
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
+491 stars
from 1,086 · score 6.20
28unclecode / crawl4ai
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord https://discord.gg/VuxzM8mtf
+461 stars
from 86,261 · score 6.14
29mem0ai / mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
+447 stars
from 67,795 · score 6.10
30Infini-AI-Lab / hermit
A framework for continual learning and recursive self-improvement through harness adapter evolution.
+441 stars
from 111 · score 6.09
31breezeblue-ai / breeze-tts
Official PyTorch inference for Breeze TTS 2
+426 stars
from 877 · score 6.06
32PaddlePaddle / 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.
+418 stars
from 91,660 · score 6.04
33mukul975 / 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
+392 stars
from 35,012 · score 5.97
34unslothai / 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.
+365 stars
from 78,561 · score 5.90
35OpenBMB / VoxCPM
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
+353 stars
from 40,590 · score 5.87
36drowzeys / Imagination-Studio-by-keys-Wasserman
Imagination Studio by keys+Wasserman powered by TensorFold: an AI film studio for Mac and NVIDIA DGX Spark. Plan a film like a crew (Slate workflow by Sam Wasserman), render Qwen-Image-2.1 / FLUX3-K pictures and MiniMax H3 / FastH3 video with sound on TensorFold.
+340 stars
from 161 · score 5.83
37thomasunise / casecite
CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.
+333 stars
from 5 · score 5.81
38kornia / kornia
🐍 Geometric Computer Vision Library for Spatial AI
+329 stars
from 11,447 · score 5.80
39jingyaogong / minimind
🧠 Train a 64M-parameter LLM from scratch in just 2h!
+325 stars
from 64,409 · score 5.79
40goldmansachs / gs-quant
Python toolkit for quantitative finance
+318 stars
from 13,549 · score 5.77
+316 stars
from 1,912 · score 5.76
42Robbyant / lingbot-map
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
+305 stars
from 18,208 · score 5.72
43google-deepmind / detectorscope
Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)
+299 stars
from 9 · score 5.70
44anthropics / single-agent-loop-kit
No description provided by the repository host.
+289 stars
from 176 · score 5.67
45rockmatrix-ai / EdgeRock
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
+287 stars
from 619 · score 5.66
46KittenML / KittenTTS
Open-source State-of-the-art TTS model which runs on a CPU 😻
+286 stars
from 16,479 · score 5.66
47ATH-MaaS / Pixelle-Video
🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
+283 stars
from 29,374 · score 5.65
+281 stars
from 0 · score 5.64
49StreamEval / StreamEval
🔥 The first-ever interactive streaming video generation benchmark.
+269 stars
from 342 · score 5.60
50C4rohan / Lampline
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
+264 stars
from 267 · score 5.58
51huggingface / 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.
+259 stars
from 168,161 · score 5.56
52bojieli / 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
+250 stars
from 6,970 · score 5.53
53dengmeiluan / ticket-monitoring
✈️ 自托管的多渠道机票价格监控：航班明细采集 → 钉钉图文推送 → 达标四层强提醒。国内航线与国际航线（五洲目的地）同一套采集-判定-推送链路；数据留在本机，配置全在网页，开源免费。
+247 stars
from 143 · score 5.51
54syv-ai / HyperQwen
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
+243 stars
from 2,231 · score 5.50
55FlashML-org / FreeVideo
Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.
+241 stars
from 2,332 · score 5.49
56topoteretes / cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
+237 stars
from 32,750 · score 5.47
57agentskills / agentskills
Specification and documentation for Agent Skills
+234 stars
from 26,616 · score 5.46
58jaredpalmer / kev
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
+232 stars
from 9,521 · score 5.45
59google-research / timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
+225 stars
from 34,770 · score 5.42
60haolpku / Omni-Edu
OmniEdu: Open Foundation Models for Learning and Teaching
+224 stars
from 266 · score 5.42
61ZJU-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。
+222 stars
from 4,072 · score 5.41
62ArcAnima / ComfyUI-Anima-Ref-Adapter
Reference-image character and style transfer for Anima in ComfyUI (offset-RoPE reference frame + LoRA)
+222 stars
from 0 · score 5.41
63jundot / omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
+219 stars
from 23,050 · score 5.39
64getzep / graphiti
Build Real-Time Knowledge Graphs for AI Agents
+204 stars
from 32,210 · score 5.32
65HarnessRouter / 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.
+203 stars
from 3,630 · score 5.32
66hummingbot / hummingbot
Open source software that helps you create and deploy high-frequency crypto trading bots
+198 stars
from 20,703 · score 5.29
67opensandbox-group / OpenSandbox
Secure, Fast, and Extensible Sandbox runtime for AI agents.
+198 stars
from 16,162 · score 5.29
68Arekejoker / qwen21-nsfw-pose-skill
Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw
+198 stars
from 3,723 · score 5.29
69anthropics / financial-services
No description provided by the repository host.
+197 stars
from 40,776 · score 5.29
70google / skills
Agent Skills for Google products and technologies
+195 stars
from 21,574 · score 5.28
71sgl-project / sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
+192 stars
from 38,156 · score 5.26
72google / langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
+186 stars
from 39,041 · score 5.23
73chenxiachan / textfold
Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text.
+182 stars
from 678 · score 5.21
74comet-ml / opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
+179 stars
from 22,919 · score 5.19
75langbot-app / LangBot
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Kimi, openclaw / hermes agent, deerflow
+179 stars
from 18,482 · score 5.19
76MaxLiu22 / Motion2MixamoRig
Retarget human motion from video to an Adobe Mixamo-rigged 3D character.
+177 stars
from 1,678 · score 5.18
77srbhr / Resume-Matcher
The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.
+176 stars
from 28,860 · score 5.18
78ranaroussi / yfinance
Download market data from Yahoo! Finance's API
+174 stars
from 25,608 · score 5.16
79Evil0ctal / Douyin_TikTok_Download_API
🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API，支持 AI agent 通过 MCP 调用与离线语音转文字，Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.
+173 stars
from 20,895 · score 5.16
80huggingface / lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
+168 stars
from 28,464 · score 5.13
81home-assistant / core
:house_with_garden: Open source home automation that puts local control and privacy first.
+165 stars
from 91,729 · score 5.11
+164 stars
from 747 · score 5.11
83EverMind-AI / EverOS
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
+154 stars
from 13,600 · score 5.04
84datalab-to / omni_parse_bench
No description provided by the repository host.
+154 stars
from 30 · score 5.04
85mistralai / timestral
Repository for Timestral, the time-series foundation model by Mistral AI
+152 stars
from 875 · score 5.03
86patch-gg / crowdbricks
Batched NVIDIA MotionBricks: generate the motion of hundreds of characters in one model call.
+150 stars
from 0 · score 5.02
87sgaofen / humanizer-local-model
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
+148 stars
from 528 · score 5.00
88KingKongRobotics / jumper
🦀 Jumper — an crab robot.
+147 stars
from 2,887 · score 5.00
89QwenLM / Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.
+145 stars
from 14,008 · score 4.98
90dgtlmoon / changedetection.io
Best and simplest tool for website change detection, web page monitoring, and website change alerts. Perfect for tracking content changes, price drops, restock alerts, and website defacement monitoring—all for free or enjoy our SaaS plan!
+143 stars
from 35,291 · score 4.97
91everyinfra / everyinfra-agent-plugins
EveryInfra MCP server & agent plugin: scraper API for TikTok, Instagram, Amazon, YouTube, Xiaohongshu & Douyin. 573 data APIs across 106 platforms, from $0.56/1K calls. For Claude Code, Cursor, Codex.
+140 stars
from 54 · score 4.95
92Phocinae / Phocinae-Largha-150M-v1
斑海豹 — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions. 小海豹，大决断。
+139 stars
from 315 · score 4.94
93Wan-Video / Wan2.2
Wan: Open and Advanced Large-Scale Video Generative Models
+136 stars
from 18,172 · score 4.92
94daixudk96-max / agent-skill-gate
Agent Skill 步进治理体系：由程序保证 Agent 不跳步骤（step-gate Rust 门控 + 交付门 + 链治理）
+136 stars
from 604 · score 4.92
95Aider-AI / aider
aider is AI pair programming in your terminal
+134 stars
from 49,751 · score 4.91
96confident-ai / deepeval
The LLM Evaluation Framework
+132 stars
from 19,099 · score 4.89
97ekzhang / resin
🧱 Experimental library for building inference engines
+132 stars
from 230 · score 4.89
98AlibabaResearch / abench
No description provided by the repository host.
+132 stars
from 15 · score 4.89
99huggingface / smolagents
🤗 smolagents: a barebones library for agents that think in code.
+128 stars
from 30,049 · score 4.86
100assafelovic / gpt-researcher
An autonomous agent that conducts deep research on any data using any LLM providers
+125 stars
from 30,291 · score 4.84