401.xinxuxin / keystone-bench
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
+142 stars
from 931 · score 4.96
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
401–500 of 2,462 by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
402.HKUDS / LightRAG
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
+141 stars
from 40,327 · score 4.96
403.MemoriLabs / Memori
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
+141 stars
from 17,144 · score 4.96
404.Tavotto / Tavotto
AI drew your research figure. Tavotto makes it publication-ready: edit matplotlib and AI-generated figures on a canvas, lay out multi-panel pages in mm, check journal rules before export. Scripts stay untouched.
+141 stars
from 486 · score 4.96
405.everyinfra / 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
406.mvt-project / mvt
MVT (Mobile Verification Toolkit) helps with conducting forensics of mobile devices in order to find signs of a potential compromise.
+139 stars
from 15,536 · score 4.94
407.actionow-ai / vvv
一次构建视频模板，多次复用：给 Claude Code、Codex 等 25+ 个 Agent 的开源可编辑婚礼视频模板与 Agent Skill。Build a video template once, reuse it across coding agents.
+139 stars
from 371 · score 4.94
408.Phocinae / 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
409.scrapy / scrapy
Scrapy, a fast high-level web crawling & scraping framework for Python.
+138 stars
from 65,024 · score 4.93
410.Datalux / Osintgram
Osintgram is a OSINT tool on Instagram. It offers an interactive shell to perform analysis on Instagram account of any users by its nickname
+138 stars
from 15,224 · score 4.93
411.Tencent-Hunyuan / Hy-SimulMT
No description provided by the repository host.
+138 stars
from 84 · score 4.93
412.Shyboy0499 / precondition-library
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
+137 stars
from 168 · score 4.93
413.SimplifyJobs / Summer2027-Internships
Summer 2027 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.
+136 stars
from 48,126 · score 4.92
414.Wan-Video / Wan2.2
Wan: Open and Advanced Large-Scale Video Generative Models
+136 stars
from 18,172 · score 4.92
415.linyqh / NarratoAI
利用 AI 大模型，一键解说并剪辑视频
+136 stars
from 11,535 · score 4.92
416.trailofbits / skills
Trail of Bits skills for security research, vulnerability detection, and audit workflows
+136 stars
from 7,801 · score 4.92
417.daixudk96-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
+136 stars
from 74 · score 4.92
419.harvard-edge / cs249r_book
Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
+135 stars
from 29,628 · score 4.91
420.Prophetlab / Investor-Last-Exam
Investor’s Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
+135 stars
from 0 · score 4.91
421.Aider-AI / aider
aider is AI pair programming in your terminal
+134 stars
from 49,751 · score 4.91
422.assafkip / claudemy
Claudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it researches the web and builds a course of 2-minute audio lessons with cited sources. A free Claude Code skill.
+134 stars
from 450 · score 4.91
423.emmabostian / developer-portfolios
A list of developer portfolios for your inspiration
+133 stars
from 27,380 · score 4.90
424.chris-ritsen / samsung-tv-root
Samsung Tizen root
+133 stars
from 361 · score 4.90
425.JMS1717 / ming-voice
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
+133 stars
from 285 · score 4.90
426.confident-ai / deepeval
The LLM Evaluation Framework
+132 stars
from 19,099 · score 4.89
427.karpathy / minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
+132 stars
from 10,848 · score 4.89
428.ikow / php2shell-poc
CVE-2026-109618/109619 — 5 RCE chains + detection rules (Suricata, Sigma, ModSecurity). PHP session.upload_progress pre-auth exploit research.
+132 stars
from 1,790 · score 4.89
429.ekzhang / resin
🧱 Experimental library for building inference engines
+132 stars
from 230 · score 4.89
430.AlibabaResearch / abench
No description provided by the repository host.
+132 stars
from 15 · score 4.89
431.vnpy / vnpy
基于Python的开源量化交易平台开发框架
+130 stars
from 46,055 · score 4.88
432.fishaudio / fish-speech
SOTA Open Source TTS
+130 stars
from 33,402 · score 4.88
433.sanjayadanushka712 / TaskFlow
End-to-end DevOps TaskFlow API — FastAPI, PostgreSQL, SQLAlchemy, Alembic, Docker Compose, Pytest and GitHub Actions CI,Kubernetes,prometheus,Grafana,helm,k9s,kompose,minikube
+130 stars
from 4 · score 4.88
434.baihua2471 / mcd-expiry-butler
看看哪些麦当劳权益快到期，哪些值得用，哪些不用为了到期硬消费。基于麦当劳官方 MCP 的 WorkBuddy Skill：只读查询优惠券与积分，按预算给出最多两套经官方接口试算的用餐方案。McDonald's coupon & points expiry assistant — a WorkBuddy Skill on the official McDonald's MCP. Read-only queries, official price calculation, max 2 budget-friendly plans.
+130 stars
from 7 · score 4.88
435.microsoft / SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
+129 stars
from 18,676 · score 4.87
436.WenyuChiou / ai-research-skills
Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.
+129 stars
from 406 · score 4.87
437.CuboiLeo / SuperMimic-Reproduced
Reproduction of SuperMimic (arXiv:2610.28480): learned differentiable world model + BPTT policy for G1 humanoid motion tracking, on mjlab/MuJoCo Warp
+129 stars
from 220 · score 4.87
438.huggingface / smolagents
🤗 smolagents: a barebones library for agents that think in code.
+128 stars
from 30,049 · score 4.86
439.KKKKhazix / khazix-skills
数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
+128 stars
from 21,654 · score 4.86
440.GeeeekExplorer / nano-vllm
Nano vLLM
+128 stars
from 16,125 · score 4.86
441.stepll2026 / OntiCards
OntiCards 是面向企业的 AI 数据中枢（AI Data Hub），围绕业务数据库提供一站式能力：数据源连接、元数据理解、自然语言查询、跨源融合、数据质检、查询审计与数据资产管理等
+128 stars
from 545 · score 4.86
442.ryan-bergio03h1 / Instagram-View-Booster-Free-Reel-Story-Views-Tool-2026
Free Instagram view booster for Reels, Stories and Videos. Increase views, reach and engagement with smart delivery system. Easy to use, multiple safety modes, fully configurable.
+128 stars
from 122 · score 4.86
443.sanjayadanushka712 / Neoarch
NeoArch Package Manager for Arch Linux,endeavouros and Arch based distos — multi-source GUI (pacman, AUR, Flatpak, npm, pipx)
+128 stars
from 6 · score 4.86
444.Open-LLM-VTuber / Open-LLM-VTuber
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms
+126 stars
from 14,387 · score 4.84
445.assafelovic / gpt-researcher
An autonomous agent that conducts deep research on any data using any LLM providers
+125 stars
from 30,291 · score 4.84
446.anthropics / claude-code-security-review
An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
+125 stars
from 6,544 · score 4.84
447.Cygnux-Labs / Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
+125 stars
from 234 · score 4.84
+125 stars
from 171 · score 4.84
+124 stars
from 54,966 · score 4.83
450.sanjayadanushka712 / Ghost-Night
Local-only browser fingerprint & identity rotation toolkit for authorized security testing. Tor/obfs4, coherent profiles, WebRTC/DNS leak protection.
+124 stars
from 5 · score 4.83
451.NVIDIA / garak
the LLM vulnerability scanner
+123 stars
from 9,699 · score 4.82
+122 stars
from 1,282 · score 4.81
453.agno-agi / agno
The self-driving agent platform
+121 stars
from 42,888 · score 4.80
454.OpenDCAI / DataFlow
[SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.
+121 stars
from 8,278 · score 4.80
455.xzf-thu / VoiceMem
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
+121 stars
from 2,697 · score 4.80
+121 stars
from 361 · score 4.80
457.zeroFhacker / vibeguard
Security linter for AI-generated code: catches the exact vulnerabilities Copilot, Cursor and ChatGPT repeatedly produce. SQL injection, hardcoded secrets, JWT bypass, command injection and 15+ more rules. Grade A–F. Zero config. CI/CD ready.
+121 stars
from 18 · score 4.80
458.eriklindernoren / ML-From-Scratch
Machine 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.
+120 stars
from 33,128 · score 4.80
459.sanjayadanushka712 / Dracula-Deep
A low-glare Dracula-inspired VS Code theme with measured WCAG AA contrast, muted UI accents, and six-step bracket-depth highlighting.
+120 stars
from 5 · score 4.80
460.pydantic / pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
+119 stars
from 20,865 · score 4.79
461.alexturkey / voxcpm2-turkce-ses-tasarimi
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices.
+119 stars
from 255 · score 4.79
462.Razdva122 / clean-your-tv-lg-webos
A clean home screen for LG webOS. No root. No always-on computer. On-TV Home-button helper, a customizable app grid and dock, and a way back to LG Home.
+119 stars
from 87 · score 4.79
463.BlueKnightNet / Blue-Knight-Proxy-BotHosting
Telegram proxy and owner panel for Bot-Hosting, with a standalone Cloudflare WEB bridge.
+119 stars
from 2 · score 4.79
464.GreyDGL / PentestGPT
Automated Penetration Testing Agentic Framework Powered by Large Language Models
+118 stars
from 16,114 · score 4.78
465.Sallyn0225 / eidolon-sc
和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon）
+118 stars
from 238 · score 4.78
466.Mayzmei / anime-series-maker
2 character sheets + 1 line of story → a finished AI anime episode. Agent skill for Claude Code / Codex, powered by Renoise MCP.
+118 stars
from 16 · score 4.78
467.microsoft / RD-Agent
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report
+117 stars
from 15,060 · score 4.77
468.dwr-git / dewiar-app
Голосовая помощница с командой ИИ-персонажей для Windows, Ubuntu и Android — делает дела голосом · Voice AI assistant that actually does things
+117 stars
from 279 · score 4.77
469.Comfy-Org / ComfyUI-Manager
ComfyUI-Manager is an extension designed to enhance the usability of ComfyUI. It offers management functions to install, remove, disable, and enable various custom nodes of ComfyUI. Furthermore, this extension provides a hub feature and convenience functions to access a wide range of information within ComfyUI.
+116 stars
from 16,572 · score 4.76
470.aixisstudio / Snitch
Real-time network monitor + outbound firewall — see & block every connection. Privacy-first, local-first, Rust fleet agent, SIEM exports, 8 languages. / Moniteur réseau temps réel + pare-feu sortant, agent de flotte Rust, exports SIEM. 100 % local.
+116 stars
from 572 · score 4.76
471.fatihaydost / brand-identity-skill
A Claude Code skill that designs a brand identity as one system: logo, typography and colour palette built together from one brief, measured, compared as identity cards, and delivered as a brand guidelines kit.
+116 stars
from 165 · score 4.76
472.Anjok07 / ultimatevocalremovergui
GUI for a Vocal Remover that uses Deep Neural Networks.
+115 stars
from 26,783 · score 4.75
473.HKUDS / AI-Trader
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
+115 stars
from 22,955 · score 4.75
474.spytheeuclidean-a11y / knoxmap
KnoxMap: turn any real place into a playable Project Zomboid Build 42 map (built on Knoxify)
+115 stars
from 125 · score 4.75
475.eagle-hq / EAGLE-4
Official Inference Code of EAGLE-4
+114 stars
from 989 · score 4.74
476.shuishuipingan / qoder2api-hub
Qoder国际国内多账号反代网关，Qoder 国际国内双区多账号 OpenAI 兼容网关中枢 — COSY 签名推理、稳定设备指纹防风控、OAuth 设备授权免客户端登录、每日签到与 Pro 福利、后台定时调度器、Web 监控看板，支持 Codex / Claude Code 与标准 OpenAI 客户端
+114 stars
from 378 · score 4.74
477.RightBrain-Networks / mnemonic
The anti-vibe coding AI tool built for experienced engineers.
+114 stars
from 0 · score 4.74
478.FoundationAgents / MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
+113 stars
from 71,013 · score 4.74
479.jtydhr88 / screenwriting-skills
Professional agent skills for screenwriting, television writing and dramaturgy
+113 stars
from 1,805 · score 4.74
480.Wunsch2048 / codex-bailong-desktop-pet
Codex&GPT桌宠数据中心 | 你桌面的龙娘小助手
+113 stars
from 171 · score 4.74
481.simular-ai / Agent-S
Agent S: the state-of-the-art open source computer use agents
+112 stars
from 12,737 · score 4.73
482.wesbos / photo-frame-dashboard
Getting ADB, root, backups and custom apps onto locked-down Android photo frames (Skylight Calendar, BIUFRAME)
+112 stars
from 1,514 · score 4.73
+112 stars
from 1,089 · score 4.73
484.Fruank4 / laya-ort
Laya typed decisions on Linux x86_64 via ONNX Runtime
+112 stars
from 271 · score 4.73
485.LINGYK352 / Watchtower
Watchtower | Self-hosted AI security assessment, asset intelligence, and evidence workflows.
+112 stars
from 75 · score 4.73
486.KooroshRH / AReA
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
+112 stars
from 40 · score 4.73
487.echris6 / motion-video-kit
Claude Code skill kit for premium AI-assisted business videos: independent critic loop, motion principles from 28 launch films, quality bar, sound design, business offers, Three.js patterns, scripts
+111 stars
from 1,216 · score 4.72
488.kukemc / bili-cli
为 AI Agent 设计的哔哩哔哩命令行工具：扫码登录、看视频、评论、私信、发动态、投稿，全部 JSON 输出
+111 stars
from 225 · score 4.72
489.Significant-Gravitas / AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
+110 stars
from 187,749 · score 4.71
490.phone-harness / phone-harness
let your agent control your phone
+110 stars
from 3,943 · score 4.71
491.charolettebradford1361985svo-bit / stable-sprite-animation
Reference-preserving sprite animation skill for AI agents: intact-limb walks, small jumps, transparent PNG sequences and GIF.
+110 stars
from 1 · score 4.71
492.deepseek-ai / DeepSeek-V3
No description provided by the repository host.
+109 stars
from 104,597 · score 4.70
493.run-llama / llama_index
LlamaIndex is the document processing platform for AI
+109 stars
from 52,663 · score 4.70
494.composio-community / awesome-codex-skills
A curated list of practical Codex skills for automating workflows across the Codex CLI and API.
+109 stars
from 17,051 · score 4.70
+109 stars
from 1,397 · score 4.70
496.jordanhubbard / daemonarchy
A new desktop installer and curated and signed package ecosystem for FreeBSD; inspired by Omarchy, FreeBSD and the classic world of video games
+109 stars
from 119 · score 4.70
+108 stars
from 53,687 · score 4.69
498.MaxGramser / homeassistant_espscreen
Tessera: beautiful, easy touch screens for Home Assistant on affordable ESP32 panels, 2.8 to 10.1 inch (CYD, Guition, Waveshare). Drag-and-drop editor, no YAML, no MQTT.
+108 stars
from 881 · score 4.69
499.megadose / holehe
holehe allows you to check if the mail is used on different sites like twitter, instagram and will retrieve information on sites with the forgotten password function.
+107 stars
from 15,382 · score 4.68
500.livekit / agents
A framework for building realtime voice AI agents 🤖🎙️📹
+107 stars
from 14,933 · score 4.68