logCong

wechat-article-exporter. 一款在线的 微信公众号文章批量下载 工具，支持导出阅读量与评论数据，无需搭建任何环境，可通过 在线网站 使用，支持 docker 私有化部署和 Cloudflare 部署。 支持下载各种文件格式，其中 HTML 格式可100%还原文章排版与样式。

gzh-design-skill. 把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

xiaomi-miloco. Xiaomi Miloco

phonebuddy. Training open models for agentic phone use with real-app and mock-app environments.

Confucius4-TTS. Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

QAnything. Question and Answer based on Anything.

cc-switch. A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

v2rayN. A GUI client for Windows, Linux and macOS, support Xray and sing-box and others

OpenGame. OpenGame: Open Agentic Coding for Games

Awesome-finance-skills. A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills

awesome-agent-skills. Agent Skills 终极指南：快速入门、资源推荐、精选技能与实用工具 ｜The Ultimate Guide to Agent Skills: QuickStart, Resources, Features&Toolkit

bigset. What if you had all the data in the world?

DeepSeek-Reasonix. DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

openclacky. The most Token-efficient open-source AI Agent

TencentDB-Agent-Memory. TencentDB Agent Memory delivers fully local long-term memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies.

cli. The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.

guizang-ppt-skill. AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

MemPrivacy. MemPrivacy is a privacy-preserving personalized memory management framework for edge-cloud agents.

privacy-filter. OpenAI Privacy Filter

cc-haha. Claude Code 泄露源码 - 本地可运行版本，新增跨平台桌面端软件补齐Computer Use（附带核心模块解析）

awesome-deepseek-agent.

QwenPaw. Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

OpenRoom. A browser-based desktop where AI Agent operates every app through natural language.

hermes-agent. The agent that grows with you

khazix-skills. 数字生命卡兹克开源的 AI Skills 合集

Fay. fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。

nuwa-skill. 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

superpowers. An agentic skills framework & software development methodology that works.

qiushi-skill. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.

zhangxuefeng-skill. 张雪峰.skill — 张雪峰的认知操作系统。高考志愿/考研/职业规划的实战思维框架。由女娲.skill生成。

tong-jincheng-skill. 童锦程视角 Skill — 用深情祖师爷的思维框架分析人际关系

baoyu-skills. TypeScript

GLM-skills. Official skills for the GLM family of models.

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

instructor. structured outputs for llms

colleague-skill. 将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

ex-skill. 前任 skill

dingtalk-workspace-cli. DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is designed for both human users and AI agent scenarios.

wpsnote-skills. Python

autoresearch. AI agents running research on single-GPU nanochat training automatically

twinkle. Twinkle✨: Training workbench to make your model glow.

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

AReaL. The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

awesome-openclaw-skills. The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

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.

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

gemini-voyager. An all-in-one enhancement suite for Google Gemini & AI Studio - timeline navigation, folder management, prompt library, and chat export in one powerful extension. / Google Gemini & AI Studio 全能增强插件：集成时间轴导航、文件夹管理、提示词库及聊天导出等众多功能。

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Open-Claude-Cowork. OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.

coworker. Coworker is the open source Al coworker that lives on your desktop

notebooklm-skill. Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your uploaded documents and get source-grounded, citation-backed answers from Gemini. Features browser automation, library management, persistent authentication, and answers exclusively from your own knowledge base.

Engram. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

MiroThinker. MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

LandPPT. 一个基于LLM的演示文稿生成平台，能够自动将文档内容转换为专业的PPT演示文稿。平台支持多种AI模型，提供丰富的模板和样式选择，让用户能够创建高质量的演示文稿。

opencode. The open source coding agent.

MAI-UI. MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B

gelab-zero. STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities.

banana-slides. 一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌

12-factor-agents. What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

MiMo-V2-Flash. MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model

CosyVoice. Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Open-AutoGLM-Hybrid. Open-AutoGLM混合方案 - 在手机上运行AI自动化，无需电脑

Open-AutoGLM. An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

cua. Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

MonkeyOCR. A lightweight LMM-based Document Parsing Model

RSSHub. 🧡 Everything is RSSible

Folo. 🧡 Folo is the AI RSS Reader

LeetCodeAnimation. Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路,完整单步/回看/变速/语音讲解在 algomooc.com）

Awesome-Nano-Banana-images. A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development of image generation and unified models(click to website to see our blog)

llm_benchmark.

chinese-llm-benchmark. 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。

BettaFish. 微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

LongCat-Flash-Omni. This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

skills. Public repository for Agent Skills

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

nanochat. The best ChatGPT that $100 can buy.

chrome-devtools-mcp. Chrome DevTools for coding agents

neutts. On-device TTS model by Neuphonic

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

CookLikeHOC. 🥢像老乡鸡🐔那样做饭。已添加2026年发布的《老乡鸡菜品溯源报告 2.0中新出现的菜品。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

BMAD-METHOD. Breakthrough Method for Agile Ai Driven Development

system_prompts_leaks. Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT GPT-5.6, Codex GPT-5.6, GPT-5.5. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

stable-diffusion-webui. Stable Diffusion web UI

DFT. [ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

coze-studio. An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

XHS-Downloader. 小红书（XiaoHongShu、RedNote）链接提取/作品采集工具：提取账号发布、收藏、点赞、专辑作品链接；提取搜索结果作品、用户链接；采集小红书作品信息；提取小红书作品下载地址；下载小红书作品文件

FastGateway. a high-performance, lightweight API gateway built with Spring Cloud Gateway

fastmcp. 🚀 The fast, Pythonic way to build MCP servers and clients.

DailyHotApi. 🔥 今日热榜 API，一个聚合热门数据的 API 接口，支持 RSS 模式 及 Vercel 部署 | 前端页面：https://github.com/imsyy/DailyHot

ChinaTextbook. 所有小初高、大学PDF教材。

social-media-agent. 📲 An agent for sourcing, curating, and scheduling social media posts with human-in-the-loop.

MoneyPrinterTurbo. 利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

suna. The Company AI Command Center

PPTAgent. An Agentic Framework for Reflective PowerPoint Generation

Paper2Poster. [NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

DeepResearchAgent. DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coordinate multiple specialized lower-level agents, enabling automated task decomposition and efficient execution across diverse and complex domains.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Awesome-MCP-ZH. MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients

Awesome-LLM-RAG-Application. the resources about the application based on LLM with RAG pattern

python-sdk. The official Python SDK for Model Context Protocol servers and clients

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

cherry-studio. AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

easy-dataset. A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

OpenManus. No fortress, purely open ground. OpenManus is Coming.

owl. 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

rag-from-scratch. Jupyter Notebook

olmocr. Toolkit for linearizing PDFs for LLM datasets/training

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

llama.cpp. LLM inference in C/C++

DeepGEMM. DeepGEMM: clean and efficient BLAS kernel library on GPU

DeepEP. DeepEP: an efficient expert-parallel communication library

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

ktransformers. A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

awesome-deepseek-integration. Integrate the DeepSeek API into popular software

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

MoneyPrinterV2. Automate the process of making money online.

ModernBERT. Bringing BERT into modernity via both architecture changes and scaling

HuatuoGPT-o1. Medical o1, Towards medical complex reasoning with LLMs

O1-Journey. O1 Replication Journey

MindSearch. 🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

awesome-cursorrules. 📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

NextChat. ✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

awesome-rag. Awesome-RAG: Collect typical RAG papers and systems.

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

omniparse. Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

TableStructureRec. 整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

article2card. 一个把长文转款成摘要卡片/图片的前端应用，使用 Kimi 对文章进行结构化总结。

tablegpt-agent. A pre-built agent for TableGPT2.

awesome-qwen-prompt-insight. 🧠 世界上覆盖最全的优秀Qwen提示语大全，欢迎贡献你的提示词。🧠 The most comprehensive collection of excellent Qwen prompts in the world. Feel free to contribute your own prompts!

awesome-LLM-resources. 🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

MinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

zhihu-download. 将知乎专栏文章转换为 Markdown 文件保存到本地

lingua. Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

awesome-rag. A curated list of retrieval-augmented generation (RAG) in large language models

LangGPT. LangGPT: Empowering everyone to become a prompt expert! 🚀 📌 结构化提示词（Structured Prompt）提出者 📌 元提示词（Meta-Prompt）发起者 📌 最流行的提示词落地范式 | Language of GPT The pioneering framework for structured & meta-prompt design 10,000+ ⭐ | Battle-tested by thousands of users worldwide Created by 云中江树

LLMsBook. 大型语言模型实战指南：应用实践与场景落地

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

flux. Official inference repo for FLUX.1 models

Easy-RAG. 一个适合学习、使用、自主扩展的RAG【检索增强生成】系统！可联网做AI搜索

GraphRAG-Local-UI. GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

gpt-prompt-engineer. Jupyter Notebook

Awesome-Text2SQL. Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

Qwen2-Audio. The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Awesome-Role-Play-Papers. Awesome papers for role-playing with language models

Awesome-LLMs-Datasets. Summarize existing representative LLMs text datasets.

llm-datasets. Curated list of datasets and tools for post-training.

Awesome-LLM-Inference. 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

Awesome-Chinese-Stable-Diffusion. 中文文生图stable diffsion模型集合

DeepSeek-V2. DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

fsdp_qlora. Training LLMs with QLoRA + FSDP

awesome-llm-role-playing-with-persona. Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

Chinese-LLaMA-Alpaca-3. 中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

360zhinao. 360zhinao

Chinese-Tiny-LLM. Python

Langchain-Chatchat. Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

chat-langchain. TypeScript

mixinglaws. Jupyter Notebook

MediaCrawler. 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

OpenHands. 🙌 OpenHands: AI-Driven Development

XuanYuan. 轩辕：度小满中文金融对话大模型

CLongEval. CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models

GaLore. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

generative-models. Generative Models by Stability AI

seq-monkey-data.

Tianji. 制作懂人情世故的大语言模型 | 涵盖提示词工程、RAG、Agent、LLM微调教程

Entropy-ABF. Official implementation for 'Extending LLMs’ Context Window with 100 Samples'

Chinese-Mixtral-8x7B. 中文Mixtral-8x7B（Chinese-Mixtral-8x7B）

promptflow. Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

ms-agent. MS-Agent: a lightweight framework to empower agentic execution of complex tasks

LongLoRA. Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

lmdeploy. LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

LLaMA-Pro. [ACL 2024] Progressive LLaMA with Block Expansion.

Large-Language-Model-Notebooks-Course. Practical course about Large Language Models.

LongLM. [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

selfextend. an implementation of Self-Extend, to expand the context window via grouped attention

LLMSurvey. The official GitHub page for the survey paper "A Survey of Large Language Models".

MathPile. [NeurlPS D&B 2024] Generative AI for Math: MathPile

Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

Aurora. The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"

S-LoRA. S-LoRA: Serving Thousands of Concurrent LoRA Adapters

MOELoRA-peft. [SIGIR'24] The official implementation code of MOELoRA.

AutoGPTQ. An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

AutoAWQ. AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Awesome-AI4Med. A curated list of medical LLMs, multimodal systems, datasets, benchmarks, and more. 🏥

awesome-LLMs-In-China. 中国大模型

MoDS. Python

DeepSeek-Coder. DeepSeek Coder: Let the Code Write Itself

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

zagi. Release the power of GPT

mLoRA. An Efficient "Factory" to Build Multiple LoRA Adapters

dify. Production-ready platform for agentic workflow development.

UniIE. Python