AgentOran

cn-news-tts-bench. Target-level automatic benchmark for raw-input Chinese news TTS pronunciation accuracy

listenhub-cli. ListenHub CLI - command-line interface for ListenHub SDK

frontend-slides. Create beautiful slides on the web using a coding agent's frontend skills

ColaMD. The Agent Native Markdown Editor.

web-access. 给 Claude Code 装上完整联网能力的 skill：三层通道调度 + 浏览器 CDP + 并行分治

TypeNo. A free, open source, privacy-first voice input app for macOS.

coli. Core library for Cola. Provides essential capabilities commonly used by agents.

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

CodePilot. A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.

ai-claude-start. Multi-profile Claude Code launcher with secure credential management

guizang-s-prompt. 这里是歸藏的提示词储存库，存放着歸藏撰写的所有 AI 模型提示词（This is Guizang's prompt repository, containing all AI model prompts written by Guizang.）

listenhub-mcp-server. ListenHub's official MCP Server | The AI Voice for Every Creator

skills. Public repository for Agent Skills

claude-code-now. The World's Fastest Claude Code Launcher Make Claude Code launching simpler Click Dock to launch, or start from any folder instantly.

chatterbox. SoTA open-source TTS

ten-framework. Open-source framework for conversational voice AI agents

zenfeed. Make RSS 📰 great again with AI 🧠✨!!

metorial. Connect any AI model to 1200+ integrations (MCP, CLI, API)

BabelDOC. Yet Another Document Translator

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

md. ✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器：支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性

marreta. Uma ferramenta que quebra barreiras de acesso e elementos que atrapalham a leitura! / Marreta is a tool that removes access barriers and visual distractions!

Sonic. Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

AudioCap. Sample code for recording system audio on macOS 14.4+

YuE. YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

DeepSeek-Math. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

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

UI-TARS-desktop. The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

chatmcp. ChatMCP is an AI chat client implementing the Model Context Protocol (MCP).

Thinking-Claude. Let your Claude able to think

screenshot-to-code. Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Deep-Live-Cam. real time face swap and one-click video deepfake with only a single image

mem0. Universal memory layer for AI Agents

MacOS-Agent. MacOS Agent: A Simplified Assistant for Your Mac

Macify. Turn your Chrome's new tab page into macOS' gorgeous screensaver aerial videos.

QuickRecorder. A lightweight screen recorder based on ScreenCapture Kit for macOS / 基于 ScreenCapture Kit 的轻量化多功能 macOS 录屏工具

reor. Private & local AI personal knowledge management app for high entropy people.

awesome-cloudflare. ⛅️ 精选的 Cloudflare 工具、开源项目、指南、博客和其他资源列表。/ ⛅️ A curated list of Cloudflare tools, open source projects, guides, blogs and other resources.

llama3-Chinese-chat. Llama3-中文后训练版

SillyTavern. LLM Frontend for Power Users.

dify2openai. Turn Dify into OpenAI

morphic. An AI-powered search engine with a generative UI

camel. 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

llm-answer-engine. Perplexity Inspired Answer Engine

every-chatgpt-gui. Every front-end GUI client for ChatGPT, Claude, and other LLMs

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

OhEarningsCal. Subscribe to US stock earnings dates from your calendar app

translation-starter. TypeScript

marker. Convert PDF to markdown + JSON quickly with high accuracy

gpt-researcher. An autonomous agent that conducts deep research on any data using any LLM providers

opengpts. Rich Text Format

ComfyUI-AnimateDiff-Evolved. Improved AnimateDiff for ComfyUI and Advanced Sampling Support

factool. FacTool: Factuality Detection in Generative AI

openinterpreter. A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

paycheck-extension. poorly guess how much money a tweet is worth

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

companion-app. AI companions with memory: a lightweight stack to create and host your own AI companions

AutoChain. AutoChain: Build lightweight, extensible, and testable LLM Agents

chroma. Search infrastructure for AI

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

ShortGPT. 🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation

RealChar. 🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime (All in One Codebase!). Have a natural seamless conversation with AI everywhere (mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text2Speech🎙️🤖

DeepSpeech. DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

WizardLM. LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

youtube-to-chatbot. Train a chatbot on an entire YouTube channel using OpenAI & Pinecone.

GirlfriendGPT. OSS AI Companion Chatbot - Build your own AI companion in Python using ChatGPT.

ChatLongDoc. Python

Webpilot. Vue

dify. Production-ready platform for agentic workflow development.

claude-to-chatgpt. This project converts the API of Anthropic's Claude model to the OpenAI Chat API format.

gpt4free. The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

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

chatbox. Powerful AI Client

nativefier. Make any web page a desktop application

llm-wiki-agent. A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

bark. 🔊 Text-Prompted Generative Audio Model

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

AGIEval. Python

ai-brainstore. An experiment concept for an AI brain.

BIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

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.

chatGPTBox. Integrating ChatGPT into your browser deeply, everything you need is here

the-craft-of-selfteaching. One has no future if one couldn't teach themself.

BingGPT. Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux)

speechgpt. 💬 SpeechGPT is a web application that enables you to converse with ChatGPT.

agent. My profile & the agent skills I created

chatgpt-md. A (nearly) seamless integration of ChatGPT into Obsidian.

donut. Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

ai-vocabulary-builder. An AI-powered smart vocabulary tool with features like One-click vocabulary building and story-based memorization.

text2vec. text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

openai-scf-proxy. 使用腾讯云函数一分钟搭建 OpenAI 免翻墙代理

openai-cookbook. Examples and guides for using the OpenAI API

bob-plugin-openai-translator. 基于 LLM 的文本翻译、文本润色、语法纠错 Bob 插件，让我们一起迎接不需要巴别塔的新时代！Licensed under CC BY-NC-SA 4.0

ControlNet. Let us control diffusion models!

stable-diffusion-webui. Stable Diffusion web UI

chat-langchainjs. TypeScript

rime-ice. Rime 配置：雾凇拼音 | 长期维护的简体词库

bob-plugin-akl-deepl-free-translate. **DeepL免秘钥,免启服务**,双击使用,免费无限次使用,(**新增DeepL单词查询功能**)根据网页版JavaScript加密算法逆向开发的bobplugin;所以只要官网的算法不改,理论上就可以无限使用;(重大更新!!!回馈老用户,现已优化,频繁访问后仍然可以继续免费翻译!!) **apiKey is not required,No account password required**

chatgpt-for-chatbot-feishu. 快速将 ChatGPT 接入飞书，基于 OpenAI 官方接口，作为私人工作助理或者企业员工助理

WAAS. Whisper as a Service (GUI and API with queuing for OpenAI Whisper)

awesome-chatgpt-prompts-zh. ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

ChatGPT. 🔮 ChatGPT Desktop Application (Mac, Windows and Linux)

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.

numbr. Notepad + calculator

storyteller. Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech

heti. 赫蹏（hètí）是专为中文内容展示设计的排版样式增强。它基于通行的中文排版规范而来，可以为网站的读者带来更好的文章阅读体验。

MiaoYan. ⛷ Lightweight Markdown app to help you write great sentences.

Pake. 🤱🏻 Turn any webpage into a desktop app with one command.