Starred repositories
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。
《Agentic Design Patterns》中文翻译版
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。
前端面试 前端知识点 面试题大全 js vue react node git element typescript ts next 支付 微信公众平台 每日持续更新 前端周刊 vue3 react18 vite redux 前端
Lets make video diffusion practical!
🤖 GPT（ Deepseek and more ） Code Review for Gitlab （针对于 Gitlab 的 LLM 辅助 Code Review 工具）项目详细文档 👇🏻
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
自动化上传视频到社交媒体：抖音、小红书、视频号、tiktok、youtube、bilibili
虎牙，斗鱼，抖音，BiliBili，TikTok，Twitch🔥热门🔥智能直播视频剪辑发布AI机器人，自动化🤖，全智能化⚙（智能生成切片，标题，封面，简介），可视化👓，平台热门监控🌡，丰富插件随意扩展🕹，快速部署⚡，视频账号打造自动发布🌟，支持DIY🎮
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.
Easily build AI systems with Evals, RAG, Agents, fine-tuning, synthetic data, and more.
Reverse Engineering: Decompiling Binary Code with Large Language Models
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.
dperf: High-Performance Network Load Testing Tool Based on DPDK
Magic to turn Cursor/Windsurf as 90% of Devin
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
For GenAI and LLM usage. This package converts codebase (folder structure with files) into a single text file or a Microsoft Word document (.docx), preserving folder structure and file contents. Th…
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Official comfyui repository of Hellomeme