我的开发经验+提示词库=vibecoding工作站；My development experience + prompt dictionary = Vibecoding workstation；ניסיון הפיתוח שלי + מילון פרומפטים = תחנת עבודה Vibecoding；私の開発経験 + プロンプト辞書 = Vibecoding ワークステーション；나…

本项目为 chatgpt-on-wechat下游分支, 额外对接了LLMOps平台 Dify，同时支持gewechat，相比itchat更加稳定。

Convert any PDF into a podcast episode!

Ongoing research training transformer language models at scale, including: BERT & GPT-2

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/Docker

Askbot is a Django/Python Q&A forum. **Contributors README**: https://github.com/ASKBOT/askbot-devel#how-to-contribute. Commercial hosting of Askbot and support are available at https://askbot.com

Personal AI search copilot, open-source Perplexity

Interactive User Feedback MCP

Interactive User Feedback MCP,本 MCP 工具 interactive_feedback ，把多轮对话在一次请求内完成，最大化利用 25 次子调用额度，实现把 Cursor 500次请求变2500次。

Code for the blog "Neural audio codecs: how to get audio into LLMs"

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

FastMLX is a high performance production ready API to host MLX models.

g1: Using GPT-4o to create o1-like reasoning chains

A Gradio Web UI for running local LLM on Intel GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) using IPEX-LLM.

Knowledge Base QA using RAG pipeline on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) with IPEX-LLM

谷歌notebookLM开源平替，支持中英双语。基于 ChatTTS ，支持流式输出、音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。

Fork of Baize to get 30B 8-bit model working on two RTX3090/4090 GPUs

Build your own AI friend

用于编排角色扮演、自主人工智能代理的框架。通过促进协作智能，CrewAI 使代理能够无缝协作，处理复杂的任务。

OpenAI-Compatible RESTful APIs for managed LLMs