AI Sharing Circle

Day arching a pawn and sharing for the king!
RLAMA:命令行操作的本地文档智能问答 RAG 系统

RLAMA: A RAG System for Intelligent Quizzing of Local Documents Operated from the Command Line

Comprehensive Introduction RLAMA is a document intelligent Q&A RAG (Retrieval Augmentation Generation) system developed open-source by DonTizi and hosted on GitHub, whose core feature lies in the realization of functionality through command line operations. Users can use simple terminal commands to connect to local ...
7mos ago
024K
Google 搜索“AI 模式”上线:剑指 Perplexity 与 ChatGPT

Google Search "AI Mode" Goes Live: Taking Aim at Perplexity and ChatGPT

Recently, Google Search launched an experimental feature in its generative experience (SGE) called "AI Mode" (AI Mode), which is powered by the Gemini 2.0 Big Model, capable of handling complex queries and with powerful reasoning capabilities, directly...
7mos ago
018.7K
Tavus 发布情感智能 CVI 平台:三大核心模型驱动数字人实时视频交互

Tavus Releases Emotionally Intelligent CVI Platform: Three Core Models Drive Real-Time Video Interaction with Digital People

Introduction The field of human-computer interaction is undergoing a profound transformation, and Tavus, a company specializing in the development of advanced AI interaction technologies, has been driving this change. Last year, Tavus launched what was then called the world's fastest conversational video interface (Convers...
7mos ago
015K
Tavus:生成高真实度数字分身视频的开发者平台

Tavus: a developer platform for generating high fidelity digital split videos

General Introduction Tavus is a developer platform focused on human-AI interactions, providing easy-to-use APIs that allow developers to build AI agents with visual, speech, and emotional intelligence. Its core product, Conversational Video In...
7mos ago
022.3K
Unsloth 解决 QwQ-32B 量化版本重复推理问题

Unsloth solves duplicate inference problem in quantized version of QwQ-32B

Recently, the Qwen team released QwQ-32B, an inference model that has shown excellent performance on many benchmarks comparable to DeepSeek-R1. However, many users have encountered problems with infinite generation, too much duplicate content, tok...
7mos ago
016.2K
ScribeAI:验证商业创意和数据洞察的AI分析工具

ScribeAI: AI Analytics Tool for Validating Business Ideas and Data Insights

General Introduction ScribeAI is an online tool that utilizes AI technology to help users validate business ideas. It provides clear data support for entrepreneurs to avoid blindly developing failed products by analyzing market trends, competitors' strategies and potential needs. Users simply describe their business...
7mos ago
021K
Newsful:基于AI的金融新闻摘要网站

Newsful: an AI-based financial news summary site

General Introduction Newsful is an online platform that utilizes artificial intelligence technology to provide financial news services, focusing on real-time aggregation of corporate news and market developments from around the world. The site uses natural language processing (NLP) and machine learning technologies to extract information from multiple media sources for the use...
7mos ago
023K
Fast-Agent:声明式语法和MCP集成快速构建多智能体工作流

Fast-Agent: Declarative Grammar and MCP Integration for Rapidly Building Multi-Intelligent Body Workflows

General Introduction Fast-Agent is an open source tool maintained by the evalstate team on GitHub, designed to help developers quickly define, test and build multi-intelligence workflows. It is based on a simple declarative syntax, and supports the use of MCP (Mode...
7mos ago
023.4K
观看多个大模型进行”狼人杀“推理游戏竞技,测验谁的推理能力更强!

Watch multiple large models compete in a game of Werewolf Reasoning to test who has the best reasoning skills!

General Introduction LLM Mafia Game Competition is an innovative online platform developed by the OpenNumbers team, focusing on engaging Artificial Intelligence Language Models (AI LLMs) in "Werewolf" style reasoning matches. Users can...
7mos ago
019.6K
HeyGem:硅基智能开源的 Heygen 数字人平替产品

HeyGem: Silicon Intelligence's Open Source Heygen Digital Human Pantographs

General Introduction HeyGem is a fully offline video compositing tool designed for Windows systems, developed by the GuijiAI (Silicon Intelligence) team and open-sourced on GitHub. It utilizes advanced AI algorithms to accurately clone the user's appearance and voice...
4mos ago
038.3K