4D-ARE

Build LLM agents that explain why, not just what. Attribution-driven agent requirements engineering framework. Based on the 4D-ARE Paper - https://arxiv.org/abs/2601.04556

daily_stock_analysis

LLM驱动的 A 股智能分析器，多数据源行情 + 实时新闻 + Gemini 决策仪表盘 + 微信推送，零成本，纯白嫖，定时运行

opensrc

Fetch source code for npm packages to give AI coding agents deeper context

smart-coding-mcp

An extensible Model Context Protocol (MCP-Local-MRL-RAG-AST) server that provides intelligent semantic code search for AI assistants. Built with local AI models, inspired by Cursor's semantic search research.

banana-slides

一个基于nano banana pro🍌的原生AI PPT生成应用，迈向真正的＂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 - An AI-native PPT generator based on nano banana pro🍌

full-stack-fastapi-nextjs-llm-template

Full-stack FastAPI + Next.js template generator with PydanticAI/LangChain agents, WebSocket streaming, 20+ enterprise integrations, and Logfire/LangSmith observability. Ship AI apps fast. CLI tool to generate production-ready FastAPI + Next.js projects with AI agents, auth, and observability.

kiro-openai-gateway

OpenAI-compatible API gateway for Kiro IDE (AWS CodeWhisperer). Use free Claude models with any OpenAI client.

RealVideo

A real-time streaming conversational video system that transforms text interactions into continuous, high-fidelity video responses using autoregressive diffusion.

privacy-firewall

A local AI-powered DLP solution

GLM-TTS

GLM-TTS是一个基于大型语言模型的高质量文本到语音（TTS）合成系统，支持零样本语音克隆和流式推理。本系统采用两个阶段架构：首先使用LLM生成语音令牌序列，然后使用流模型将令牌转换为高质量的音频格式。通过引入多奖励强化学习（Multi-Reward RL）框架，GLM-TTS能够生成更加丰富的情感表达力和流式推理，显着提升了传统TTS系统的表现力。

laravel-llm-suite

A unified, driver-based Laravel toolkit for working with multiple LLM providers for chat, image generation, and more.

GLM-ASR

GLM-ASR Readme in EnglishREADME.md 👋 加入我们的 微信 社区 模型介绍 **GLM-ASR-Nano-2512** 是一款鲁棒的开源语音识别模型，参数量为 **1.5B**。 该模型专为应对真实世界的复杂场景而设计，在多项基准测试中超越 OpenAI Whisper V3，同时保持紧凑的模型规模。 核心能力包括： * **卓越的方言支持** 除标准普通话和英语外，模型针对**粤语**及其他方言进行了深度优化，有效填补了方言语音识别领域的空白。 * **低音量语音鲁棒性** 专门针对**"低语/轻声"**场景进行训练，能