100% of the code was written by AI. Fulling is your Next.js full-stack engineer, integrating Claude, Next.js, shadcn/ui, and a PostgreSQL database.

AipexBase is an AI-native BaaS platform. You only need to develop the frontend with vibe coding tools, and leave the backend to AipexBase! It is the AI-era's Supabase and Firebase.

An AI-powered multi-agent platform for automated investment research — combining LLM reasoning, RAG retrieval, and real-time market data to generate smart financial insights and dynamic reports.

Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.

A relation-free graph constrcution method for efficient GraphRAG.

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…

INFTY Engine: An Optimization Toolkit to Support Continual AI

A blueprint for building production-ready RAG systems that minimize hallucination, featuring switchable 3-step (Speed) and 4-step (Precision) pipelines.

A cross-platform instant messaging client application built with Tauri and Vue 3, featuring one-to-one chat, group chat, file transfer, audio/video calling, screen recording, screenshot capture, an…

this file contains anomaly detection related script/model/automation, and explanation.

PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

Packing irregular objects with deep reinforcement learning.

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。

Open-source models for financial risk detection and fraud analytics

From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano

[COLM 2025] Assessing Judging Bias in Large Reasoning Models: An Empirical Study https://openreview.net/pdf?id=SlRtFwBdzP

[TKDE2025] Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on large language model-based …

Valuation of tokens corresponding to influential individuals on social platforms through AI algorithms

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

A lightweight and modular image processing pipeline written in Go. Includes utilities for cropping, resizing, watermarking, format conversion, and more.

A real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate with any open source Avatar components (real-time model, visual, voice, memory, search, etc.).

小而美的Vue3异步处理解决方案，让复杂的异步逻辑变得简单优雅，让重复的样板代码成为历史

🤖 A comprehensive task management system specifically designed for AI assistants. Supports project management, task tracking, team collaboration, and seamless AI integration through MCP (Model Cont…

[IEEE JBHI 2024] Towards Connectivity-Aware Pulmonary Airway Segmentation