✨Data Intelligence Lab@HKU✨ ORG

Lightweight, open-source AI agent for your tools, chats, and workflows.

A lightweight AI agent you install on your own machine that can browse the web, run shell commands, manage files, and respond via Discord, Slack, or Telegram, supporting Anthropic, OpenAI, and local models.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

A framework that wraps existing software applications with command-line interfaces so AI agents can control them automatically instead of through graphical menus.

[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

Python library for building question-answering systems over large document collections using knowledge graphs instead of flat text search.

DeepTutor: Agent-native Personalized Tutoring. https://deeptutor.info/.

AI tutoring assistant that lets you have conversations with documents, ask questions, get explanations, and learn interactively instead of just reading passively.

"RAG-Anything: All-in-One RAG Framework"

Python framework for building question-answering systems that handle complex documents with text, images, tables, charts, and equations all together.

"AI-Trader: 100% Fully-Automated Agent-Native Trading"

Open-source trading platform where AI agents can register, publish signals, copy trades, and sync orders with brokers like Binance and Interactive Brokers across stocks, crypto, and forex.

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

DeepCode is an AI-powered multi-agent system that converts research papers, text descriptions, or ideas into working code, frontends, backends, or research implementations, without writing code yourself.

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

OpenHarness is an open-source Python framework for building AI agents that can use tools, remember things across sessions, follow permission rules, and coordinate with other agents.

"Vibe-Trading: Your Personal Trading Agent"

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

Multi-agent video generation system that turns an idea, novel, screenplay, or photo into a full video by coordinating Director, Screenwriter, Producer, and Video Generator roles.

"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"

Build and run AI agents without writing any code, describe what you want in plain language and AutoAgent constructs single agents or multi-agent pipelines automatically.

"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"

"OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/

[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

"Paper2Slides: From Paper to Presentation in One Click"

[KDD'2026] "VideoRAG: Chat with Your Videos"

"FastCode: Accelerating and Streamlining Your Code Understanding"

[ACL2026] "MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"

"Your Fully-Automated Personal AI Assistant"

[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"

[ACL 2026] "OpenPhone: Mobile Agentic Foundation Models for AI Phone"

"VideoAgent: All-in-One Agentic Framework for Video Understanding, Editing, and Remaking"

"AnyTool: Universal Tool-Use Layer for AI Agents"

[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

[ICML 2025] "SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator"

[WSDM'2024 Oral] "SSLRec: A Self-Supervised Learning Framework for Recommendation"

[WSDM'2024 Oral] "LLMRec: Large Language Models with Graph Augmentation for Recommendation"

[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"

[KDD'2024] "UrbanGPT: Spatio-Temporal Large Language Models"

"CatchMe: Make Your AI Agents Truly Personal"

[KDD'2024] "LLM4Graph: A Survey of Large Language Models for Graphs"

[EMNLP2025] "GraphAgent: Agentic Graph Language Assistant"

[EMNLP'2024] "OpenGraph: Towards Open Graph Foundation Models"

"DeepInnovator: AI Research Assistant - Idea Spark & Scientific Discovery"

"AnyGraph: Graph Foundation Model in the Wild"

[WWW'2023] "MMSSL: Multi-Modal Self-Supervised Learning for Recommendation"

"MoChat: OpenClaw as Your Social Agent https://mochat.io"

[ICLR'2023] "LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation"

[EMNLP'2024] "XRec: Large Language Models for Explainable Recommendation"

"OpenCity: Open Spatio-Temporal Foundation Models for Traffic Prediction"

"FutureShow: Can AI Predict the Future? Live Real-World Forecasting"

"Litewrite: Vibe Writing is Coming - Write Faster and Better! https://litewrite.ai"

[EMNLP'2025] "EasyRec: Simple yet Effective Language Model for Recommendation"

[KDD'2024] "HiGPT: Heterogenous Graph Language Models"

"GraphEdit: Large Language Models for Graph Structure Learning"

[WSDM'2024 Oral] "DiffKG: Knowledge Graph Diffusion Model for Recommendation"

[WSDM'2023] "HGCL: Heterogeneous Graph Contrastive Learning for Recommendation"

[ACM CSUR] "A Comprehensive Survey of Self-Supervised Learning for Recommendation"

[ACL2025] "RecLM: Recommendation Instruction Tuning"

[ACM MM'2024]"DiffMM: Multi-Modal Diffusion Model for Recommendation"

[ICML'2024] "FlashST: A Simple and Universal Prompt-Tuning Framework for Traffic Prediction"

[NeurIPS'2023] "GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks"

[CIKM'2024] "RecDiff: Diffusion Model for Social Recommendation"

[KDD'2023] "KGRec: Knowledge Graph Self-Supervised Rationalization for Recommendation"

[WWW'2024] "GraphPro: Graph Pre-training and Prompt Learning for Recommendation"

[WSDM'2025] "DiffGraph: Heterogeneous Graph Diffusion Model"

[SIGIR'2024] "SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation"

[SIGIR'2023] "GFormer: Graph Transformer for Recommendation"

[KDD'2023] "AdaGCL: Adaptive Graph Contrastive Learning for Recommendation"

[WWW'2023] "AutoST: Automated Spatio-Temporal Graph Contrastive Learning"

[SIGIR'2023] "MAERec: Graph Masked Autoencoder for Sequential Recommendation"

[WWW'2023] "DCRec: Debiased Contrastive Learning for Sequential Recommendation"

[SIGIR'2023] "DCCF: Disentangled Contrastive Collaborative Filtering"

[CIKM'2023] "STExplainer: Explainable Spatio-Temporal Graph Neural Networks"

[WSDM'25] "LightGNN: Simple Graph Neural Network for Recommendation"

[ICML'2023] "GraphST: Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation"

[ACM TIST] "LLM4Urban: Urban Computing in the Era of Large Language Models"

[EMNLP2025] "RecGPT: A Foundation Model for Sequential Recommendation"

"FastAgent: Simple, Fast, and Strong LLM Agents"

[WWW'2024] "PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning"

[WWW'23] "AutoCF: Automated Self-Supervised Learning for Recommendation"

"DeepResearch-Eval: An End-to-End Evaluation Framework for DeepResearch Systems"

Memory Governance Protocol

No description.

Upskill your model: Flash price. Pro performance.

[IJCAI'2023] "DSL: Denoised Self-Augmented Learning for Social Recommendation"

[WWW'23] "SimRec: Graph-less Collaborative Filtering"

[CIKM'2023] "CL4ST: Spatio-Temporal Meta Contrastive Learning"

[ICDE'23] "DGNN: Disentangled Graph Social Recommendation"

[ICDE'2024] "GraphAug: Graph Augmentation for Recommendation"

[WSDM'2025] "MixRec: Heterogeneous Graph Collaborative Filtering"

[CIKM'2024] "EasyST: A Simple Framework for Spatio-Temporal Prediction"

[CIKM'2023] "GTE: How Expressive are Graph Neural Networks for Recommendation?"

[Recsys'2023] "RCL: Multi-Relational Contrastive Learning for Recommendation"

No description.

No description.

No description.