hkuds

A framework that automatically generates command-line interfaces for any software application, making them accessible to AI agents. Transforms GUI-based tools into agent-controllable CLIs with a unified interface across thousands of applications.

Agent-native personalized learning assistant that combines unified chat workspace, autonomous TutorBots, AI co-writing, and guided learning paths. Features persistent memory and knowledge bases to create adaptive, context-aware tutoring experiences.

An all-in-one, multimodal retrieval-augmented-generation framework that ingests text, images, tables, and equations from documents into a single pipeline, letting agents query across mixed-media knowledge bases.

Lightweight open-source AI agent that works across your tools, chats, and workflows — integrates with Claude, OpenAI Codex, and OpenClaw.

Simple, fast retrieval-augmented generation system from HKUDS that combines vector search and graph-based knowledge representation. EMNLP 2025.

Open agentic coding system from HKUDS — turns research papers, text descriptions, and design intent into working web frontends and backend services.

A self-evolving engine that makes AI agents smarter, more cost-efficient, and able to share knowledge with each other. Skills automatically improve from real-world usage, reducing token costs by 46% while enabling collective intelligence across agents.

Fully-automated, zero-code LLM agent framework from HKUDS — define agents in natural language with no Python required.

HKUDS's tool that turns a research paper into a presentation deck in one click — automatic slide generation with figures, key takeaways, and structure.

HKUDS's system for accelerating and streamlining code understanding — LLM-powered repo navigation, symbol mapping, and concept extraction at speed.

All-in-one agentic framework for video understanding, editing, and remaking. Open-source counterpart to NotebookLM-style video tools.

HKUDS's RAG system for video — chat with hours of footage, ask questions, and get cited timestamps and clips back.

HKUDS's autonomous scientific innovation agent — proposes research questions, runs experiments, and writes up findings end-to-end.

ACL 2026 paper exploring whether small language models can teach large language models to reason, with code and training recipes.

Universal tool-use layer for AI agents, providing orchestration over arbitrary tools and MCP servers for computer-use agents.

A personal, agent-driven trading assistant.

AI research assistant that sparks novel ideas and accelerates scientific discovery — point it at a domain and get hypothesis suggestions.

ICML 2025 paper accelerating large language models by compressing each segment into a single separator token to speed up inference.

Social AI agent that uses OpenClaw to handle your DMs, posts, and online interactions on your behalf.

A fully automated, agent-native trading system powered by LLMs.

Self-supervised learning framework for recommender systems. Covers contrastive, generative, and graph SSL methods in one toolkit.

An agentic video-generation system with director, screenwriter, and producer agents.

WSDM 2024 paper using LLMs with graph augmentation for recommendation systems, including multi-modal and side-information signals.

Personal AI agent that learns from your screen and recall history to deliver context-aware responses.

Simple, fast, and strong LLM agent framework with tool use, computer use, and orchestration.