-
GMU
- Fairfax, VA
- zye1996.github.io
Stars
Build multi-agent systems that learn and improve with every interaction.
[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"
Turn paper/text/topic into editable research figures, technical route diagrams, and presentation slides.
AgentScope: Agent-Oriented Programming for Building LLM Applications
Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …
REFRAG-style RAG (compress → sense/select → expand) — Single-file reference implementation
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Memory for 24/7 proactive agents like openclaw (moltbot, clawdbot).
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)
Gemma open-weight LLM library, from Google DeepMind
[DEIMv2] Real Time Object Detection Meets DINOv3
[NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat
Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
MAESTRO is an AI-powered research application designed to streamline complex research tasks.
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Fastest LLM gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
A self hosted virtual browser that runs in docker and uses WebRTC.