🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Making large AI models cheaper, faster and more accessible

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

A modular graph-based Retrieval-Augmented Generation (RAG) system

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Fast and memory-efficient exact attention

Mamba SSM architecture

Janus-Series: Unified Multimodal Understanding and Generation Models

"LightRAG: Simple and Fast Retrieval-Augmented Generation"

a state-of-the-art-level open visual language model | 多模态预训练模型

🐫 CAMEL: Finding the Scaling Law of Agents. The first and the best multi-agent framework. https://www.camel-ai.org

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

A simple, easy-to-hack GraphRAG implementation

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

GPTeam: An open-source multi-agent simulation

Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).

Agent S: an open agentic framework that uses computers like a human

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

OO for LLMs

"MiniRAG: Making RAG Simpler with Small and Free Language Models"

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

[ACL 2024] Progressive LLaMA with Block Expansion.

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

This is the official github repo of Think-on-Graph (ICLR 2024). If you are interested in our work or willing to join our research team in Shenzhen, please feel free to contact us by email (xuchengj…

ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate

Official Implementation of NeurIPS 2024 paper "G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering""