LlamaIndex is a data framework for your LLM applications

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

Deploy your agentic worfklows to production

Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Incorporating Agile methodology into agents to create complex real-world softwares

Open-source framework to make AI agents' team collaboration as effective as human collaboration.

ChocoBuilder (Chocolate Factory) is a cutting-edge LLM toolkit designed to empower you in creating your very own AI assistant.Chocolate Factory 是一款开源的 LLM 应用开发框架，旨在帮助您轻松打造强大的软件开发 SDLC + LLM 生成助手。无论您是需要生成前端页面、后端 API、SQL 图表，还是测试用例数据，Chocolate Factory 都能满足您的需求。

🔧 Repair JSON！Solution for JSON Anomalies from LLMs.

MAGNet: Multi-agents control using Graph Neural Networks

Multi-Agents & Plugins repo for DB-GPT, Can complete various tasks around databases.

🌟 Revolutionize Your Operations with One Sentence Automation: Utilizing large language models and Multi-Agents to generate operational copy, images, and videos with one-line requirements.

A framework that uses multi-agents to enable users to perform a systematic data science pipeline with just two inputs.

MultiAgent Chat UI

PyTorch agents and tools for (Deep) Reinforcement Learning

Swarm for Ollama. OpenAI Framework to build/orchestrate/deploy multi-agent systems. Working offline with Ollama

An Agent-Based Financial Platform. See how evolve agents in a realistic double auction order book

A powerful AI-powered newsletter aggregator built with KaibanJS and React.

The AdLeap-MAS project proposes a new framework for implementing and simulating Ad-hoc reasoning environments. Built 100% in Python using the Open-AI Gym as its basis, we propose a component-based architecture to enable quick implementations to perform multi-agents systems experiments.

This repository provides a flexible and customizable implementation of an advanced conversational AI agent, allowing you to leverage the capabilities of your preferred LLM provider without the need for additional libraries.

NeurIPS workshop : We examine the risk of powerful malignant intelligent actors spreading their influence over networks of agents with varying intelligence and motivations.