Awesome AI Agents › Collaborative Swarm Systems
PartyKit for Workers, also known as PartyServer, is a comprehensive set of libraries, examples, and documentation designed to facilitate the development of real-time applications using Cloudflare Workers. The project leverages Durable Objects, a Cloudflare Workers feature, to provide enhanced capabilities for building scalable and resilient real-time apps. PartyServer is inspired by the original PartyKit and aims to simplify working with WebSockets and real-time communication. The repository includes several key packages: PartyServer, the core library that extends Durable Objects to support WebSocket management, lifecycle hooks, and broadcasting features; PartySocket, a WebSocket library that offers reconnection, buffering, and resilience; Y-PartyServer, which integrates Yjs, a CRDT library for real-time collaborative editing, allowing developers to build collaborative applications with ease; partysub, a pub/sub library designed for scaling PartyServer by distributing load across multiple Durable Object instances globally; partysync, an experimental library for synchronizing state between Durable Objects and clients; partywhen, a task scheduling library for large-scale applications; and hono-party, middleware for the Hono framework to handle PartyServer requests. The project also provides a collection of small, self-contained example applications in the fixtures directory to demonstrate various use cases and help developers get started quickly. PartyKit for Workers is actively maintained and encourages community engagement through social media and the Cloudflare Workers Discord channel. Overall, PartyKit for Workers is a powerful toolkit for developers looking to build real-time, collaborative, and scalable applications on the Cloudflare Workers platform, leveraging the unique capabilities of Durable Objects and WebSockets.
https://github.com/cloudflare/partykit
AgentVerse is a versatile open-source framework that enables the deployment and collaboration of multiple LLM-based agents for task-solving and simulation applications, supporting research and development in multi-agent AI systems.
Solace Agent Mesh is an open-source event-driven framework for building and orchestrating scalable multi-agent AI systems that integrate with real-world data and systems.
Langroid is a Python framework that enables building LLM-powered applications using a multi-agent programming approach for collaborative problem solving and enhanced developer experience.
EvoAgentX is an automated framework for building a self-evolving ecosystem of AI agents that generate, evaluate, and execute multi-agent workflows based on natural language goals.
agentUniverse is a multi-agent framework based on large language models that enables developers to build collaborative intelligent agents integrating domain expertise for solving complex problems.
Public research log of Hyperspace, a libp2p peer-to-peer network where autonomous agents run experiments across five domains, gossip findings, pool machines into private pods and train models collaboratively.
GPTeam is an open-source multi-agent simulation platform that uses GPT-4 to enable AI agents to collaborate and communicate effectively to achieve predefined goals.
uAgents is a lightweight Python framework by Fetch.ai for creating secure, decentralized autonomous AI agents that operate within a blockchain-enabled network.