lobehub/lobehub
LobeHub is a platform that enables multi-agent collaboration and human-agent co-evolution by treating AI agents as units of work, providing tools to build, manage, and collaborate with AI agent teams seamlessly.
Awesome MCP › Agent Orchestration Platforms
NeuroLink is a TypeScript library from Juspay that abstracts more than twenty large-language-model providers behind a single streaming interface, so switching provider does not require rewriting calling code. Everything is modelled as a stream: tokens, tool calls, memory operations, voice and documents pass through the same pipeline. Its MCP support makes it a client — a NeuroLink application can connect to any MCP server and the tools that server publishes become available to whichever model the application is currently using, which is the practical benefit of the provider abstraction combined with MCP: one tool catalogue usable across OpenAI, Anthropic and the other supported backends. Additional built-in layers cover retrieval-augmented generation, conversation memory, file and document processors, and voice through text-to-speech, speech-to-text and realtime modes. It is published on npm as @juspay/neurolink, MIT licensed, with continuous integration and a documented local-first mode. The README states it originated in production use at Juspay, where it backs internal systems named Tara, Yama and Clairvoyance, rather than being written as a demonstration library. The audience is TypeScript teams building AI features who want provider independence and do not want to assemble MCP client plumbing, RAG and voice from separate packages.
https://github.com/juspay/neurolink
LobeHub is a platform that enables multi-agent collaboration and human-agent co-evolution by treating AI agents as units of work, providing tools to build, manage, and collaborate with AI agent teams seamlessly.
OpenHuman is a local-first personal AI assistant with persistent Markdown memory, multi-agent workflow orchestration, and research tools, connecting to 100+ OAuth integrations and thousands of MCP servers.
GPT Researcher is an autonomous AI agent that conducts deep local and web research on any topic, generating detailed, unbiased reports with citations and supporting integration with the Model Context Protocol (MCP) for enhanced data sourcing.
Haystack is an open-source AI orchestration framework for building production-ready LLM applications in Python, enabling modular pipelines and agent workflows with explicit control over retrieval, ...
Activepieces is an open-source AI automation platform providing an extensible MCP toolkit and over 280 MCP servers for AI agents, designed for both technical and non-technical users.
Swarm is an educational framework by OpenAI for lightweight, scalable multi-agent orchestration using agents and handoffs, designed to explore and teach multi-agent coordination techniques.
Superset is a desktop application designed to orchestrate and manage multiple CLI-based AI coding agents in parallel, using isolated Git worktrees for efficient, context-separated development.
VoltAgent is an open-source TypeScript framework for building and orchestrating autonomous AI agents with support for the Model Context Protocol (MCP) to enable standardized tool interactions and scalable multi-agent systems.