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
puppyone-ai/DeepWideResearch
Open Deep Wide Research is an open-source agentic Retrieval-Augmented Generation (RAG) system designed to be highly customizable and compatible with the Model Context Protocol (MCP). It addresses the evolving needs of RAG technology by offering granular control over the depth and breadth of information retrieval and reasoning, enabling users to balance response quality, speed, and cost effectively. The system allows users to customize data sources, ranging from internal knowledge bases to specialized APIs, and adjust the "Deep" parameter to control reasoning depth and response time, as well as the "Wide" parameter to control the breadth of information across selected sources. This dual control system, referred to as the "Deep × Wide" coordinate system, also provides transparent cost predictions for each response, helping users manage budgets efficiently. The project supports self-hosting for maximum privacy and security, allowing deployment on private infrastructure. It features hot-swappable models, enabling users to plug in various language models such as OpenAI, Claude, or private LLMs instantly. Additionally, it supports customizable search engines with out-of-the-box integration for providers like Tavily and Exa, as long as they comply with MCP. The system is designed to be extensible and future-proof, leveraging MCP for seamless integration with compliant data sources and tools. Open Deep Wide Research is suitable for diverse scenarios including customer service bots, market research, and enterprise analytics, each benefiting from tailored settings for depth and width to optimize performance and cost. The project provides both backend API and full-stack deployment options with a web UI for ease of use. It requires Python 3.9+, Node.js 18+, and API keys for Open Router and at least one supported search provider. The project emphasizes transparency, flexibility, and control in RAG applications, making it a valuable tool for developers and enterprises aiming to implement advanced, customizable RAG agents.
https://github.com/puppyone-ai/DeepWideResearch
Also in Agent Orchestration Platforms
tinyhumansai/openhuman
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.
assafelovic/gpt-researcher
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.
deepset-ai/haystack
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/activepieces
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.
openai/swarm
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-sh/superset
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/voltagent
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.