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
evilsocket/nerve
Nerve is a comprehensive Agent Development Kit (ADK) designed to build, run, evaluate, and orchestrate large language model (LLM)-based agents using a declarative YAML format and command-line interface (CLI) tools. It targets technical users who require programmable, auditable, and reproducible automation leveraging LLMs. The project emphasizes simplicity and power, allowing users to define agents declaratively with system prompts, tasks, tools, and variables all specified in a single YAML file. Nerve supports a variety of tools including shell commands, Python functions, and remote tools, all fully typed and annotated for ease of use and extensibility. A standout feature of Nerve is its native support for the Model Context Protocol (MCP), enabling it to function as both an MCP client and server. This capability allows users to define MCP servers declaratively in YAML, facilitating agent teams and deep orchestration scenarios. The framework also includes an evaluation mode that supports benchmarking agents with YAML, Parquet, or folder-based test cases, enabling reproducible testing, structured output logging, and tracking of regression or progress. Nerve supports workflows by composing agents into simple linear pipelines for multi-step automations with shared context. It is LLM-agnostic, built on LiteLLM, and supports a wide range of models including OpenAI, Anthropic, Ollama, and many others, allowing users to switch models easily. Installation and usage are straightforward, with commands to install the package, download or create agents, and run them. The project is open source under the GPL 3 license and encourages community contributions through GitHub and Discord. Extensive documentation and examples are provided to help users get started and make the most of the ADK. Keywords: Agent Development Kit, LLM-based agents, declarative YAML, CLI tools, Model Context Protocol, MCP client, MCP server, agent orchestration, evaluation mode, benchmarking, workflows, LiteLLM, OpenAI, Anthropic, Ollama, automation, reproducible testing, programmable agents, extensibility, open source, GPL 3 license.
https://github.com/evilsocket/nerve
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.