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
subeshb1/agenite
Agenite is a TypeScript framework for building AI agents, made up of a set of npm packages under the @agenite scope. The core is @agenite/agent, which orchestrates the loop between a model and its tools, manages conversation state and context, executes tool calls and handles their results, supports nested execution for multi-agent workflows and streams output for interactive use. @agenite/tool defines tools with TypeScript types and JSON Schema validation of inputs plus structured error handling, so a tool returns a result flagged as data or error rather than throwing. @agenite/llm is the provider interface that keeps the same API across back ends, with concrete adapters in @agenite/openai, @agenite/anthropic, @agenite/bedrock and @agenite/ollama for models run locally. Execution is built on JavaScript generators, giving a bidirectional, step-based model where each step can be observed or intercepted; state is updated through reducers and behaviour is extended through middleware, of which @agenite/pretty-logger is an example that prints coloured execution traces for debugging. The Model Context Protocol enters through @agenite/mcp, a client implementation that connects an Agenite agent to MCP servers and makes their tools available alongside locally defined ones, which is how the framework reaches web content, filesystems, databases and other external sources without bespoke integration code for each. A short example in the README builds a calculator tool with an input schema, creates an agent backed by an AWS Bedrock provider with the pretty logger middleware attached, and runs it on an arithmetic question. The repository is a monorepo that also holds the documentation site. It targets TypeScript developers who want typed agent plumbing they assemble themselves, with MCP as the standard way to attach external tools.
https://github.com/subeshb1/agenite
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.