paperclipai/paperclip
Node.js server and React dashboard that runs teams of AI agents as a virtual company, connecting them to outside tools through governed remote MCP connectors.
Awesome MCP › Agent Orchestration Platforms
Heurist Agent Framework is a modular, multi-interface AI agent framework designed to support advanced reasoning, tool use, memory, blockchain interaction, and integration with the Model Context Protocol (MCP). It enables the creation of sophisticated AI agents and agents-as-a-service that can operate across multiple platforms such as Telegram, Discord, Twitter, Farcaster, REST API, and MCP clients. The framework is built on a component-based architecture that allows agents to process text and voice messages, generate images and videos, and interact consistently across platforms. It supports knowledge storage and retrieval using PostgreSQL and SQLite databases and can access external APIs and tools, including a wide range of community-contributed Mesh Agents. The Heurist Mesh is an open network of specialized AI agents contributed by the community, functioning similarly to decentralized finance smart contracts. These agents can process data, generate reports, and perform actions collectively to solve complex tasks. All Mesh Agents are accessible via a unified REST API and the MCP, allowing seamless integration with various MCP clients. The framework includes recommended Mesh Agents for blockchain token analysis, Twitter intelligence, web search, and wallet asset queries. The architecture consists of a BaseAgent abstract class defining common functionality and a CoreAgent implementation that orchestrates components and workflows. The framework supports multiple agent interfaces tailored for different platforms. Core components include PersonalityProvider, KnowledgeProvider, ConversationManager, ValidationManager, MediaHandler, LLMProvider, and MessageStore. It offers advanced workflows such as Augmented LLM Calls, Chain of Thought Reasoning, and Research Workflow for complex reasoning and information retrieval. Tool management is facilitated through a ToolBox framework with MCP integration for executing tools. External clients like SearchClient and MCPClient provide unified access to web search and MCP servers. The framework is designed for extensibility, allowing developers to build and contribute new agents and tools, making it a powerful platform for AI agent development with MCP support.
https://github.com/heurist-network/heurist-agent-framework
Node.js server and React dashboard that runs teams of AI agents as a virtual company, connecting them to outside tools through governed remote MCP connectors.
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.
Agent meta-harness that wraps Claude Code and Codex with 100+ specialized agents, coordinated swarms, persistent cross-session memory, and an MCP server so any MCP client can drive it.
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.