affaan-m/ECC
ECC is a comprehensive agent harness performance optimization system providing skills, instincts, memory, security, and research-first development for various AI agent harnesses including Claude Co...
FradSer/mcp-server-mas-sequential-thinking
The project "mcp-server-mas-sequential-thinking" is an advanced implementation of a sequential thinking process using a Multi-Agent System (MAS) architecture, developed with the Agno framework and served via the Model Context Protocol (MCP). This system represents a significant evolution from simpler state-tracking or single-agent approaches by employing a coordinated team of specialized agents to collaboratively analyze, synthesize, and process complex thoughts for deeper problem-solving. The MAS includes a coordinating agent (the Team object in coordinate mode) that manages workflow and delegates specific sub-tasks to specialized agents such as Planner, Researcher, Analyzer, Critic, and Synthesizer. These agents actively process incoming thoughts, enabling complex thought patterns including revisions and branching to explore alternative problem-solving paths. The system integrates external tools like Exa for dynamic information gathering and uses robust Pydantic validation to ensure data integrity. Detailed logging tracks agent interactions and the overall process. This Python/Agno implementation marks a fundamental shift from the original TypeScript version by moving from passive logging to active thought processing with distributed agent logic and explicit team coordination. The system is designed to provide higher quality analysis and nuanced thinking by leveraging the collaborative power of specialized AI agents. It requires Python 3.10+, compatible LLM APIs, and optionally an Exa API key for enhanced research capabilities. The server runs as an executable script communicating via stdio, compatible with MCP client configurations. Due to the MAS architecture, the tool consumes significantly more tokens than single-agent alternatives, prioritizing analysis depth and quality over token efficiency.
https://github.com/FradSer/mcp-server-mas-sequential-thinking
Also in Agent Platforms
open-webui/open-webui
Open WebUI is a self-hosted, extensible AI platform supporting multiple LLM runners and OpenAI-compatible APIs with advanced features like Retrieval Augmented Generation, model building, and offline deployment.
Mintplex-Labs/anything-llm
AnythingLLM is an all-in-one AI application with full MCP compatibility that enables intelligent chat interactions with documents using various LLMs, multi-user support, and no-code AI agent building capabilities.
aaif-goose/goose
goose is an open-source, extensible AI agent providing desktop, CLI, and API interfaces for code, workflows, and general tasks, featuring broad LLM provider compatibility and connection to MCP exte...
HKUDS/nanobot
nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework in Python, offering a WebUI, tools, memory, MCP integration, multi-agent workflows, automation, and chat app co...
zhayujie/CowAgent
CowAgent is an open-source, multi-model AI assistant and Agent Harness designed for autonomous task planning, tool execution, and continuous learning, featuring native Model Context Protocol (MCP) ...
sickn33/agentic-awesome-skills
This project provides an installable GitHub library and npm installer for over 1,900 agentic skills and playbooks, designed to enhance AI coding assistants like Claude Code, Gemini CLI, Cursor, and...
danny-avila/LibreChat
LibreChat is an open-source enhanced ChatGPT clone that integrates multiple AI models and supports the Model Context Protocol (MCP) for advanced AI assistant features including no-code agents, secure code execution, multimodal interactions, and customizable conversation management.