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...
ChronulusAI/chronulus-mcp
chronulus-mcp is a Model Context Protocol server published by Chronulus AI that exposes its hosted forecasting and prediction agents to MCP clients, so a user can ask for a forecast in a chat session and get a prediction plus the agent explanation back. The server is a thin bridge: it authenticates against the Chronulus service with a CHRONULUS_API_KEY environment variable and relays the session to the Chronulus agents, which do the forecasting work remotely. Installation follows the standard Python MCP patterns. The package is on PyPI and can be installed with pip and then run as a module, pulled and run directly with uvx, installed from a Git clone, or built into a Docker image and started with docker run so the API key is passed in as an environment variable. The README documents the matching claude_desktop_config.json entries for each of those options on macOS and Windows, including the common failure where the client reports a spawn ENOENT error and the fix is to give the absolute path to the python or uvx binary. The project is written for a workflow in which Chronulus runs alongside other MCP servers: the demo configuration adds the reference filesystem and fetch servers so documents and web pages can be pulled into a forecasting request, and the README shows the Claude profile preferences used for the published demos. Those preferences steer the assistant to pass documents to Chronulus through its own TextFromFile, PdfFromFile and ImageFromFile input field types rather than reading binary files directly, and to print the Chronulus forecast explanation underneath any plot of a forecast. It is aimed at analysts and forecasting users who already have a Chronulus account.
https://github.com/ChronulusAI/chronulus-mcp
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.