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...
Awesome MCP › Agent Platforms
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...
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.
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.
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...
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...
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) ...
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...
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.
MindsHub is a unified workspace for AI agents, allowing users to automate tasks, connect data, and swap between open-source and proprietary models to build and publish AI-driven applications.
A multi-harness agentic plugin marketplace providing 84 plugins, 192 agents, 156 skills, and 102 commands specifically designed for Claude Code but consumable across OpenAI Codex CLI, Cursor, OpenC...
A curated list of resources and tools for customizing Claude AI workflows and building specialized AI agents.
An official Anthropic-managed directory of high-quality plugins for Claude Code, supporting MCP server configurations and plugin integration to extend Claude Code's functionality.
AgentScope is a multi-agent platform that simplifies building LLM-empowered distributed applications with robust fault-tolerance and integration with Model Context Protocol (MCP) Server.
Oh My Pi (omp) is an advanced AI coding agent for the terminal, integrating IDE features, optimized tool harnesses, LSP, and debugging capabilities for enhanced development workflows.
Agent2Agent (A2A) is an open protocol that enables secure communication and interoperability between opaque AI agents, facilitating multi-agent collaboration across diverse platforms and ecosystems.
Go Micro is a versatile Go framework for building AI agents and distributed services, integrating Model Context Protocol (MCP) for seamless communication and tool orchestration.
DocsGPT is a private AI platform for building intelligent agents, assistants, and enterprise search with multi-model support, deep research, document analysis, and extensive API connectivity, designed for secure and scalable deployment including MCP integration.
Astrid is a portable, capability-secure operating system designed for composable software, emphasizing runtime trust over prompt trust for AI agents by enforcing security boundaries.
Evolver is a GEP-powered self-evolution engine for AI agents that transforms ad hoc prompt tweaks into auditable, reusable evolution assets through Genes and Capsules.
Microsandbox is a self-hosted, secure sandbox environment that uses hardware-level microVM isolation and built-in MCP support to safely and rapidly run AI-generated or untrusted code with full user control.
Mobile Next is a Model Context Protocol server enabling scalable, platform-agnostic mobile automation and development across iOS, Android, emulators, simulators, and physical devices using structured accessibility data and screenshot-based interactions.
Klavis AI is an open-source platform offering production-ready Model Context Protocol (MCP) servers and clients for seamless integration and scaling of AI applications across multiple platforms with built-in authentication and extensive tool support.
Openfang is an open-source Agent Operating System built in Rust for managing and coordinating AI agents, potentially leveraging LLMs and adhering to the Model Context Protocol.
GaiaNet Node is a decentralized AI agent platform that enables users to install, configure, and run their own AI nodes using open-source models and vector databases in a distributed network.
ACI.dev is an open-source platform that enables AI agents to securely access and interact with over 600 integrated tools via a unified Model-Context-Protocol (MCP) server or direct function calls, simplifying authentication and infrastructure for production-ready AI applications.
Agentgateway is a high-performance, secure, and multi-tenant agent gateway designed for enterprise-grade deployments with robust MCP-focused features and dynamic configuration support.
53AI Hub is an open-source AI portal that enables rapid building, deployment, and management of AI agents, prompts, and tools with seamless integration to multiple development and cloud platforms, supporting both cloud and local environments.
Octelium is a free and open-source self-hosted unified zero trust secure access platform supporting remote access VPN, ZTNA, API/AI gateways, PaaS, Kubernetes ingress, and MCP/A2A architectures.
kagent is a Kubernetes native framework for building, deploying, and managing AI agents with integration as an MCP server, supporting multiple LLM providers and tools as Kubernetes custom resources.
Shrimp Task Manager is an MCP-based intelligent task management system that converts natural language into structured development tasks with dependency tracking and iterative refinement, enhancing AI Agents' programming workflows through chain-of-thought reasoning and task memory.
The a2a-python project is the official Python SDK for the Agent2Agent (A2A) Protocol, enabling developers to build and run agentic applications as A2AServers following the A2A Protocol.
SmythOS is a comprehensive operating system designed to build, deploy, and manage intelligent AI agents at scale with a unified SDK and modular architecture.
AWorld is an open-source framework that utilizes MCP servers to build and run collaborative multi-agent assistance systems, advancing agentic AI through self-improving multi-agent learning.
Pydantic Deep Agents is a Python framework for building production-grade autonomous AI agents with advanced capabilities like planning, filesystem operations, subagent delegation, and comprehensive...
Arcade AI Platform is a modular developer platform for building, deploying, and managing AI agent tools, featuring serving infrastructure for Model Context Protocol (MCP) servers.
Python A2A is a production-ready Python library implementing Google's Agent-to-Agent protocol with full Model Context Protocol integration, enabling seamless communication and collaboration between interoperable AI agents.
ARGO is an open-source local AI agent platform that integrates generative AI models and MCP tools to provide autonomous task planning, execution, and private offline operation for complex workflows.
Evo AI is an open-source platform for creating, managing, and integrating diverse AI agents with support for Model Context Protocol and Google's Agent 2 Agent interoperability protocol.
Joinly.ai is an open-source middleware platform that enables AI agents to join and actively participate in video meetings using a Model Context Protocol server, supporting real-time interaction and multiple meeting platforms.
This project offers an MCP server for agentic interaction with the Lean theorem prover via the Language Server Protocol, providing tools for LLM agents to understand, analyze, and interact with Lea...
1MCP is a unified Model Context Protocol server that aggregates multiple MCP servers into a single, resource-efficient, and secure interface for managing AI assistants.
Vibe Check MCP is a research-backed MCP server that acts as an AI meta-mentor to prevent over-engineering and reasoning lock-in in AI agent workflows by implementing strategic pattern interrupts and metacognitive oversight.
Agent Control Plane (ACP) is a cloud-native distributed agent scheduler on Kubernetes designed for orchestrating outer-loop AI agents with asynchronous tool calls and full Model Context Protocol (MCP) support.
Skillz is an MCP server that enables the loading, discovery, and execution of Claude-style skills for various AI agents, providing a flexible and standardized way to extend agent capabilities.
BlockRun MCP is an open-source Model Context Protocol server providing AI agents with 20+ tools for real-time data, actions, and Polymarket trading, with pay-per-call USDC micropayments and no API ...
TypeScript planning and execution layer for AI coding agents on Claude Code and Codex, storing state in a per-repo SQLite file and shipping a genie mcp command that serves task and board state over stdio MCP.
Python environment platform for agentic reinforcement learning from Ant Group that exposes tools, benchmarks and whole agents as MCP-based environments behind one unified Environment interface.
An advanced Multi-Agent System for sequential thinking implemented with the Agno framework and served via MCP, enabling coordinated specialized agents to collaboratively analyze and synthesize complex thoughts for deeper problem-solving.
The PayPal Agent Toolkit enables integration of popular agent frameworks and the Model Context Protocol (MCP) with PayPal APIs, providing extensive tools for managing invoices, payments, disputes, shipments, products, subscriptions, and business insights through AI-driven function calling.
Large MCP-native Python server bundling dozens of agent capabilities: multi-provider LLM routing, cognitive memory, browser automation, documents, databases, vector search and CLI utilities.
A Python service that deploys Haystack pipelines and agents as REST APIs and simultaneously exposes each of them as an MCP tool, with A2A, OpenAI-compatible chat completion and tracing options.
An MCP server that queries other AI CLIs — Codex, Gemini, OpenCode, ClaudeOR and AiChat — from inside Claude Code and can run a multi-round deliberation between them.
Python MCP server that connects Claude Desktop and other MCP clients to the Chronulus AI forecasting and prediction agents through the Chronulus API.
An MCP server fronting several deep research agents — OpenAI Deep Research, Gemini Deep Research, Allen AI's DR-Tulu and Hugging Face's Open Deep Research — behind one interface.
An MCP server for Replicate's API that runs hosted machine-learning models through a tool interface. It is superseded by Replicate's official server and no longer developed.
An MCP server fronting Octagon's hosted deep research agents, adding comprehensive multi-source research and analysis to any MCP client without rate limits.
An MCP server that puts one question to several local Ollama models, each with its own persona, and returns their answers for the calling model to synthesise.
Go MCP server that lists and executes Dify workflows on demand, mapping workflow names to API keys so an MCP client can invoke several custom Dify applications by name.