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...
The Agent2Agent (A2A) Protocol is an open protocol designed to enable communication and interoperability between opaque agentic applications, particularly in the context of generative AI agents developed on diverse frameworks and hosted on separate servers. The protocol addresses the challenge of allowing these AI agents to communicate and collaborate effectively as autonomous agents rather than mere tools. A2A provides a standardized language and framework that facilitates agent discovery, negotiation of interaction modalities (such as text, forms, and media), and secure collaboration on long-running tasks without exposing the internal state, memory, or proprietary tools of the agents involved. Key features of the A2A protocol include standardized communication using JSON-RPC 2.0 over HTTP(S), agent discovery through "Agent Cards" that detail capabilities and connection information, and flexible interaction modes supporting synchronous request/response, streaming via Server-Sent Events (SSE), and asynchronous push notifications. The protocol supports rich data exchange formats including text, files, and structured JSON data, and is designed with enterprise requirements in mind, incorporating security, authentication, and observability. The project provides SDKs in multiple programming languages such as Python, JavaScript, and Java, along with sample implementations to demonstrate the protocol in action. The A2A protocol aims to break down silos between different AI ecosystems, enable complex multi-agent collaboration, promote open standards for agent communication, and preserve the opacity of agents to protect intellectual property and enhance security. The project is open-source, maintained by Google LLC under the Apache License 2.0, and encourages community contributions to evolve the protocol. Future enhancements planned include formalizing authorization schemes within agent discovery, dynamic skill querying, improved task lifecycle and user experience features, and enhancements to client methods and transport mechanisms. Overall, the A2A protocol is a foundational technology for building interconnected, collaborative AI agent ecosystems that can operate securely and efficiently across diverse platforms and organizations.
https://github.com/a2aproject/A2A
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.