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...
themanojdesai/python-a2a
Python A2A is a production-ready Python library that fully implements Google's Agent-to-Agent (A2A) protocol with integrated support for the Model Context Protocol (MCP). This library enables seamless communication and collaboration between interoperable AI agents, allowing developers to build sophisticated multi-agent ecosystems that can work together to solve complex problems. The A2A protocol standardizes communication between AI agents regardless of their underlying implementation, while MCP extends this by providing a standardized way for agents to access external tools and data sources. The library offers a comprehensive and intuitive API that supports the latest MCP v2.0, rebuilt from scratch following the JSON-RPC 2.0 specification. It features a provider-based architecture for external MCP servers, including providers for GitHub, browser automation, and filesystem management, with real-world production-ready examples. Python A2A supports enterprise-grade deployments with robust transport abstractions such as stdio and Server-Sent Events (SSE), ensuring reliable and scalable communication. Key features include an agent network system for managing and discovering multiple agents, a workflow engine for defining complex multi-agent workflows with conditional branching and parallel execution, and an AI-powered router to automatically route queries to the most appropriate agent. The library also provides a command-line interface for agent control, enhanced asynchronous support, and improved error handling and retry logic. Python A2A integrates seamlessly with LangChain, allowing the use of tools and agents from both ecosystems in mixed workflows. It supports converting between A2A agents and LangChain agents, enabling developers to leverage thousands of pre-built tools instantly. The streaming architecture is advanced, with task-based streaming, improved chunk processing, multi-endpoint support, and robust fallback mechanisms. Designed to be framework-agnostic, Python A2A works with any Python web framework such as Flask, FastAPI, or Django. It offers native integrations with major LLM providers including OpenAI, Anthropic, AWS Bedrock, and Ollama. The library is production-ready with minimal dependencies, excellent developer experience through comprehensive documentation, type hints, and examples, making it suitable for enterprise and research applications in AI agent interoperability and collaboration.
https://github.com/themanojdesai/python-a2a
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.