a2aproject/A2A
Agent2Agent (A2A) is an open protocol enabling secure communication and interoperability between diverse generative AI agents to foster collaboration and innovation in the AI ecosystem.
Awesome AI Agents › Multi-Agent Platforms
IBM/mcp-context-forge
The IBM MCP Context Forge project is a Model Context Protocol (MCP) Gateway designed to serve as a central management point for tools, resources, and prompts accessible by MCP-compatible large language model (LLM) applications. It acts as a gateway and proxy that federates MCP and REST services, providing a unified endpoint for AI clients. The gateway supports converting REST API endpoints to MCP, composing virtual MCP servers with enhanced security and observability, and converting between multiple protocols such as stdio and Server-Sent Events (SSE). The MCP Gateway offers a comprehensive feature set including federation across multiple MCP and REST services, virtualization of legacy APIs as MCP-compliant tools and servers, and support for various transport protocols including HTTP, JSON-RPC, WebSocket, SSE, and stdio. It includes an optional Admin UI for real-time management and configuration, built with HTMX and Alpine.js, and supports authentication methods like Basic, JWT, and custom schemes. The gateway is designed for scalability and production use, deployable via PyPI or Docker, and capable of multi-cluster Kubernetes deployments with Redis-backed federation and caching. It provides built-in observability features such as structured logs, health endpoints, and metrics, along with retry and rate-limiting policies to ensure robust operation. Additional capabilities include automatic JSON Schema extraction for REST-to-MCP tool adaptation, support for headers, tokens, and custom authentication, and unified registries for prompts, resources, and tools with features like versioning, MIME detection, caching, and concurrency controls. The project is well-tested with over 400 tests and includes developer conveniences like live reload and pre-commit hooks. Overall, the MCP Gateway simplifies the integration and management of diverse AI tools and services by providing a unified, secure, and scalable interface that supports multiple protocols and deployment environments, making it a valuable component for AI infrastructure leveraging the Model Context Protocol.
https://github.com/IBM/mcp-context-forge
Also in Multi-Agent Platforms
a2aproject/a2a-python
The A2A Python SDK is an official toolkit for building and running agentic applications as A2AServers following the Agent2Agent (A2A) Protocol, supporting multiple databases and easy installation.
TooTallNate/proxy-agents
TooTallNate/proxy-agents is a Node.js monorepo containing various HTTP Proxy Agent implementations that enable routing HTTP requests through different proxy protocols.
i-am-bee/acp
ACP is an open protocol enabling seamless communication and coordination between AI agents, applications, and humans through structured multimodal messages.
BigSweetPotatoStudio/HyperChat
HyperChat is an open-source, cross-platform chat client that integrates multiple LLM APIs and the MCP protocol to deliver a versatile and productivity-enhancing chat experience.
ai-boost/awesome-a2a
A curated collection of resources, tools, and implementations for the Google Agent2Agent (A2A) Protocol enabling secure communication and collaboration between AI agents from different vendors and frameworks.
operand/agency
Agency is a minimal and scalable Python framework for building flexible agentic systems using the Actor model, supporting concurrency, networked communication, and detailed observability.
livekit/python-sdks
LiveKit Python SDKs provide real-time video, audio, and data communication capabilities for Python applications, enabling easy integration with LiveKit Cloud or self-hosted servers for building interactive and streaming applications.