machinepulse-ai/world2agent

World2Agent(W2A) is an open protocol that standardizes how Al agents perceive the real world.

What it solves

World2Agent (W2A) addresses the perception gap for AI agents, providing a standardized way for agents to receive real-time, structured data from the physical and digital world. Instead of building custom integrations for every data source, developers can use a common protocol that allows agents to perceive environment changes and act upon them.

How it works

W2A operates on a "World $\rightarrow$ Sensor $\rightarrow$ Agent" architecture. Sensors act as bridges that monitor specific data sources and emit signals in a standardized schema. These signals are then delivered to AI agents via plugins or bridges for various agent runtimes (such as Claude Code, Hermes, and OpenClaw).

Who it’s for

  • AI Agent Developers: Those looking to integrate real-time world data into their agents without writing custom boilerplate for every single API.
  • Community Contributors: Developers who want to build and share new sensors as npm packages to expand the agent perception ecosystem.

Highlights

  • Open Protocol: A standardized schema for how agents perceive the world, allowing sensors to be swapped freely.
  • Plugin Ecosystem: Native support for popular agent runtimes like Claude Code, Hermes, and OpenClaw.
  • SensorHub: A centralized catalog of official and community-built sensors for tracking everything from news and markets to production alerts.
  • Easy Sensor Creation: Tools and skills to help developers build and publish new sensors to npm in approximately 50 lines of code.

Related

  • Project
    a2aproject/A2A

    An open protocol that enables communication and interoperability between AI agents built on different frameworks and servers, allowing them to collaborate without exposing internal logic.

  • Dispatch
    The A2A Protocol: Enterprise Agent Communication vs. MCP

    The A2A (Agent-to-Agent) protocol by Google aims to standardize how independent AI agents discover and communicate, though it faces stiff competition from the Model Context Protocol (MCP) in the startup and developer ecosystem.

  • Project
    ag-ui-protocol/ag-ui

    An open, event-based protocol that standardizes how AI agents connect to user-facing applications, enabling real-time interaction and generative UI.

  • Project
    a2aproject/a2a-samples

    A collection of code samples and demonstrations for the Agent2Agent (A2A) protocol, designed to enable interoperability and communication between different AI agents.

  • Project
    ai-sns/ai-sns

    A distributed social infrastructure network that allows AI agents to communicate, collaborate, and compete on a real-time 3D map without a central server.