# World2Agent：为AI智能体补上"感知"层，让它们能主动察觉现实世界事件

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-04-30 00:28
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmoka5eq200h8sleg59rzvksb
- 原文链接：https://x.com/rohanpaul_ai/status/2049526278915867043

## AI 摘要

当前AI智能体缺乏感知层，只能被动响应提示。World2Agent (W2A) 通过构建开放协议解决了这一问题，它将现实世界事件（如GitHub动态、股价变动或社交媒体帖子）通过传感器转化为结构化信号。智能体可订阅这些信号，从而能自主决策和行动，无需人工持续输入。这消除了开发者需手动集成轮询、Webhook等复杂逻辑的负担。本质上，W2A为构建主动型智能体提供了缺失的基础设施层，类似于MCP协议为工具调用所做的标准化工作。例如，当特定人物发帖时，传感器捕捉信号后，智能体可自动触发代码库审查任务，实现了“知道何时行动”的关键能力。

## 正文

Right now AI Agents have a serious missing layer - agents can act， but they still can't really notice.

Most agents still wait for a prompt. World2Agent （W2A） changes the setup： sensors watch real-world events， turn them into structured signals， and send them to agents so they can decide and act without someone manually feeding every update.

So W2A has built an open protocol that gives AI agents a standard way to notice real-world events， not just respond after a human tells them something. Sensors provide real-world context. You define the action.

Think GitHub trends， stock moves， Steam deals， meeting changes， research drops， X posts， error logs， or any source that can emit a signal.

Today's agents are mostly reactive because they lack a perception layer， and builders currently have to manually stitch together polling， webhooks， auth， schemas， deduplication， and delivery logic every time they want an agent to "notice" something.

The important idea is this： tools give agents the ability to act， but sensors give them the ability to know when to act.

W2A wants sensors to emit structured signals in one shared format， so an agent can subscribe to them the way software subscribes to events.

So basically this is the missing infrastructure layer for proactive agents， similar in spirit to what MCP did for tool use.

🧵 1. In this example here， Andrej Karpathy posts → Sensor catches the signal → Agent auto-reviews your codebase using their insight.