[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-716":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":19,"rankGlobal":10,"rankLanguage":10,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":16,"starSnapshotCount":16,"syncStatus":31,"lastSyncTime":32,"discoverSource":33},716,"world2agent","machinepulse-ai\u002Fworld2agent","machinepulse-ai","World2Agent(W2A) is an open protocol that standardizes how Al agents perceive the real world.","https:\u002F\u002Fworld2agent.ai",null,"TypeScript",1280,38,15,5,0,1,14,17.77,"Apache License 2.0",false,"main",true,[25,26,27],"agent","proactive-agent","protocol","2026-06-12 02:00:17","![Welcome to World2Agent](https:\u002F\u002Fworld2agent.ai\u002Fassets\u002Freadme-banner.png)\n\n\u003Cp align=\"center\">\n  \u003Ci>Agents can't act on what they can't perceive.\u003C\u002Fi>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\".\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg\" alt=\"License\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.npmjs.com\u002Forg\u002Fworld2agent\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fnpm-%40world2agent-red\" alt=\"npm\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fworld2agent.ai\">Website\u003C\u002Fa> ·\n  \u003Ca href=\"#quick-start\">Quick Start\u003C\u002Fa> ·\n  \u003Ca href=\"#sensors\">Sensors\u003C\u002Fa> ·\n  \u003Ca href=\"https:\u002F\u002Fworld2agent.ai\u002Fhub\">SensorHub\u003C\u002Fa> ·\n  \u003Ca href=\".\u002Fdocs\">Docs\u003C\u002Fa> ·\n  \u003Ca href=\"#community\">Community\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003C!-- Concept Video -->\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fworld2agent.ai\u002Fassets\u002Fpromo-w2a.mp4\">\n    Watch the W2A Concept Video\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fworld2agent.ai\u002Fassets\u002Fgithub-star.gif\" width=\"600\" alt=\"star\" \u002F>\n\u003C\u002Fp>\n\n***\n\n## What is World2Agent?\n\nWorld2Agent (W2A) is an open protocol that standardizes how AI agents perceive the real world. Install a sensor, your agent gets structured, real-time data. Swap sensors freely — they all speak the same schema.\n\nW2A isn't a product. It's an open protocol and an invitation. We built the first sensors — the real breakthroughs will come from the community.\n\n→ [Why W2A? Full story](.\u002Fdocs\u002Fwhy-w2a.md)\n\n## Architecture\n\n**World → Sensor → Agent**\n\nSensors watch data sources and emit structured data following W2A Protocol. Your agent receives signals and decides what to do.\n\n![World2Agent system architecture](.\u002Fdocs\u002Fimages\u002Fsystem-architecture.png)\n\n→ [Signal format spec](.\u002Fdocs\u002Fsignal-format.md) · [Architecture deep dive](.\u002Fdocs\u002Farchitecture.md)\n\n## Quick Start\n\nW2A ships with native [agent-runtime plugins](https:\u002F\u002Fgithub.com\u002Fmachinepulse-ai\u002Fworld2agent-plugins) for Claude Code, Hermes, and OpenClaw — pick whichever runtime you already use.\n\n### Claude Code\n\nIn an active session, install the `world2agent` plugin:\n\n```\n\u002Fplugin marketplace add machinepulse-ai\u002Fworld2agent-plugins\n\u002Fplugin install world2agent@world2agent-plugins\n\u002Freload-plugins\n```\n\nAdd a sensor — for example, Hacker News stories, frontier AI lab posts:\n\n```\n\u002Fworld2agent:sensor-add @world2agent\u002Fsensor-hackernews\n\u002Fworld2agent:sensor-add @quill-io\u002Fsensor-frontier-ai-news\n```\n\nRestart Claude Code with the plugin channel loaded so sensor signals flow into your session:\n\n```bash\nclaude --dangerously-load-development-channels plugin:world2agent@world2agent-plugins\n```\n\n### Hermes\n\nInstall the bridge once:\n\n```bash\nnpm install -g @world2agent\u002Fhermes-sensor-bridge\nhermes skills install machinepulse-ai\u002Fworld2agent-plugins\u002Fhermes-sensor-bridge\u002Fskills\u002Fworld2agent-manage\n```\n\nIn an interactive `hermes` session, describe the intent in natural language or use the slash form — the agent handles npm install, `SETUP.md` Q&A, webhook subscription, and subprocess startup:\n\n```\n\u002Fworld2agent-manage add @world2agent\u002Fsensor-hackernews\n```\n\n> First time only: the agent will ask you to restart `hermes gateway` once after it enables the webhook platform. Every install after that is seamless.\n\nEach signal triggers a fresh `AIAgent.run_conversation()` against the generated handler skill.\n\n### OpenClaw\n\nThree steps:\n\n```bash\nnpm install -g @world2agent\u002Fopenclaw-sensor-bridge\nopenclaw skills install world2agent-manage\n```\n\nThen send this in your OpenClaw chat:\n\n```\nUse world2agent-manage skill install @quill-io\u002Fsensor-frontier-ai-news\n```\n\nThe skill walks the SETUP.md Q&A, generates a handler skill, registers the sensor, and starts the supervisor. Subsequent signals each trigger a fresh `\u002Fhooks\u002Fagent` call against the handler.\n\n> First time only: the bridge writes a managed `hooks` block into `~\u002F.openclaw\u002Fopenclaw.json` (auto-generates `hooks.token` if absent) and asks you to run `openclaw gateway restart` once. A timestamped backup of the original config is kept next to the file. Every install after that is seamless.\n\nIf you have a paired chat platform (Feishu, iMessage, Telegram, …) configured via `\u003CPLATFORM>_HOME_CHANNEL` in `~\u002F.openclaw\u002F.env`, replies are auto-pushed to that chat by default.\n\n---\n\n→ Browse the full catalog on [SensorHub](https:\u002F\u002Fworld2agent.ai\u002Fhub).\n\n> **Security — install only sensors you trust.** A sensor's signals drive what your agent perceives and does, so an untrusted sensor is effectively an untrusted instruction source. Stick to open-source sensors from authors you trust, and review the code first.\n\n**Integrating W2A into your own agent system?** See the [developer quick start](.\u002Fdocs\u002Fquick-start.md#option-2-code--sdk--sensor) for the SDK code path.\n\n→ [Full guide](.\u002Fdocs\u002Fquick-start.md) · [Multi-sensor](.\u002Fdocs\u002Fmulti-sensor.md) · [SensorHub](.\u002Fdocs\u002Fsensorhub.md)\n\n## Sensors\n\n### [SensorHub](https:\u002F\u002Fworld2agent.ai\u002Fhub)\n\n**SensorHub is the catalog of every W2A sensor** — official and community-built, organized by what each one perceives (markets, news, production alerts, weather, AI labs, …). Browse it to see what's available, view each sensor's signal schema, and grab the one-line install command. **Looking for a sensor? Start here.**\n\nEvery sensor is a standard npm package — `npm search w2a-sensor` works as a fallback if you prefer the raw view.\n\n→ [SensorHub guide](.\u002Fdocs\u002Fsensorhub.md)\n\n### Missing a sensor?\n\n[Build your own](.\u002Fdocs\u002Fbuild-a-sensor.md) in ~50 lines. The `build-w2a-sensor` skill walks an AI coding agent through discovery, signal design, scaffolding, and the install recipe — install it with:\n\n```bash\nnpx skills add https:\u002F\u002Fgithub.com\u002Fmachinepulse-ai\u002Fworld2agent\u002Fskills\u002Fbuild-w2a-sensor\n```\n\nOnce it's ready, ship it to npm:\n\n```bash\nnpm publish\n```\n\nThat's it — your sensor is now installable by anyone, anywhere.\n\n## Roadmap\n\n* **Graph layer** — compose and enrich signals from multiple sensors before they reach your agent. → [RFC](.\u002Fdocs\u002Frfc-graph.md)\n\n## Contributing\n\n* 🔧 **Build a sensor** — `npm publish` and it's live\n\n* 🐛 **Report bugs** — [open an issue](https:\u002F\u002Fgithub.com\u002Fmachinepulse-ai\u002Fworld2agent\u002Fissues)\n\n* 💡 **Suggest a sensor** — [Discussions](https:\u002F\u002Fgithub.com\u002Fmachinepulse-ai\u002Fworld2agent\u002Fdiscussions)\n\n→ [Contributing guide](.\u002Fdocs\u002FCONTRIBUTING.md)\n\n## Community\n\n[Website](https:\u002F\u002Fmachinepulse.ai\u002F) · [X \u002F Twitter](https:\u002F\u002Fx.com\u002FMachinePulse_AI) · [YouTube](https:\u002F\u002Fyoutube.com\u002F@MachinePulse_AI) · [Discord](https:\u002F\u002Fdiscord.gg\u002FhDjaD8pX)\n\n\u003C!-- Star History — uncomment after launch -->\n\u003C!-- [![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=machinepulse-ai\u002Fworld2agent&type=Date)](https:\u002F\u002Fstar-history.com\u002F#machinepulse-ai\u002Fworld2agent&Date) -->\n\n## License\n\n[Apache 2.0](.\u002FLICENSE)\n\n***\n\n\u003Cp align=\"center\">\n  Built by \u003Ca href=\"https:\u002F\u002Fmachinepulse.ai\">MachinePulse\u003C\u002Fa> · Open source, open protocol, open invitation.\n\u003C\u002Fp>\n","World2Agent (W2A) 是一个开放协议，旨在标准化AI代理如何感知现实世界。其核心功能是通过安装传感器，让AI代理能够接收结构化、实时的数据，并且这些传感器遵循统一的数据模式，方便用户自由更换不同类型的传感器。W2A采用TypeScript开发，支持多种流行的AI运行时环境如Claude Code, Hermes等，使得开发者可以轻松地将其集成到现有项目中。适用于需要增强AI系统对外部信息响应能力的各种场景，比如新闻聚合、市场分析等领域。",2,"2026-06-11 02:38:51","CREATED_QUERY"]