启动 HN：Voygr（YC W26）——为代理和人工智能应用提供更好的地图 API
嗨，HN，我们是来自VOYGR的Yarik和Vlad（<a href="https://voygr.tech">https://voygr.tech</a>），致力于为应用开发者和代理商提供更好的现实世界地点智能。这里有一个演示：<a href="https://www.youtube.com/watch?v=cNIpcWIE0n4" rel="nofollow">https://www.youtube.com/watch?v=cNIpcWIE0n4</a>。
谷歌地图可以告诉你某家餐厅的评分是“4.2星，营业到10点”。但他们的API无法告诉你厨师上个月离职、等待时间翻倍以及当地人已经转移的情况。如今的地图API仅提供固定的快照。我们正在构建一个无限、可查询的地点档案，结合准确的地点数据和最新的网络信息，如新闻、文章和事件。
Vlad曾参与谷歌地图API的开发，并在共享出行和旅游领域工作。Yarik在苹果、谷歌和Meta负责机器学习/搜索基础设施，推动数亿用户每天使用的产品。我们意识到，没有人将地点数据的新鲜度视为基础设施，因此我们正在构建它。
我们从最困难的部分开始——确认一个地点是否真实。我们的商业验证API（<a href="https://github.com/voygr-tech/dev-tools" rel="nofollow">https://github.com/voygr-tech/dev-tools</a>）可以告诉你一个商家是否实际运营、关闭、重新品牌或无效。我们聚合多个数据源，检测冲突信号，并返回结构化的判断。可以把它想象成物理世界的持续集成。
问题是：约40%的谷歌搜索和高达20%的大型语言模型（LLM）提示涉及本地上下文。每年有25-30%的地点会发生变化。世界并不会主动发出结构化的“我关闭了”的事件——你必须主动去检测。随着代理商开始在现实世界中搜索、预订和购物，这个问题变得更大——而且没有人正在为此构建基础设施。我们最近对大型语言模型处理本地地点查询的能力进行了基准测试（<a href="https://news.ycombinator.com/item?id=47366423">https://news.ycombinator.com/item?id=47366423</a>）——结果不佳：即使是最好的模型也会在12个本地查询中出错1次。
我们每天为企业客户处理数万个地点，包括领先的地图和科技公司。今天，我们向开发者社区开放API访问。请在这里查看详细信息：<a href="https://github.com/voygr-tech/dev-tools" rel="nofollow">https://github.com/voygr-tech/dev-tools</a>。
我们非常希望得到诚实的反馈——无论是关于问题、我们的解决方案，还是你认为我们哪里做错了。如果你在自己的产品中遇到过过时的地点数据，我们尤其希望听到你的意见。我们全天在线，欢迎提问。
查看原文
Hi HN, we’re Yarik and Vlad from VOYGR (<a href="https://voygr.tech/">https://voygr.tech/</a>), working on better real-world place intelligence for app developers and agents. Here’s a demo: <a href="https://www.youtube.com/watch?v=cNIpcWIE0n4" rel="nofollow">https://www.youtube.com/watch?v=cNIpcWIE0n4</a>.<p>Google Maps can tell you a restaurant is "4.2 stars, open till 10." Their API can't tell you the chef left last month, wait times doubled, and locals moved on. Maps APIs today just give you a fixed snapshot. We're building an infinite, queryable place profile that combines accurate place data with fresh web context like news, articles, and events.<p>Vlad worked on the Google Maps APIs as well as in ridesharing and travel. Yarik led ML/Search infrastructure at Apple, Google, and Meta powering products used by hundreds of millions of users daily. We realized nobody was treating place data freshness as infrastructure, so we're building it.<p>We started with one of the hardest parts - knowing whether a place is even real. Our Business Validation API (<a href="https://github.com/voygr-tech/dev-tools" rel="nofollow">https://github.com/voygr-tech/dev-tools</a>) tells you whether a business is actually operating, closed, rebranded, or invalid. We aggregate multiple data sources, detect conflicting signals, and return a structured verdict. Think of it as continuous integration, but for the physical world.<p>The problem: ~40% of Google searches and up to 20% of LLM prompts involve local context. 25-30% of places churn every year. The world doesn't emit structured "I closed" events - you have to actively detect it. As agents start searching, booking, and shopping in the real world, this problem gets 10x bigger - and nobody's building the infrastructure for it. We recently benchmarked how well LLMs handle local place queries (<a href="https://news.ycombinator.com/item?id=47366423">https://news.ycombinator.com/item?id=47366423</a>) - the results were bad: even the best gets 1 in 12 local queries wrong<p>We're processing tens of thousands of places per day for enterprise customers, including leading mapping and tech companies. Today we're opening API access to the developer community. Please find details here: <a href="https://github.com/voygr-tech/dev-tools" rel="nofollow">https://github.com/voygr-tech/dev-tools</a><p>We'd love honest feedback - whether it's about the problem, our approach, or where you think we're wrong. If you're dealing with stale place data in your own products, we'd especially love to hear what breaks. We're here all day, AMA.