{"id":94809,"title":"🚀 Riveter API: Replace your entire scraper infrastructure with a single API","tagline":"Power your product with real data from the web.","body":"We’re excited to launch our most requested feature: the **Riveter API**.\n\nWeb data is one of the biggest unlocks for what’s now possible with AI. But retrieving and structuring that data for your product or agents is far more complicated than it should be.\n\n---\n\n### **The Problem**\n\nYou need data from the web to equip your agents with more information or pipe structured data directly into your product.\n\nBut when it comes to web scraping, the gap between _idea_ and _working solution_ is huge.\n\n* What starts as **“just a simple scraper” often turns into a patchwork of 5+ vendors** (SERP providers, proxy networks, headless browsers, scraper libraries, and infrastructure) leading to weeks or months of engineering effort.\n* Timelines creep, **engineering costs rise, and maintaining scrapers becomes an ongoing burden**. All of this distracts your team from building your _core product._\n\nhttps://youtu.be/1pFXQJExRGw\n\n---\n\n### **The Solution**\n\n**Riveter** is the all-in-one web search agent. Configuration is simple — your team defines what data they need, and Riveter handles everything else.\n\n* **Prompt-based configuration, tool selection, and custom formatting.** Tell Riveter what you need via a prompt, then select tools like web search, scraper, PDF reader, or image reader.\n* **Everything built in.** SERP/search, proprietary scrapers, proxy management, and browser infrastructure are fully integrated, so you don’t have to build or connect multiple systems.\n* **Structured, consistent output.** Apply custom tags or enums, specify date formats, or define JSON objects to get clean, predictable results every time.\n\nThe API routes data directly into your app — giving you real, grounded web data with minimal engineering overhead.\n\n### **How It Works**\n\nYou can either **create a project in Riveter** to reference in your API request, or **configure all input and output fields directly in the API call.**\n\n#### **Option 1: Creating an API request from a Riveter project**\n\nCreating a project allows you to test and refine prompts and formatting before fetching data via the API.\n\n**Best for:**\n\n* Running recurring or long-term data collection\n* Quickly testing and iterating on prompts and tools\n* Structuring data that needs to be ingested by code\n\n#### **Option 2: Configuring input/output fields directly in the API request**\n\nOn-the-fly configuration gives you the flexibility to change columns and prompts dynamically based on your inputs.\n\n**Best for:**\n\n* Giving AI agents access to create their own Riveter requests\n* Handling variable outputs - e.g., running an initial request with Riveter, then defining attributes to evaluate your product or dataset on\n\n### **Getting Started**\n\nWe can’t wait to see what you build with Riveter!\n\nHead to[ ](https://riveterhq.com?utm_source=chatgpt.com)[**riveterhq.com**](http://riveterhq.com) and click **Get Started** — your first 500 searches are free!\n\nNeed a hand?[ Grab time here](https://riveterhq.com/contact?utm_source=chatgpt.com) and we’ll help you get set up.","slug":"OfB-riveter-api-replace-your-entire-scraper-infrastructure-with-a-single-api","created_at":"2025-10-21T20:14:19.297Z","updated_at":"2026-05-25T01:41:34.660Z","total_vote_count":14,"url":"https://www.ycombinator.com/launches/OfB-riveter-api-replace-your-entire-scraper-infrastructure-with-a-single-api","share_image_url":"//bookface-static.ycombinator.com/assets/ycdc/yc-og-image-c440a0ad1dacfb86eeeb343717479cc54d256614449b4ef719977a0a451f8bc8.png","company":{"id":30017,"name":"Riveter","slug":"riveter","url":"https://www.riveterhq.com/","logo":"https://bookface-images.s3.amazonaws.com/small_logos/ba11fcc185e7540e26d2fc388417c1e4c6dfad61.png","batch":"Fall 2024","industry":"B2B","tags":["Artificial Intelligence","B2B","E-commerce","Market Research","AI"],"search_path":"https://bookface.ycombinator.com/company/30017"}}