Riveter (YC F24)
Riveter (Y Combinator F24) · Coding · Marketing
Riveter is an AI agent that searches the live web and turns what it finds into finished, structured datasets, delivered through one API or an app.
About Riveter (YC F24)
What Is Riveter
Riveter is a web data platform from a Y Combinator F24 team. You describe the list you need in plain language, and its AI agents search the web, visit pages, read what they find and hand back a structured dataset. A dentist example the company uses: ask for every dental practice in a city and the dentists at each one, and Riveter returns the rows, contact details included.
The company frames the problem as access, not availability. The information is already online. Pulling it into a usable table is the hard part, because scrapers break when a site changes and static data vendors sell records that go stale the moment you buy them. Riveter's agents read pages the way a person would, so the same setup keeps working after a redesign, and data is fetched live at the moment you ask rather than served from a cached index. Teams at OpenAI, Snap and Fermat are named as users.
Two limits stand out. Pricing runs on credits tied to actions, so cost tracks how much searching and enrichment you ask for rather than a flat seat fee. And the free plan is sized for exploring: 250 credits a month, enough to test but not to run a production pipeline.
Getting Started
- Start a free account at riveterhq.com, or book a short demo for 1,000 trial credits
- Describe the list or question you need in a prompt, or bring your own rows of company or people data
- Let the agents search the live web, then layer on enrichments such as contact details, pricing or a lead score
- Pull the finished dataset from the app, through the API, or from an MCP connection in your AI assistant
- Schedule a monitor to re-run the same enrichment and keep the data current
Product Information
A quick look at Riveter (YC F24)'s pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Sales and GTM teams
- Data and engineering teams
- Pricing and competitive research teams
- Operations and finance teams
Tasks
- Building a list from nothing
- Enriching existing rows
- Reading hard to parse pages
- Monitoring for changes
- Answering a single research question
Scenarios
- A weekly competitor price check
- Building an outbound list
- A market map
- A fast moving dataset
- A one-off research task
Key features
Build Datasets From a Prompt
Riveter compiles any list of companies, people or places from a plain-language description, with no input data required. You can also bring your own rows and let the agents find what is missing. One request can handle a single record or millions, according to the company.
AI Agents That Search and Extract
Rather than follow a fixed page structure, Riveter's agents run searches, visit pages and read results the way a researcher would, then extract exactly the fields you asked for. The same configuration keeps working after a site redesign, which is where hand-written scrapers break.
Live Data, Not a Cached Index
Riveter fetches from live websites at the moment you ask, instead of serving results from a pre-built index. That matters for pricing, inventory, job postings and funding news, where a cached index can run weeks out of date. For fast moving data, the company says you can refresh as often as every minute.
Reliable Access to Any Source
The platform reads websites, PDFs and images, and can call third-party APIs as part of a workflow, then combine everything into one output. Riveter handles bot detection and changing layouts, so your pipelines keep running when a site shifts.
Enrichment and Monitoring
Beyond building lists, Riveter fills in new columns with an AI agent per cell, adding lead scores, contact data, pricing or custom fields. You can schedule any project to re-run and monitor for changes, keeping the dataset fresh without manual work.
API First, With an MCP Server
Everything runs through a REST API, with official SDKs for TypeScript, Python, Ruby and Go. The same endpoints are exposed as tools through a hosted or local MCP server, so the work can be driven from Claude, ChatGPT, Cursor or another AI assistant.
Pros and cons
Pros
- Fetches live data at request time, so results reflect the web now rather than a stale index
- AI agents read pages the way a person would, so pipelines survive site redesigns that break fixed scrapers
- One API covers list building, enrichment, scraping, search and extraction, with SDKs in four languages
- MCP server support lets you run the whole workflow from an AI assistant, not just a code editor
- Free plan with 250 monthly credits lets you test the core workflow before paying
Cons
- Pricing is credit-based per action, so heavy searching or enrichment adds up and is harder to predict than a flat seat fee
- The free plan's 250 credits suit testing, not a production pipeline, and scaling up means a paid plan or credit top-ups
- Deep extraction from hard sites is a separate, paid one-time discovery step per site, which adds friction for one-off jobs
Frequently asked questions
Riveter is an AI agent that finds and structures data from the web. You describe what you need in plain language, and its agents search the live web, navigate to the data and extract it, returning a finished, structured dataset through a single API. It handles bot detection, proxies and site changes.
Related content
Explore related tools, skills, and articles for Riveter (YC F24).
Riveter (YC F24) Alternatives
Base Code
Base44 (Wix) · Coding · ProductivityBase Code is a shared cloud development environment from Base44. Teammates describe changes to an existing GitHub codebase in chat, preview them live and send them back as pull requests.
Google EmbeddingGemma 2
Google DeepMind · Writing · Image · CodingGoogle EmbeddingGemma 2 is a 740M-parameter open model that turns text, code, images, audio, and video frames into vectors in one 768-dimension space, running on phones and laptops.
GitGlow
GitGlow · Coding · ProductivityGitGlow is a local-first desktop Git client that lets independent developers review their own code and their AI agents' changes in one place before shipping.