Obsession vs Firecrawl: scraped pages beside what companies show only to customers
Firecrawl reads a page the moment your code asks, login steps included. Obsession stays signed up for months and keeps every email, price and offer that arrives.
Example: Northwind is an invented company
- Firecrawl’s column follows its own pages, read 11 November 2026. Not described means its pages don’t say.
In Obsession vs Firecrawl, Firecrawl turns pages into clean data for AI agents and Obsession keeps what companies show only to signed-up customers. Firecrawl reads a page when your code asks, login steps included in a short session; Obsession stays signed up for months and keeps every email, member price, trial limit and cancel offer, each dated with a screenshot. Teams often use Firecrawl for what a company publishes and Obsession for what it sends its customers.
ComparedFirecrawl and Obsession at a glanceGo straight to the comparisonOn this page
What Firecrawl and Obsession are
Firecrawl: web data from any page you point it at
As of 11 November 2026, Firecrawl’s home page says “Firecrawl is the open-source web data API for AI agents and LLM applications”. Its products are Search, Scrape, Crawl, Map, Parse, Interact and Monitor: find pages, turn them into markdown or JSON, walk a whole site, and check pages again for changes.
For pages behind a login, Firecrawl offers two tools. Its scrape endpoint takes actions such as click, write, press and wait before it reads a page, and serves a cached copy younger than 2 days unless you ask for a fresh one. Interact drives a managed browser through multi-step flows; its home page says it supports “login, click, fill” but “is not designed for long-running persistent sessions”. Its pages don’t describe staying signed up to a company for days or keeping the emails a company sends.
Obsession: the web behind the login, kept over time
Obsession collects what companies show only to customers, step by step: their screens, emails and texts, member prices, trial limits, quotes and cancel offers, each dated with a screenshot. Teams and AI agents look up any company through the API or MCP, and a company not yet covered is added on request. Each account stays open for months, so every new email, price and offer lands dated the day it arrives, and nobody writes or maintains login steps for each company.
Firecrawl and Obsession at a glance
| Option | What it holds | How it’s read | Freshness and history | Price as listed | Best for |
|---|---|---|---|---|---|
| FirecrawlSearch, Scrape, Crawl, Map, Interact, Monitor | Any page you point it at, as markdown or JSON | API, SDKs, CLI and an MCP server | Cache up to 2 days, or freshMonitor checks pages again | Free: 1,000 credits a monthStandard $99 a monthScale $749 a month | Turning public pages into data |
| ObsessionOursSearch, Insights, Watch, API and MCP | Emails, member prices, trial limits, quotes, cancel offers | 5 verbs over MCP, the API and SDKs, or a table | Kept from the first sign-upEach fact dated with its screenshot | Early access, onboarding teams nowPriced per call or per company watched | What a company shows only to customers |
When to use Firecrawl, and when to use Obsession
- Use Firecrawl to read pages on demand: a competitor’s docs, a whole site crawled into your own search, a public pricing page turned into JSON, or a page you check again each week. It is open source, so a team can run it itself.
- Use Obsession for what a company shows only after someone becomes its customer: the welcome email and the 3 that follow, the price a signed-in member pays, the limit on the free plan and the save offer in the cancel flow. Those arrive over days and weeks, after a login wall, so a request that lasts minutes never sees them.
- Build it yourself, or look it up. With web scraping tools or a headless browser, a team writes the login steps for each company, keeps an inbox per account and stores every capture. Obsession does that for any company you name, and keeps the history for as long as you follow it.
Using Firecrawl and Obsession together
Both run as MCP servers (Firecrawl’s is in its docs; Obsession’s install line is on the developer page), so one agent can call both. Firecrawl reads the competitor’s public site; Obsession returns what that competitor emailed new customers this month and the price a signed-in member sees, each with its receipt: the raw email with its DKIM result, or the page as captured.
To see one company’s record end to end, open the sample data. An Obsession agent never gets round a CAPTCHA or a bot block; where a site puts one in front of a step, the record names the step it couldn’t reach (the lines every agent keeps).
Yes, for a session. Its scrape actions and its Interact endpoint can fill a login form and read the page after it, and Interact can save a browser profile for later scrapes. Its home page says Interact is not designed for long-running persistent sessions.
For scraping public pages, no: use Firecrawl or another scraper. Obsession holds what companies show only to signed-up customers, kept over months, so teams that need both use both.
Its pages don’t describe it. Obsession keeps every email a company sends a new subscriber, dated as it arrived, with its sender checked.
Firecrawl lists a free plan with 1,000 credits a month, Hobby at $19, Standard at $99, Growth at $399 and Scale at $749 a month, read on 11 November 2026. Obsession is in early access and is priced per call or per company watched, never per token.
Sources
In the order the page cites them. Every page was read on 11 Nov 2026.