Skip to main content
Integrate Firecrawl with OpenClaw to give your agents the ability to scrape, search, crawl, and interact with the web, and run Agent jobs, all through the Firecrawl CLI.

​
Why Firecrawl + OpenClaw

  • No local browser needed — every session runs in a remote, isolated sandbox. No Chromium installs, no driver conflicts, no RAM pressure on your machine.
  • Real parallelism — run many browser sessions at once without local resource fights. Agents can browse in batches across multiple sites simultaneously.
  • Secure by default — navigation, DOM evaluation, and extraction all happen inside disposable sandboxes, not on your workstation.
  • Better token economics — agents get back clean artifacts (snapshots, extracted fields) instead of hauling giant DOMs and driver logs into the context window.
  • Full web toolkit — scrape, search, and browser automation all through a single CLI that your agent already knows how to use.

​
Setup

Tell your agent to install the Firecrawl CLI, authenticate and initialize the skill with this command:
  • --all skips agent selection and initializes every detected agent
  • --browser opens the browser for Firecrawl authentication automatically
or install everything separately:
Verify everything is set up correctly:
Once the skill is installed, your OpenClaw agent automatically discovers and uses Firecrawl commands — no extra configuration needed.

​
Scrape

Scrape a single page and extract its content:
Get specific formats:
Search the web and optionally scrape the results:

​
Interact

Scrape a page, then keep working with it in a live browser session. Each session runs remotely in an isolated sandbox, so no local Chromium install is required. interact uses the most recent scrape by default.
Run code against the live page instead of a prompt:
Your agent issues intent-level prompts, or short Playwright snippets, instead of managing a local browser. Run firecrawl interact stop when it’s done to release the session. The older firecrawl browser command is deprecated; use scrape followed by interact instead.

​
Example: tell your agent

Here are some prompts you can give your OpenClaw agent:
  • “Use Firecrawl to scrape https://example.com and summarize the main content.”
  • “Search for the latest OpenAI news and give me a summary of the top 5 results.”
  • “Use Firecrawl to open Hacker News with interact, get the top 5 stories, and the first 10 comments on each.”
  • “Crawl the docs at https://docs.firecrawl.dev and save them to a file.”

​
Further reading