Firecrawl + FileTools

[gurezende]

Hey,

I have been working on a single agent where I use Firecrawl to scrape a webpage, and I would like that saved to a markdown file.
I know the scrape is working because I can see it on the firecrawl Dashboard, however it is not saving to the file as I ask it to.
Not sure what I am doing wrong here.

from agno.agent import Agent
from agno.models.google import Gemini
import os
from agno.tools.firecrawl import FirecrawlTools
from agno.tools.file import FileTools

url = "https://en.wikipedia.org/wiki/List_of_largest_banks"

# Web-Search Agent 
agent = Agent(model= Gemini(id="gemini-1.5-flash",
              api_key = os.environ.get("GEMINI_API_KEY")),
              tools=[FirecrawlTools(scrape=True, formats=["markdown"]),
                     FileTools(read_files=True, save_files=True)],
              description= "You are an assistant that can search the web, read and save files.",
              instructions= ["Use the Firecrawl tool to scrape the website",
                             "Get the result scraped from the url and save it to a file named 'content.md'"
                             "Use FileTools to read and save files",
                             ],
              expected_output="The website's content."
              )

# Run agent
agent.print_response(
    f"Get the Firecrawl result scraped from {url} and save it to a file named 'content.md'",
    markdown=True
   ) 

The tool calls show it is apparently working, but my file shows only "content". So it is saving the word "content", not the variable's content.

┏━ Tool Calls ┃
┃ • scrape_website(url=https://en.wikipedia.org/wiki/List_of_largest_banks) ┃
┃ • save_file(contents=content, file_name=content.md)

[monali7-d]

Hi @gurezende
thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon.
If it’s urgent, please let us know. We appreciate your patience!

[gurezende]

Thanks! Em seg., 9 de jun. de 2025 às 02:25, Monali ***@***.***> escreveu:

…

Hi @gurezende <https://github.com/gurezende> thanks for reaching out and supporting Agno. I’ve shared this with the team, we’re working through all requests one by one and will get back to you soon. If it’s urgent, please let us know. We appreciate your patience! — Reply to this email directly, view it on GitHub <#3486 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AMEYQQCDGVI6XE5B7XSD74D3CUSG7AVCNFSM6AAAAAB6WUCREWVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNBQGY3DOMA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- Best, Gustavo Santos

[Ayush0054]

hey @gurezende could you please add the path for saving file like this tools=[FileTools(Path("tmp/file"))],

thanks 🙌

[gurezende]

Mine is the folder where the script is. "C:/Projects/agno-ai-labs" It actually saves the file, just the content is not in there. When I open it, it shows only the word "content". Em seg., 9 de jun. de 2025 às 15:11, Ayush ***@***.***> escreveu:

…

hey @gurezende <https://github.com/gurezende> could you please add the path for saving file like this tools=[FileTools(Path("tmp/file"))], thanks 🙌 — Reply to this email directly, view it on GitHub <#3486 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AMEYQQDGR4MPMWGQCV6KXLL3CXL5BAVCNFSM6AAAAAB6WUCREWVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTGNBRGMYDEOI> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- Best, Gustavo Santos