Open source · Cloudflare free tier

Web research that comes back as JSON

I've been running this as my Claygent-style agent inside and outside Clay. You send a prompt and a schema. Ferret searches the web, reads the pages, and returns actionable fields for your GTM motion.

ferret · live research loop
…
💬
ask ferret
You → Ferret
Ferret
On it. Searching the web.
prompt + schema → structured research
◈
developers.cloudflare.com/workers/platform/pricing
Docs / Workers / Platform / Pricing

Workers Pricing

Last reviewed · developers.cloudflare.com

Cloudflare Workers lets you run JavaScript at the edge with no servers to manage. Deploy code close to your users in milliseconds.

The Free plan includes 100,000 requests per day and is ideal for prototypes and side projects. No credit card required to start.

On the Workers Paid plan ($5/month), you get higher limits, longer CPU time, and access to Browser Rendering.

Billing is usage-based beyond the included allotment, so you only pay for what you use.

found
G
google.com/search
Workers Paid plan · Cloudflare
$5/month includes 10 million requests. Usage-based billing after that…
Cloudflare Workers pricing explained
How free tier and paid plan request limits work in practice…
✓
ferret · structured answer
Ferret

Cloudflare Workers pricing

researched from live web sources

Pricing model Free tier + usage-based paid
Free requests / day 100,000
Paid plan $5 / month

Built for people who already wire HTTP into workflows

the loop

It searches, opens pages, and only then answers

The model chooses queries and URLs. You get schema-checked JSON where numbers stay numbers and enums stay legal.

Swap LLM, SERP, or scraper

Each provider is one function. Point AGENT.md at your keys and keep the loop.

POST from Clay, n8n, Make, Codex…

If you can fire JSON over HTTP, you can run Ferret. No special platform required.

Spend free fetches first

Native edge fetch first, then Browser Rendering, then paid proxies only when the page fights back.

Cap the budget

MAX_FETCHES and a deadline kill a confused run before your HTTP client hangs.

Stay on one site

Pin research to a domain when third-party blogs would only add noise.

Dead URLs recover

A 404 stops the paid cascade. Ferret hunts the live page instead of burning credits.

Ship it free on your Cloudflare account

Clone the repo, have your coding agent wire your keys, then deploy. The free Workers tier is enough to start.

git clone https://github.com/edsmkt/Ferret.git && wrangler deploy
Open the repo