Give your AI agent Google Search without a paid SERP API. A real browser warms up your own proxy, searches like a person and returns SerpApi-style JSON. Captchas are reported, never passed off as empty results. MCP server, HTTP API and CLI. MIT.
An open-source harness that separates the causes of a scraping failure - exit IP, browser, TLS handshake, the machine you run it on, the target - by varying one at a time in the same hour. Every attempt is a JSONL row in the repo, and every table is generated from those rows.
Built by Nodemaven for developers who are working in scraping, browser automation, anti-bot systems and others related fields.
