Open-source tools let AI agents search the web with lower cost
browser-search is an open-source set of tools that helps AI agents search and browse the web by themselves. such as OpenCode, Claude Code, and Cursor can handle code well, but web browsing can fail when sites block automation, rely heavily on JavaScript, or require paid APIs. The setup combines three tools through a skill: SearXNG for searching many s at once, Camofox for opening and controlling web pages through a ready-to-use browser, and for sites protected by systems such as Cloudflare, Akamai, or DataDome.
The agent chooses which tool to use without a person stepping in. It does not require API keys, , or paid search services. If Camofox gets blocked, the setup can switch to automatically.
Readability.js is used to pull out clean article text, with a claimed token saving of about 70%. The main SKILL.md file is plain text, so users can fork it and adapt it, and the project is available on GitHub under the MIT license.
Key points
- browser-search gives AI agents a self-hosted way to search and browse the web.
- It connects SearXNG, Camofox, and through a plain-text skill.
- It avoids paid search APIs, API keys, and .
- It can switch browsers automatically when a site blocks the normal browser path.
- Readability.js is used to extract cleaner article text and may cut token use by about 70%.