pi-chrome-search

Free, keyless web search through the user's own visible Chrome (Google, DuckDuckGo, Yandex, and opt-in Avito/Ozon listings) for pi

Packages

Package details

extension

Install pi-chrome-search from npm and Pi will load the resources declared by the package manifest.

$ pi install npm:pi-chrome-search
Package
pi-chrome-search
Version
2.2.1
Published
Nov 14, 2026
Downloads
522/mo · 522/wk
Author
sh2nk
License
MIT
Types
extension
Size
954.2 KB
Dependencies
1 dependency · 2 peers
Pi manifest JSON
{
  "extensions": [
    "./index.ts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

pi-chrome-search

npm downloads pi ci license node

Web search and page reading for pi, through your own visible Chrome. Same profile, cookies and IP. Google, DuckDuckGo and Yandex return compact Markdown and their native AI summary when there is one; Avito listings (price, location, age) and Ozon goods (price, rating) are available opt-in. No keys, no paid APIs, no headless mode, no fingerprint spoofing. Node 26+, Chrome 136+.

Install

pi install npm:pi-chrome-search

Chrome 136+ enables debugging only after an explicit click:

  1. Open chrome://inspect/#remote-debugging.
  2. Tick Discover network targets, then click Allow.

The window stays visible. The extension attaches to it and never launches, restarts or closes Chrome.

Tools

web_search and web_read are direct. The other three sit behind tool_search.

Tool Exposure Arguments
web_search direct q string; n? integer 1..10; engines? "auto" or ("google" or "duckduckgo" or "yandex" or "avito" or "ozon") or list of ("google" or "duckduckgo" or "yandex" or "avito" or "ozon") 1..5; summary? boolean; page? integer >=1; format? "md" or "json"
web_read direct url string; offset? integer >=0; maxChars? integer >=1; format? "md" or "text"
image_search deferred q string; n? integer 1..12; engine? "google" or "yandex"; attach? boolean or "bytes"
web_research deferred q string; budget? "quick" or "normal" or "deep"
web_doctor deferred probe? boolean; fix? boolean

A call has one 60 second deadline. DuckDuckGo has no pagination: page > 1 is reported as ignored.page; neither marketplace has an AI block, so summary is reported as ignored.summary. Every unresolved link stays marked unresolved, and card facts (price/availability/rating/location) render on their own line after the snippet.

engines: "auto" only ever means Google → DuckDuckGo → Yandex. Avito and Ozon are special engines: off by default and reachable only by naming them. To turn one on, set engines.avito.enabled or engines.ozon.enabled to true (Avito also takes engines.avito.location, a region slug such as kaluga or all) in ~/.pi/agent/web-search.json — ask your agent to do it, that is the intended path.

Limits

No headless browsing, automation profile, captcha solving, proxy rotation, cookie export, telemetry or paid search API. Google and Yandex forbid automated access in their terms. If a captcha appears, solve it in the window or stop.

Failures

Every failure is an E_* code with a stage, a retry flag and a hint you can act on. The full table is in errors.md. Start with /web-doctor or node src/cli/doctor.ts --json.

Config reference: config.md.

MIT.