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
Package details
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
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:
- Open
chrome://inspect/#remote-debugging. - 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.