npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@parallel-web/pi-extension

v1.1.0

Published

Add web search and web fetch to your pi agent

Readme

@parallel-web/pi-extension

Pi extension that adds web_search and web_fetch backed by Parallel.

Install it with:

pi install npm:@parallel-web/pi-extension

What It Does

  • Registers web_search
  • Registers web_fetch
  • Adds a parallel-login command for browser auth
  • Stores the resulting Parallel API key in Pi's auth store

Auth resolution order:

  1. Stored Pi auth for provider key parallel
  2. PARALLEL_API_KEY

Dogfooding Locally

Build the extension first:

pnpm --filter @parallel-web/pi-extension build

Option 1: Load It Directly With pi -e

This is the fastest way to test a local checkout.

From the repo root:

pi --no-extensions --no-skills -e ./packages/pi-extension/dist/index.js

If the extension loads successfully, Pi will have:

  • the web_search tool
  • the web_fetch tool
  • the parallel-login command
  • per-session Parallel session_id reuse inside that Pi session

Option 2: Symlink It Into Pi Extensions

This is better if you want Pi to auto-discover it and support /reload.

First build it:

pnpm --filter @parallel-web/pi-extension build

Then symlink the package directory into Pi's global extensions folder:

mkdir -p ~/.pi/agent/extensions
ln -s \
  parallel-npm-packages/packages/pi-extension \
  ~/.pi/agent/extensions/parallel-pi-extension

Then start Pi normally:

pi

After code changes, rebuild and run /reload inside Pi:

pnpm --filter @parallel-web/pi-extension build

Local Auth Testing

Use Stored Pi Auth

Inside Pi, run:

/parallel-login

That opens the browser for Parallel OAuth. On success, the API key is stored in Pi auth under parallel.

Use Environment Variable Instead

export PARALLEL_API_KEY=your_key_here
pi --no-extensions --no-skills -e ./packages/pi-extension/dist/index.js

Note: stored Pi auth is preferred over PARALLEL_API_KEY if both exist.

Override The OAuth Platform URL

For local or staging OAuth testing, set PARALLEL_PLATFORM_URL before starting Pi:

export PARALLEL_PLATFORM_URL=https://your-platform-host
pi --no-extensions --no-skills -e ./packages/pi-extension/dist/index.js

This changes the browser login endpoints used by parallel-login and on-demand auth.

Quick Smoke Test

Once Pi is running with the extension loaded, ask something that should force web usage, for example:

Search the web for the latest Parallel docs on OAuth and summarize them.

Or ask Pi to call the tool explicitly.

web_search requires search_queries.

web_fetch accepts multiple URLs in a single call, so the agent can batch extraction work instead of parallelizing many single-URL requests.

Dev Loop

pnpm --filter @parallel-web/pi-extension build
pnpm --filter @parallel-web/pi-extension test
pnpm --filter @parallel-web/pi-extension typecheck

Notes

  • The extension uses the parallel-web TypeScript SDK directly.
  • Search requests use Parallel SDK basic mode.
  • Search requests include client_model when Pi has an active model selected.
  • Search and extract requests reuse a generated session_id for the life of the current Pi session.
  • The login flow tries to open your browser automatically.
  • If automatic callback capture does not complete, the extension falls back to asking you to paste the callback URL.
  • Skill suppression inside the extension is prompt-level only. If you want a clean dogfooding session without your usual skills list, start Pi with --no-skills.