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

@tailored-ai/trusted-actions

v0.1.9

Published

Trusted-actions executor: approval gateway, push notifications, execution runner, Playwright adapters. HITL gateway for agent-driven purchases and other risky actions.

Readme

@tailored-ai/trusted-actions

A human-in-the-loop gateway for risky actions taken by an LLM agent — placing orders, submitting forms, sending money. Pairs with the @tailored-ai/core agent runtime but is independently usable.

The agent proposes an action via the request_action tool. The proposal lands in this service. A human approves it via a Web Push notification to their phone. Only then does a separate executor process — running inside Docker, with no access to the LLM — replay the approved steps through Playwright.

The LLM never sees credentials and never touches the browser directly.

npm install @tailored-ai/trusted-actions

Components

| Piece | What it does | |---|---| | Approval gateway (hono server) | REST + SSE for pending actions, approve/reject flow | | Push notifier (web-push) | VAPID web-push to approver's phone PWA | | Executor runner | Replays approved steps in a hermetic Docker container | | Playwright adapters | One per site — Amazon ships as the reference adapter | | PWA | Tiny SPA the approver installs on their phone | | tai-executor bin | CLI wrapper: serve, run, test-purchase, install-token |

Quick start

Setup is done from the monorepo root via shell helpers:

bash scripts/setup-tai-executor.sh             # one-time docker + .env
bash scripts/tai-executor-setup-amazon.sh      # headed Amazon login
bash scripts/tai-executor-tunnel-setup.sh      # Cloudflare Tunnel (HTTPS for push)
bash scripts/tai-executor-install-token.sh     # PWA install URL

Then in your agent config:

tools:
  request_action:
    enabled: true
    executor_url: https://your-executor.example.com

The agent calls request_action with a JSON intent; you get a push notification; you tap "Approve"; the executor runs.

PWA dashboard (optional)

The PWA can show TAI's pending decisions (capability proposals and in_review tasks) alongside the trusted-actions queue. Configure the executor with:

TAI_API_URL=http://127.0.0.1:3000     # TAI HTTP API base
TAI_API_TOKEN=<server.authToken>      # matches `server.authToken` in tai config

If either is unset, the PWA's Decisions card hides itself cleanly. See issue #121 for the phased PWA-as-dashboard plan.

Docs

License

MIT.