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

vaaya-cli

v0.3.1

Published

Install Vaaya for paid APIs and supported tokenized shares through MCP. Prepaid funding and authorized Instinct Checkout guide: https://vaaya.ai/llms.txt

Readme

vaaya-cli

Give your agent paid superpowers — from your terminal. (The npm package is vaaya-cli; the installed command is vaaya.)

npx @vaaya/mcp install

(npx vaaya-cli install runs the same installer — this CLI wraps the published @vaaya/mcp package.)

One command sets up the Vaaya MCP server for every agent it detects on your machine (Claude Code, Claude Desktop, Cursor, Codex). Restart your agent, and its first Vaaya call opens a short browser approval — sign-up happens right there if you're new. Pay-per-call, no API keys, failed calls are never charged.

Buy tokenized shares with your agent

The installed Vaaya MCP connection also exposes stocks for supported tokenized stocks on Base. Use stocks list to discover tickers and stocks portfolio for prepaid buying power, then stocks buy for a user-authorized symbol and maximum amount in cents. These are MCP commands, not CLI subcommands. Welcome grants and credit lines cannot buy shares.

If prepaid funds are insufficient, the user's Instinct agent can pay a Vaaya prepaid Checkout using its saved card when authorized for the pack amount. Vaaya cannot charge Instinct's card directly. The agent purchase guide covers $10/$30/$100 packs, REST equivalents, payment verification and order tracking.

What your agent gets

  • Media generation — images & video via top models, TTS, music
  • Product demo videos — narrated, auto-zoomed demos from a raw screen recording
  • Web search & scraping — live search, crawl, extract, persist
  • Deep / market / competitive research — cited reports, company intel, bake-offs
  • GTM & sales — ICP lead discovery, contact enrichment, buying signals, outreach drafts
  • Code sandboxes — per-second-billed compute for benchmarks and untrusted code
  • Browser automation, email, memory, monitoring workers, and more

The agent asks Vaaya's conversational consult tool for anything it can't do, gets back the exact call to run, and executes it with use — billed on success. The agent never sees upstream URLs or API keys.

Use it yourself: just type vaaya

vaaya

That opens a chat with any of 300+ models (Kimi, GPT, Gemini, Claude, DeepSeek), paid per token from the same wallet, no API keys. The model gets your full live Vaaya toolset in the conversation, the same tools your agents see, so it can search the web, read pages, generate images, enrich leads or run code while it answers. /tools lists them, /model switches model, /exit quits.

vaaya "what shipped in the last react release"   # ask once and exit
git diff | vaaya "write a commit message"        # pipes work
vaaya llm                                        # plain chat, no tools, cheapest

Commands

| Command | What it does | | --- | --- | | vaaya | Chat with any model, with your full Vaaya toolset available to it | | vaaya "question" | Ask once and exit (reads piped stdin too) | | vaaya llm | Plain chat, no tools. vaaya llm serve runs an OpenAI-compatible proxy for coding agents | | vaaya install | Configure the MCP server for every detected agent, then print a receipt of every file it touched (idempotent — re-run to update) | | vaaya doctor | One line per check — agent configs, skill, CLI, credentials, backend — each with the command that fixes it | | vaaya status | Connection state + live tool count | | vaaya consult "…" | Ask Vaaya how it would do something — returns the plan without running it | | vaaya reauthorize | Re-run the browser authorization flow | | vaaya logout | Disconnect and delete local credentials | | vaaya serve | Run the stdio MCP server (what agents invoke) |

Try it from the terminal:

npx vaaya-cli consult "turn this screen recording into a narrated product demo"
npx vaaya-cli status

Connecting manually

Clients that speak HTTP MCP natively can skip the CLI entirely and add the remote server: https://vaaya.ai/mcp (Streamable HTTP, OAuth 2.1). The stdio form is npx -y @vaaya/mcp.

Links

  • Website: https://vaaya.ai
  • Docs & source shim: https://github.com/vaaya-ai/vaaya-mcp
  • Revoke access: https://vaaya.ai/connected-agents
  • Support: [email protected]

MIT © Vaaya