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

@agentium/edge

v2.6.0

Published

Edge deployment for Agentium — IoT toolkits (GPIO, sensors, camera, BLE), edge runtime, and Ollama helpers for Raspberry Pi

Readme

@agentium/edge

Edge deployment for Agentium — IoT toolkits (GPIO, sensors, camera, BLE, servo, system) plus an edge runtime with resource monitoring, presets, and Ollama helpers. Designed for Raspberry Pi but works on any Linux SBC.

Install

npm install @agentium/edge

Hardware toolkits load their native bindings on demand. Install only what you use, e.g.:

npm install onoff           # GPIO
npm install i2c-bus         # sensors
npm install @abandonware/noble  # BLE

Quick Start — Ollama-backed local agent on a Pi

import { Agent } from "@agentium/core";
import { EdgeRuntime, edgePreset, ollama } from "@agentium/edge";

const runtime = new EdgeRuntime(edgePreset("pi-5-balanced"));
await runtime.start();

const agent = new Agent({
  name: "edge-bot",
  model: ollama(runtime.recommendedModel),
  instructions: "You are an edge AI assistant running on-device.",
});

console.log(await agent.run("hello"));

IoT Toolkits

Each toolkit exposes typed tools (with Zod schemas) the agent can call:

| Toolkit | Example tools | |---------|---------------| | GpioToolkit | gpio.write, gpio.read, gpio.toggle | | SensorToolkit | sensor.read_temperature, sensor.read_humidity (I²C / 1-Wire) | | CameraToolkit | camera.snapshot, camera.start_stream | | BleToolkit | ble.scan, ble.connect, ble.read_characteristic | | ServoToolkit | servo.move_to, servo.center | | SystemToolkit | system.cpu_temp, system.uptime, system.shutdown |

import { Agent } from "@agentium/core";
import { GpioToolkit, SensorToolkit } from "@agentium/edge";

const agent = new Agent({
  name: "garden-bot",
  model: ollama("llama3.2:3b"),
  toolkits: [
    new GpioToolkit({ pumpPin: 17 }),
    new SensorToolkit({ moistureBus: 1 }),
  ],
});

await agent.run("Water the plants if soil moisture is below 30%.");

Edge Runtime

EdgeRuntime continuously monitors CPU, RAM, temperature, and storage so you can react to resource pressure (downsize the model, defer non-critical tools, sync to cloud, etc.).

const runtime = new EdgeRuntime(edgePreset("pi-zero-2-low-power"));
runtime.on("threshold:cpu", (s) => console.warn("CPU pressure", s));
await runtime.start();

Cloud Sync

EdgeCloudSync ships local agent runs / sensor logs to a central endpoint with offline queueing — useful for fleets of Pis with intermittent connectivity.

Documentation

Full docs at docs.agentium.in

Community

Join the conversation on Discord.

License

MIT