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

@neutron-build/agents

v0.1.0

Published

Neutron Agents. File-based agent authoring — agent.ts, instructions.md, tools/ — composing the AI SDK and Workflow SDK into durable agents.

Downloads

203

Readme

@neutron-build/agents

Neutron Agents. File-based agent authoring that composes the AI SDK (model calls) and the Workflow SDK (durability) into agents you can run anywhere — locally, behind an HTTP route, or inside a Teploy sandbox.

Conventions

my-agent/
└── agent/
    ├── agent.js          # export default defineAgent({ name, model, maxSteps })
    ├── instructions.md   # always-on system prompt
    ├── tools/            # one file per AI SDK tool() export
    ├── skills/           # procedures loaded on demand (SKILL.md + tools)
    └── schedules/        # { name, every: "1d", input } per file
import { loadAgent, runTurn, LocalExecutor } from "@neutron-build/agents";

const agent = await loadAgent("./agent");
const result = await runTurn(agent, {
  input: "fix the failing test",
  executor: new LocalExecutor({ root: "/workspace" }), // adds the exec tool
});

Approval-requiring tools suspend with the same resume shape as the rest of the stack (finishReason: "tool-approval" → pass messages + toolApprovals back).

Teams

The execution unit is a team of 1..N agents; solo is the one-member case. Policies are pure routing — C3 verification strategies plug in here:

import { defineTeam, pipeline, roundtrip, runTeamTurn } from "@neutron-build/agents";

const qa = defineTeam({
  name: "qa",
  members: { author, critic },
  policy: roundtrip({ from: "author", review: "critic", maxRounds: 3 }),
});
const result = await runTeamTurn(qa, { input: "draft the announcement" });

Durable runs

With @neutron-build/workflow installed (optional peer):

import { agentWorkflow, loadSchedules, isScheduleDue } from "@neutron-build/agents/durable";

const wf = agentWorkflow(agent, { executor });
// executeRun / Scheduler / deliverEvent from @neutron-build/workflow —
// approvals park the run for free, for as long as it takes.

Execution

Agents act on compute through one interface — AgentExecutor (exec/putFile/getFile/destroy):

  • LocalExecutor — child processes under a root dir (dev/test/trusted).
  • SandboxExecutor — client for the teploy-sandbox daemon (ephemeral containers; the client defines the wire contract both sides build to).

HTTP channel

import { createAgentHandler } from "@neutron-build/agents";
export const POST = createAgentHandler({ agent, executor }); // any mode:"api" route

Status

M1–M5 core complete: conventions loader, executor contract + LocalExecutor, solo runtime, teams (pipeline/roundtrip), skills (local, on-demand), durable runs + schedules, http channel, SandboxExecutor. Deferred: skills from the Teploy catalog and MCP servers (C1), non-http channels (Chat SDK territory), the reference starter example.