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

@fusionkit/ensemble

v0.10.1

Published

Harness-agnostic ensemble runner that emits model-fusion protocol records.

Readme

@fusionkit/ensemble

@fusionkit/ensemble contains two layers:

  • the legacy harness runner (runEnsemble) used by existing FusionKit harness flows;
  • the FusionKit runtime kernel (FusionRuntime) for typed operator graphs under schedulers.

Runtime kernel quick start

import {
  DirectFastPathScheduler,
  ModelGenerateOperator,
  createTaskArtifact,
  graph,
  refs
} from "@fusionkit/ensemble";

const task = createTaskArtifact({ id: "task", prompt: "Explain model fusion." });

const workflow = graph("direct")
  .task(task)
  .node(
    "model",
    new ModelGenerateOperator({
      model: "local",
      client: {
        generate: () => ({ model: "local", content: "Fusion combines model outputs under explicit policies." })
      }
    }),
    { inputs: [refs.artifact(task.id)] }
  )
  .scheduler(new DirectFastPathScheduler())
  .compile();

const result = await workflow.run();

Built-in workflows

Register and inspect the built-in graph recipes:

import { listWorkflows, registerBuiltInWorkflows } from "@fusionkit/ensemble";

registerBuiltInWorkflows();
console.log(listWorkflows());

Built-ins:

  • direct
  • panel-capture
  • panel-judge-synth
  • rank-fuse
  • execution-select-repair

Subpath imports

For focused imports:

import { FusionRuntime } from "@fusionkit/ensemble/runtime";
import { graph } from "@fusionkit/ensemble/kernel";
import { RankFuseScheduler } from "@fusionkit/ensemble/schedulers";
import { EvidenceSourceOperator } from "@fusionkit/ensemble/operators/evidence";

Runtime guarantees

  • Artifacts are immutable and typed.
  • Operators declare side effects and input/output artifact contracts.
  • Schedulers choose execution order; operators do not choose global control flow.
  • Private/contaminated evidence is recorded in outcomes but hidden from scheduler-visible state.
  • Outcome and replay records are emitted for future learned coordination.

More docs

  • docs/fusion/runtime-kernel.md — full architecture and API guide.
  • docs/fusion/runtime-recipes.md — copy-paste workflow recipes.
  • docs/fusion/MOA_IMPLEMENTATION_STATUS.md — implementation status against the design.
  • pnpm demo 15 — runnable runtime-kernel demo.