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

@caisson-sh/local-inference

v0.2.2

Published

Local-first inference seam: deterministic stub, guarded ONNX embeddings, and rented transport drivers sharing the local privacy gate.

Readme

@caisson-sh/local-inference

The Local-first edition's inference seam: one InferenceBackend port (embed / complete) with three implementations sharing it — a deterministic offline stub, a guarded on-device ONNX backend, and metered rented-backend transports (OpenRouter, Azure OpenAI, Bedrock) — all routed through the @caisson-sh/local-privacy egress gate. A base primitive (Apache-2.0).

What it gives you

  • One port, three backends. StubInferenceBackend is a pure, network-free function of its input text (SHA-256-seeded PRNG → unit-norm vector) — the only backend CI ever exercises. OnnxEmbeddingBackend runs a MiniLM-class on-device model via transformers.js, hash-verified and first-run-fetched through the egress guard. RentedInferenceBackend wraps a metered RentedTransport (createOpenRouterRentedTransport, createAzureOpenAIRentedTransport, createBedrockRentedTransport) behind the same port.
  • EMBEDDING_DIM is the locked contract. Every backend's embed() result is exactly this many floats — the width the shared @caisson-sh/local-store vec0 table is opened with; a mismatch throws at the store's dim-guard rather than silently padding or truncating.
  • Egress stays purpose-bound. Both the ONNX and rented backends route their outbound calls through a @caisson-sh/local-privacy EgressGuard, re-exported here so a consumer never needs a second import for the same policy.

Install

bun add @caisson-sh/local-inference

Use

import {
  StubInferenceBackend,
  EMBEDDING_DIM,
} from "@caisson-sh/local-inference";

// the deterministic, offline backend every CI test exercises — no model, no socket
const backend = new StubInferenceBackend({ dim: EMBEDDING_DIM });

const vector = await backend.embed("the quick brown fox"); // Float32Array, unit-norm
const { text } = await backend.complete({
  prompt: "summarize: fox jumps",
  maxTokens: 32,
});

Tests

bun test packages/local-inference/src — the stub is deterministic (same text ⇒ byte-identical vector) and rejects a non-positive dim; the rented transports are exercised against a fake RentedTransport/MeterSink, never a live model or a live network call.

License: Apache-2.0.