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

taguru

v0.9.6

Published

TypeScript/JavaScript client SDK for the Taguru long-term semantic memory server

Readme

taguru (TypeScript/JavaScript SDK)

Official TypeScript/JavaScript client SDK for the Taguru long-term semantic memory server. The Python SDK (taguru on PyPI) exposes the identical surface — method names differ only by casing convention (searchPassagessearch_passages); data fields are the wire's own snake_case in both. Zero runtime dependencies (built-in fetch), Node 20+.

npm install taguru
import { Taguru } from "taguru";

const client = new Taguru(); // defaults: $TAGURU_URL / $TAGURU_API_TOKEN, else http://127.0.0.1:8248
await client.contexts.create("sake", { description: "青嶺酒造という架空の酒蔵の知識" });

const ctx = client.context("sake");
await ctx.addAssociations([
  { subject: "青嶺酒造", label: "代表銘柄", object: "青嶺", weight: 1.0, source: "docs/aomine.md" },
]);
await ctx.storePassages({ "docs/aomine.md": "青嶺酒造は1907年創業。代表銘柄は「青嶺」。" });

const result = await ctx.retrieve("青嶺酒造");            // resolve → describe → activate → citations
const hits = await ctx.searchPassages("1907年に創業した"); // text lane (phrase as an answer)
const pkg = await ctx.assembleEvidence("青嶺酒造", { budget: { max_items: 10 } }); // server-side budgeted package

Prefer one addAssociations call per document. Above the 10,000-association request limit, addAssociationsBatched auto-chunks it; for corpus-scale ingestion, use POST /import or taguru import. Each call pays for a full durable write.

The behavioral contract is the server's own protocol document — read it from the deployment you target: await client.protocol() (GET /protocol).

taguru/testing (Node-only) spawns a real server binary for integration tests — the twin of Python's taguru.testing.

Tracing

retrieve() composes a client-side loop the same way the server's own retrieve MCP tool does — resolve → describe → query → activate → citations → passage fallback. Optionally trace it as one OpenTelemetry span tree, taguru.retrieve with a child span per phase, joined to the server's own request span through injected traceparent/tracestate headers:

npm install @opentelemetry/api  # optional peer dependency — core install stays dependency-free otherwise
import { trace } from "@opentelemetry/api";
// wire up whichever OpenTelemetry SDK/exporter you use — this package just emits spans into it

With no TracerProvider configured (or @opentelemetry/api not installed at all), every tracing call in the SDK is a silent no-op — nothing about retrieve()'s behavior or return value changes either way; the package is loaded through a lazily cached dynamic import(), never a static one, so a plain npm install taguru never even attempts to resolve it. See Tracing for the full span tree, the attribute/event vocabulary (shared with the Python SDK via sdk/spec/tracing.yaml), and the privacy rules (spans carry counts, flags, and closed reason codes — never cue text, labels, or passage content).

See the repository's sdk/ directory for the full documentation, the LangChain integration (langchain-taguru), and the cross-language surface spec.