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

@klevox-context/sdk

v0.1.0

Published

Public TypeScript SDK for Klevox Context / OmniGraph — retrieval and memory for AI agents.

Readme

@klevox-context/sdk

The official TypeScript SDK for Klevox Context — retrieval and memory primitives for AI agents.

Install

npm i @klevox-context/sdk

Get an API key

  1. Sign up at https://context.klevox.com.
  2. Create a project. The project ID appears in the URL: https://context.klevox.com/projects/<project-id>.
  3. Generate an API key under Settings → API Keys. Treat it like a password — store it in KLEVOX_API_KEY env var, never check it into source.

Quickstart

import { Klevox } from "@klevox-context/sdk";

const kx = new Klevox({ apiKey: process.env.KLEVOX_API_KEY });
const p = kx.project(process.env.KLEVOX_PROJECT_ID!);

// userId is required: it scopes per-user memory and access policies
// the server uses to filter retrieval results (omitting it returns 422).
const result = await p.retrieve({
  query: "what did we decide about pricing tiers?",
  userId: process.env.KLEVOX_USER_ID ?? "demo-user",
});
for (const c of result.chunks) {
  console.log(c.score.toFixed(2), c.source, c.text.slice(0, 200));
}

Sample output:

0.87  vector   We standardized on three tiers: Free, Pro …
0.81  episode  Q4 review confirmed Pro tier conversion …
0.74  memory   Pricing changes require finance approval …

result.chunks is an array of RetrievalChunk objects with id (use it to deduplicate or build citations), text, score, source (one of "vector", "graph", "memory", "episode", "fused"), documentId, episodeId, provenanceIds (audit-trail IDs that link the chunk back to the originating events — useful for citations and recall debugging), and metadata. See src/types/retrieve.ts for the full shape.

v1 limitation: topK, tools, metadata, and additionalProjectIds are accepted on the SDK type for forward compatibility but the v1 server applies its own defaults — these options have no effect until v0.2.

Adapters

// LangChain.js
import { KlevoxRetriever, KlevoxMemory } from "@klevox-context/sdk/langchain";

// LlamaIndex.TS
import { KlevoxRetriever } from "@klevox-context/sdk/llamaindex";

// Vercel AI SDK
import { tools } from "@klevox-context/sdk/ai-sdk";

CLI

npx klevox login
npx klevox retrieve "pricing tiers" --project=$KLEVOX_PROJECT_ID
npx klevox ingest ./handbook.pdf --project=$KLEVOX_PROJECT_ID --tags=hr,public --wait

Errors

The SDK throws a KlevoxError hierarchy. Each subtype tells you whether to retry, whether the SDK already retried, and (where applicable) carries an upgradeUrl. See docs/errors.md.

Migrating from Graphiti / Zep / Mem0

See docs/migration-from-graphiti-zep-mem0.md for a side-by-side mapping of the most common operations.

Runtime support

  • Node.js >= 20, Bun, Deno — full support.
  • Edge runtimes (Cloudflare Workers, Vercel Edge) — supported, but p.documents.add({ source: { kind: "file", path } }) is Node-only because it uses node:fs/promises. Use kind: "buffer" or kind: "blob" (browser File/Blob) on Edge.

License

Apache-2.0