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

llmprobe

v0.1.1

Published

Compliance test runner for LLM API endpoints (OpenAI Responses, Chat Completions, Anthropic Messages).

Readme

Responses / Chat / Messages Validator

Compliance test suites for three LLM API surfaces, each runnable independently:

  • OpenAI Responses — Open Responses spec (forked upstream): POST /responses
  • OpenAI Chat CompletionsPOST /chat/completions
  • Anthropic MessagesPOST /v1/messages

Each suite ships its own OpenAPI schema, Zod validators, streaming parser, and test templates. Point any of them at any compliant backend and get pass/fail results.

This repo is a fork of openresponses/openresponses extended into a multi-spec hub.

What's in this repo

  • Specs (source): schema/{responses,chat-completions,anthropic-messages}/openapi.json
  • Generated Zod schemas: src/generated/kubb/{responses,chat-completions,anthropic-messages}/zod/
  • Compliance suites: src/lib/compliance/{responses,chat-completions,anthropic-messages}/
  • Generic runner core: src/lib/compliance/core/
  • CLI source: bin/compliance-test.ts
  • Bundled CLI (built artifact): bin/dist/llmprobe.mjs

Compliance testing

Published as the llmprobe CLI. The first positional arg is the base URL — bare hosts like localhost:1234 are auto-prefixed with http:// — and --spec selects a single suite (omit for auto-probe across all three).

Quick start with npx

# Auto-probe every supported spec at a local endpoint (no install needed)
npx llmprobe localhost:11434/v1                                  # Ollama
npx llmprobe localhost:1234/v1                                   # LM Studio
npx llmprobe https://api.openai.com/v1 -k $OPENAI_API_KEY

Single-spec runs

npx llmprobe --spec responses -k $OPENAI_API_KEY
npx llmprobe --spec chat-completions https://api.openai.com/v1 -k $OPENAI_API_KEY
# Anthropic Messages: auto-applies x-api-key auth and anthropic-version: 2023-06-01
npx llmprobe --spec anthropic-messages -k $ANTHROPIC_API_KEY

Filter or get help

npx llmprobe --spec chat-completions --filter basic-completion,streaming-completion
npx llmprobe --help

Local development

The bun run test:compliance* scripts still run the TypeScript source directly without a build step:

bun run test:compliance:responses --base-url http://localhost:8000/v1 --api-key $API_KEY
bun run test:compliance:chat --base-url https://api.openai.com/v1 --api-key $OPENAI_API_KEY
bun run test:compliance:anthropic --base-url https://api.anthropic.com --api-key $ANTHROPIC_API_KEY

Build the bundled CLI locally with bun run build:cli (output: bin/dist/llmprobe.mjs).

Adding a new spec

Each suite is a SpecSuite<TReq, TRes, TStreamCtx> (see src/lib/compliance/core/types.ts). To add a fourth surface:

  1. Drop an OpenAPI document at schema/<spec-id>/openapi.json and generate Zod schemas under src/generated/kubb/<spec-id>/zod/ (kubb config is no longer in this repo; regenerate using your tool of choice or hand-author the schemas you need).
  2. Implement src/lib/compliance/<spec-id>/{suite.ts,templates.ts,sse-events.ts,validators.ts} and export a SpecSuite.
  3. Register it in the specs map in bin/compliance-test.ts.