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

@peron_js/oai2ant

v0.1.1

Published

Zero-dependency converters between the Anthropic Messages API and the OpenAI Chat Completions API.

Readme

oai2ant

Zero-dependency, pure-function converters between the Anthropic Messages API and the OpenAI Chat Completions API. It lets an Anthropic-Messages client talk to an OpenAI-compatible backend: translate the request to OpenAI, then translate the response (and stream) back to Anthropic.

  • antReqToOaiReq(req) — Anthropic request → OpenAI request
  • oaiResToAntRes(res) — OpenAI response → Anthropic message
  • oaiStreamToAntStream(chunks) — OpenAI chunk stream → Anthropic SSE events

Types come from the official @anthropic-ai/sdk and openai packages (dev dependencies only); the published code has no runtime dependencies. Non-standard fields used by OpenAI-compatible backends — reasoning_content/reasoning, chat_template_kwargs, defer_loading, tool_reference — are modeled by the OpenAI* types in src/types/openai.ts, which extend the official SDK types.

Usage

import { antReqToOaiReq, oaiResToAntRes, oaiStreamToAntStream } from "oai2ant";

// 1. Anthropic request -> OpenAI request, send to an OpenAI-compatible backend.
const oaiReq = antReqToOaiReq(anthropicRequest);

// 2. Non-streaming: OpenAI response -> Anthropic message.
const antRes = oaiResToAntRes(await openai.chat.completions.create(oaiReq));

// 3. Streaming: OpenAI chunks -> Anthropic SSE events.
const stream = await openai.chat.completions.create({ ...oaiReq, stream: true });
for await (const event of oaiStreamToAntStream(stream)) {
  // event is an Anthropic RawMessageStreamEvent: write it to your SSE response.
}

What it converts

  • Messages: system prompt, multi-turn text, images (base64 → data URI, url), tool calls (tool_usetool_calls), and tool results (tool_resulttool role messages).
  • Tools: definitions, tool_choice (incl. parallel-use toggle), and defer_loading / tool_reference for chat-template deferred tool loading.
  • Reasoning: thinking config → reasoning_effort, and thinking blocks ↔ reasoning_content/reasoning (with chat_template_kwargs thinking control).
  • Stop reasons, token usage, refusals, and the full streaming event lifecycle.

Development

bun install
bun test          # 100% coverage is enforced
bun run typecheck
bun run lint