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

@veyorhq/anthropic

v0.2.0

Published

Anthropic API and Claude Code CLI workers for Veyor actors.

Readme

@veyorhq/anthropic

@veyorhq/anthropic provides Anthropic-backed implementations for Veyor actors.

It exposes two separate adapters:

  • @veyorhq/anthropic/anthropic creates an Effect AI model layer for @veyorhq/ai-effect.
  • @veyorhq/anthropic/claude runs a Veyor actor through the local Claude Code CLI in headless mode.

[!IMPORTANT] This package is under active development. It is private, remains at 0.0.0, and is not published to a package registry.

Anthropic API

Use anthropic(model) with agent(...) when the actor should call the Anthropic API through Effect AI.

import { agent } from "@veyorhq/ai-effect";
import { anthropic } from "@veyorhq/anthropic/anthropic";
import { Writer } from "./actors.js";

const WriterImpl = agent(Writer, anthropic("claude-opus-5"), {
  prompt: "Return a concise implementation plan.",
});

The adapter reads ANTHROPIC_API_KEY through Effect Config. Missing or invalid configuration fails when the model layer is used.

Claude Code CLI

Use claude(actor, model, options) when a Claude Code session should implement the actor. The adapter drives the CLI's supported headless mode (claude --print) with your own local authentication, passes the actor's output contract via --json-schema, and validates the structured result.

import { claude } from "@veyorhq/anthropic/claude";
import { Reviewer } from "./actors.js";

const ReviewerImpl = claude(Reviewer, "claude-opus-5", {
  effort: "high",
  cwd: process.cwd(),
  permissionMode: "dontAsk",
  instructions: "Review the assignment against its acceptance criteria.",
});

Options map onto CLI flags: effort, instructions (--append-system-prompt), permissionMode, allowedTools/disallowedTools, maxBudgetUsd, and cwd. Sessions run with --no-session-persistence; each invocation is a fresh, single-shot worker.

When several actors share the same model, effort, and permission mode, capture that once with claude.preset(...) instead of repeating it per actor:

import { claude } from "@veyorhq/anthropic/claude";
import { Reviewer } from "./actors.js";

const reviewWorker = claude.preset({
  model: "claude-opus-5",
  effort: "high",
  permissionMode: "dontAsk",
});

const ReviewerImpl = reviewWorker(Reviewer, {
  instructions: "Review the assignment against its acceptance criteria.",
});

claude.preset is sugar over claude — per-call options (including model) shallow-merge over the preset, with the per-call value winning.