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

@idriszade/a3-llm-personalization

v0.1.0

Published

Atom A3 — LLM personalization. Brand-voice grounded outbound message draft per prospect via OpenAI gpt-5.4-mini. Sprint 1 M1 GTM Engine v0.

Downloads

81

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Maintainers

mrzadexinhomrzadexinho

Keywords

atomgtmpersonalizationllmopenaipipeline-kit

Readme

A3 — LLM Personalization

Sprint 1 atom. Pipeline:

ProspectInput + brand-voice corpus (Supabase) → process-extract (OpenAI gpt-5.4-mini)
                                              → PersonalizedMessage (subject/body/cta + fixture provenance)

Tool surface

  • runA3(input, deps?) — imperative shell
  • createA3McpServe(deps?) — MCP-tool wrapper for marketplace exposure
  • fetchBrandVoiceFromSupabase() — reusable corpus reader

Cost moat

  • gpt-5.4-mini at ~$0.75/M input + $4.50/M output → ~$0.0015 per personalized draft
  • vs. $0.10-0.50/draft on legacy "AI personalization" SaaS (Lavender, Octopus, etc.)
  • 30-99% cost cut at production volume

Brand voice

Three sources, in priority order:

  1. Inline override (input.brandVoice) — highest precedence; for one-off campaigns
  2. Supabase corpus — table gtm_brand_voice_fixtures keyed on kind + optional segment
  3. Defaults (DEFAULT_BRAND_VOICE_FIXTURES) — cold-start safety net

Schema enforcement

Output runs through PersonalizedMessageSchema via process-extract's strict-JSON retry-on-fail loop (max 2 reattempts). Per feedback_pydantic_boundary_coercion.md: input fields use .catch() defaults to coerce-not-reject; output uses tight bounds (subject 1-120, body 20-2000) with retry to keep the model honest.

Dependencies

  • openai (peer-loaded by @idriszade/process-extract)
  • @idriszade/process-extract for provider-abstraction (OpenAI / Anthropic / Gemini interchangeable)
  • Supabase REST API (no SDK; native fetch)

License

MIT.