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

anansi-ai

v0.1.0

Published

Agent-first visual storytelling installer for Anansi.

Readme

Anansi AI

The visual storytelling agent for Runway.

Anansi installs the agent skills, runtime profile templates, local workflow scripts, and starter schemas for an agent-first cinematic video workflow.

npx anansi-ai connect

If the npm package has not been published yet, install directly from GitHub:

npx github:teambrukhman1/anansi-ai connect

What Installs

  • Six Anansi skills:
    • anansi-brief
    • anansi-mood-weaver
    • anansi-story-weaver
    • anansi-scene-weaver
    • anansi-runway-render
    • anansi-final-cut
  • Obsidian helper skill family for local vault work.
  • Hermes profile templates for the anansi profile.
  • Local scripts for project state, brief PDFs, storyboard gates, keyframes, Runway payloads, Telegram media manifests, and HyperFrames final assembly.
  • Public-safe schemas, docs, and examples.

What Does Not Install

This public package does not include the team's private creative vault, the creative lead source notes, local style memory, client briefs, Runway logs, API keys, or generated project artifacts.

The installer stores only a local pointer to a local vault in:

~/.anansi/config.json

To point Anansi at a local vault:

anansi-ai config set vault "/absolute/path/to/your/Anansi"

Local Paths

After install, Anansi uses:

~/anansi/agent        agent files, scripts, profile templates
~/anansi/projects     generated project folders
~/.agents/skills      portable agent skills
~/.hermes/profiles/anansi
~/.anansi/config.json local config only

Runway Key

On macOS, store the Runway key in Keychain:

anansi-ai config set runway_key rw_xxx

Keys are never written into this repo or npm package.

Check Install

anansi-ai doctor

Publish To NPM

The package name anansi-ai is public-safe and intended for npm. To make the exact install command work:

npm login
npm publish --access public

The prepack guard runs before publish and fails if a key-looking value, raw the team/iCloud path, .env, local vault folder, or private client folder is present.

Workflow

Anansi is stage-isolated so it can survive long Telegram/Hermes runs without context overload:

Strategy Gate: Brief + Mood + Story
Previsualization Gate: Scene + storyboard + keyframes
Render Gate: Runway clips + HyperFrames/final cut
Learning: local vault/client memory updates

The private creative vault remains the retrieval and learning layer. The public package only teaches agents how to find and use that layer locally.