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

@bendyline/gilde

v0.1.92

Published

The gilde catalog: model manifests, toolsets, craftbooks, roles, and project types for gezel.

Readme

gilde

The open catalog that powers gezel. Browse it rendered at gezelgilde.com, or use it as data:

npm install @bendyline/gilde

The package is raw JSON, Markdown, and implementations with no runtime dependencies. It includes the released data/, exported schemas, and the small authoring source trees consumers need to verify generated families against their inputs; repository tooling and CI files are not published.

What's inside

| Category | Path | What it is | | --- | --- | --- | | Craftbooks | data/craftbook-templates/ | Step-by-step task playbooks a gezel can follow, each with an eval sidecar (test.json) | | Chat models | data/chat-models/ | Local model manifests: engine sources (llama.cpp / MLX / ds4), pinned revisions and sha256s, tuning defaults | | Roles | data/gezel-templates/ | Gezel role templates — the about.md prose that gives a gezel its character | | Project types | data/project-types/ | Ready-made project scaffolds (mission, about, pages, embedded craftbooks) | | Image models | data/image-models/ | Image generation model manifests | | Connector types | data/connector-types/ | Connector definitions for external services | | Video models | data/video-models/ | Video generation model manifests | | Toolsets | data/toolsets/ | Hand-curated first-party toolsets | | Community toolsets | data/community/toolsets/ | Auto-imported from the MCP registry, permissive licenses only, filtered by tools/lib/community-policy.mjs — bot-managed, unreviewed | | Authoring sources | authoring/ | Reproducible source material for generated catalog families; inert at runtime |

Every item follows the same layout:

data/<category>/<shard>/<id>/manifest.json          identity: name, description, tags, license
data/<category>/<shard>/<id>/versions/<semver>/...  released content, never mutated after release
data/<category>/raw-index.json                      generated listing: item files verbatim (do not hand-edit)
data/<category>/index.json                          generated legacy listing for older gezel builds

where <shard> is the first two characters of the id.

Chat-model introductions are Gilde-only: add an authoring recipe under authoring/chat-models/, run npm run build-chat-model, and commit the new identity, version payload, and regenerated index. See authoring/chat-models/README.md for the recipe contract.

Contributing

New craftbooks, model updates, roles — contributions are welcome, from

humans and their AI agents alike. Start with

CONTRIBUTING.md; if you are an AI agent,

AGENTS.md is the contract written for you.

Every PR is validated by CI. Run the same checks locally:

npm run check         runs all validation checks below
npm run validate      structural + schema validation of the whole tree
npm run check-index   verifies the generated index files are fresh
npm run lint-models   completeness lint for chat-model manifests
npm run fix           rewrites non-canonical JSON and regenerates the indexes
                      (check never writes — run fix, then re-run check)

Validation is dependency-light on purpose: plain Node 24 plus ajv,

against the JSON Schemas in schemas/ (generated from gezel's

canonical Zod schemas — do not edit them here).

Try the project pages locally

Run the standalone page gallery from the repository root:

npm run demos

Then open http://127.0.0.1:4173/. The home page links to every latest project-type web experience. Each page recognizes that it is outside Gezel, uses local sample data, and can be reset by reloading. To choose a different address:

npm run demos -- --host 127.0.0.1 --port 8080

Licensing

The catalog structure and tooling are MIT. Each model entry carries its

own upstream license field — check it before you ship a model. Community

toolset entries are filtered to permissive licenses at import time.