`@fujocoded/astro-atproto-loader`

ATproto records meet Astro content collections. Quick & Easy™

Important

This package handles reads only. If you also want to write data (like posting to Bluesky as a logged-in user), start from @fujocoded/authproto.

What is `@fujocoded/astro-atproto-loader`?

@fujocoded/astro-atproto-loader pulls records from any public AtProto PDS (that is, your repository of AtProto data) straight into your Astro content collections. Point it at a user handle (e.g. boba-tan.bsky.social) or their DID (e.g. did:plc:abc123), tell it which kind of record to read (e.g. app.bsky.feed.post), and use the data on your Astro site like you would with any content collection!

Under the hood, @fujocoded/astro-atproto-loader:

Resolves a handle to its DID (when needed)
Resolves that DID or handle to the user's PDS
Reads records with com.atproto.repo.listRecords and getRecord
Keeps a short in-memory cache for live collections and refreshes it in the background when a request comes in (stale-while-revalidate)

What's included in `@fujocoded/astro-atproto-loader`?

In this package, you'll find:

defineAtProtoLiveCollection(), which reads public AtProto records at request time. Use it where you'd otherwise call Astro's defineLiveCollection()
defineAtProtoCollection(), which reads public AtProto records at build time. Use it where you'd otherwise call Astro's defineCollection()
toHostedBlob() and isAtBlob(), helpers for turning a record's blob ref (a profile avatar, a sprite sheet, a stream thumbnail) into a URL you can drop into <img src>. Use them inside transform

Warning

If you're generating your site as static HTML pages (for example for Neocities), you must use the static collection loader.

What can you do with `@fujocoded/astro-atproto-loader`?

Pull in content from the wider AtProto network, including Bluesky posts, Streamplace VODs, RPG Actor characters, AtProto badges, and anything else stored in a public repo (a user's per-protocol record store). For example, you can:
- Pin your favorite Bluesky posts or artist reposts on your homepage
- Embed your Streamplace VODs next to the articles they inspired
- Show off the cons you've been badged at, straight from your badge records
Show records from multiple repos in one Astro collection:
- A list of recent posts both you and your friends liked
- Profiles of your community members
- ...and many creative uses!
Hydrate linked records like strongRefs and subject URIs from inside your transform, so a post's quoted record or a label's subject is already resolved by the time your page renders
Display blob-backed media like profile avatars, sprite sheets, or stream thumbnails by handing the blob ref to toHostedBlob() inside transform

Tip

These utilities should be used when reading one repo, or merging a small handful of them. If you find yourself grouping hundreds of records across dozens of repos on every request, you probably want an AppView/server that emits the pre-aggregated payload, instead of a loader that hits N PDSs each time.

Setup

Before you start, you'll need:

Astro 5.13 or later
An Astro project using the Content Loader API
A public AtProto repo and collection NSID (like com.fujocoded.rolodex.card) to read from

Run the following command:

npm add @fujocoded/astro-atproto-loader@latest

Caution

0.2.0 is broken. Upgrade to 0.2.1 or later.

If you're stuck on 0.2.0, the correct code requires wrapping the call in "defineCollection":

import { defineCollection, z } from "astro:content";
import { defineAtProtoCollection } from "@fujocoded/astro-atproto-loader";

const sprites = defineCollection(
  defineAtProtoCollection({
    source: { repo: "bmann.ca", collection: "actor.rpg.sprite" },
    outputSchema: z.any(),
  }),
);

Define a static collection (for build time magic)...

// src/content.config.ts
import { z } from "astro:content";
import { defineAtProtoCollection } from "@fujocoded/astro-atproto-loader";

const documents = defineAtProtoCollection({
  source: {
    repo: "bobatan.fujocoded.dev",
    collection: "site.standard.document",
  },
  outputSchema: z.object({
    title: z.string(),
  }),
});

export const collections = { documents };

...or a live collection to fetch (almost) every time!

// src/live.config.ts
import { z } from "astro:content";
import { defineAtProtoLiveCollection } from "@fujocoded/astro-atproto-loader";

const contacts = defineAtProtoLiveCollection({
  source: {
    repo: "did:plc:example1234",
    collection: "com.fujocoded.rolodex.card",
  },
  outputSchema: z.object({
    username: z.string(),
  }),
});

export const collections = { contacts };

Okay how do I actually do stuff with this?

Check out the example sites included under the examples folder.

You can start with any of these:

01-static-loaders for defineAtProtoCollection(), which fetches the data once when your site builds (won't update live)
02-live-loaders for defineAtProtoLiveCollection(), which fetches your data at each request (updates live)
03-grouped-reposts for reading from multiple repos at once with sources: [...] and merging records with groupBy
04-single-entry for fetching one record by rkey with getEntry() and getLiveEntry(), and turning the record's blob into a URL with toHostedBlob()

The first two examples show off two patterns:

Passing records through directly and letting Zod validate and transform them
Reshaping records with a transform

The third one shows reading the same collection from three different repos, grouping records by a shared URI, and hydrating linked records via fetchRecord.

Configuring the loaders

Both loaders share the same options...mostly.

Shared options

Each source (or each entry in sources: [...]) accepts:

repo, required. A DID or a handle
collection, required. The AtProto collection NSID to load
parseRecord, optional. A function that runs once per record before filter, so you can validate the record's shape. When it throws, that single record is dropped with a warning.
limit, optional. Cap on how many records to load from this source.
maxPages, optional. Hard cap on the number of listRecords pages that get fetched, regardless of limit

Use source: {...} to read from a single repo, or sources: [...] to merge a handful of repos or collections into one Astro collection.

About limits

`limit`	What you get	Default `maxPages`
(omitted)	One page, up to 100 records, no cursor walk	`1`
`number` (e.g. 5)	Stop at that count, page size `min(limit, 100)`	`1`
`'all'`	Walk every cursor, 100 records per page	`Infinity`

Records rejected by filter do not count toward limit, but maxPages always caps the raw pagination (so a stray filter: () => false can't make the loader walk forever).

If you want to read every record from a source (just make sure it's only a few):

source: {
  repo: "did:plc:example1234",
  collection: "com.fujocoded.rolodex.card",
  limit: "all",
}

`parseRecord` vs `transform`

parseRecord and transform are two different jobs:

parseRecord lives on the source. It checks that a raw record has the shape you expect, and returns the typed value. It doesn't see repo, rkey, uri, or fetchRecord, because at that stage it's just answering "is this record well-formed?".
transform receives the full per-record context plus fetchRecord, and returns your Astro entry. This is where you do the work: resolving AtUris, combining a post with its embed, mapping records to your own display model. Return null or undefined to drop an entry silently

Putting them together:

import { $parse, lexicons } from "@atproto/lex";

defineAtProtoLiveCollection({
  source: {
    repo: "did:plc:example1234",
    collection: "app.bsky.feed.post",
    parseRecord: (value) => $parse(lexicons, "app.bsky.feed.post", value), // schema gate
  },
  transform: async ({ value, uri, fetchRecord }) => {
    // value is already the parsed lexicon type
    const quoted =
      value.embed?.$type === "app.bsky.embed.record"
        ? (await fetchRecord({ atUri: value.embed.record.uri }))?.value
        : null;
    return { id: uri, data: { text: value.text, quoted } };
  },
  outputSchema: z.object({ text: z.string(), quoted: z.unknown().nullable() }),
});

`fetchRecord`: hydrating records by AT-URI

Every filter and transform callback receives fetchRecord({ atUri, parse? }), which fetches a single record from any public PDS by its AtUri (the at://... address that uniquely identifies a record on the network). When more than one callback asks for the same URI in the same cycle (for example a subject URI shared across many records), they share a single network call.

A successful call resolves to { value, repo }. value is the record body (or whatever your parse callback returned). repo is the fetched record's owning DID and PDS, already resolved. So you can hand it straight to toHostedBlob({ repo, blob }) for any blob inside that hydrated record without re-resolving identity.

import { $parse, lexicons } from "@atproto/lex";

transform: async ({ value, uri, fetchRecord }) => {
  const result = await fetchRecord({
    atUri: value.subject.uri,
    parse: (v) => $parse(lexicons, "app.bsky.actor.profile", v),
  });
  if (!result) return null; // record was missing, unparseable, or unreachable
  return { id: uri, data: { label: value.val, subject: result.value } };
};

fetchRecord returns null for every failure mode: a malformed AT-URI, a PDS that can't be reached, a 404, a record whose value isn't an object, or a parse callback that threw. Each of these logs a distinct warning to your console, so when something is missing you can tell which thing went wrong.

Blob helpers: turning record blobs (and images) into URLs

When looking to display images or other files associated with records, you won't (unfortunately) find a simple address you can drop into <img src>: AtProto records don't store this content themselves, but instead only hold a "pointer" (called a blob ref) to the actual file on a user PDS.

To show that profile avatar, sprite sheet, or video thumbnail on your page, we must turn the pointer into a real URL the browser can load. That's what toHostedBlob() is for.

toHostedBlob() needs 2 things:

the blobref itself
the repo that owns the file, that is the DID + PDS url wher the record is hosted

For records you own, repo will likely out of args.repo. While for records you've hydrated via fetchRecord, use the repo field on the result.

import {
  defineAtProtoLiveCollection,
  isAtBlob,
  toHostedBlob,
} from "@fujocoded/astro-atproto-loader";

defineAtProtoLiveCollection({
  source: { repo: "boba-tan.bsky.social", collection: "actor.rpg.sprite" },
  outputSchema: z.object({
    spriteSheet: z.object({
      url: z.url(),
      mimeType: z.string(),
      size: z.number(),
    }),
  }),
  transform: ({ repo, rkey, value }) => {
    const v = value as { spriteSheet: unknown };
    if (!isAtBlob(v.spriteSheet)) return undefined;
    return {
      id: rkey,
      data: { spriteSheet: toHostedBlob({ repo, blob: v.spriteSheet }) },
    };
  },
});

You can find a working example at __examples__/04-single-entry.

Multi-source reads and `onSourceError`

When you're reading from sources: [...], onSourceError decides what happens if one of those sources fails (PDS is down, repo is gone, and so on). Use "skip" to warn and drop that source's contribution, or "throw" to fail the load:

defineAtProtoLiveCollection({
  sources: [
    { repo: "fujocoded.bsky.social", collection: "app.bsky.feed.post" },
    { repo: "fujoweb.dev", collection: "app.bsky.feed.post" }, // offline
    { repo: "bobaboard.bsky.social", collection: "app.bsky.feed.post" },
  ],
  onSourceError: "skip",
  outputSchema: z.object({ text: z.string() }),
});

The defaults are picked so each loader behaves sensibly out of the box:

Live loader: sources: [...] defaults to "skip" so one flaky PDS doesn't take down your whole live collection. source: {...} defaults to "throw", because there's no alternate source to fall back to
Static loader: defaults to "throw" everywhere, so a broken source fails the build instead of quietly publishing partial content. Pass onSourceError: "skip" if you'd rather ship the rest of the data anyway

You can also pass a function to decide case-by-case:

onSourceError: (error, source) =>
  source.repo === "critical.test" ? "throw" : "skip",

Note

When onSourceError is "throw", the first source error fails the whole load right away. When you're skipping errors and every source ends up failing, the pipeline throws an AggregateError so the failure isn't swallowed silently. In a live loader, the cache holds onto its last good snapshot when a refresh throws, so a transient outage won't blank out your page.

`groupBy`: merging records from multiple sources

When you're reading from sources: [...], you can group records together before transform runs. Every record gets handed to groupBy, which returns a string key. Records that share a key are passed to a single transform call as a group, in sources[] declaration order.

For example, here's how you'd find Bluesky posts that all three FujoCoded accounts reposted, by reading each account's app.bsky.feed.repost collection and grouping by the URI of the post being reposted:

defineAtProtoLiveCollection({
  sources: [
    { repo: "fujocoded.bsky.social", collection: "app.bsky.feed.repost" },
    { repo: "fujoweb.dev", collection: "app.bsky.feed.repost" },
    { repo: "bobaboard.bsky.social", collection: "app.bsky.feed.repost" },
  ],
  groupBy: ({ value }) => value.subject.uri,
  transform: async ({ key, records, fetchRecord }) => {
    if (records.length < 3) return null; // only keep posts all three reposted
    const post = await fetchRecord({ atUri: key as AtUriString });
    if (!post) return null;

    return {
      id: key,
      data: {
        post,
        repostedBy: records.map((record) => record.repo.did),
      },
    };
  },
  outputSchema: z.object({
    post: z.unknown(),
    repostedBy: z.array(z.string()),
  }),
});

A working version of this lives at __examples__/03-grouped-reposts.

Use filter to drop records before they reach groupBy, or return a unique key like uri for records that shouldn't merge with anything else.

Default transforms

When the loader is configured with exactly one source and no transform, it defaults to:

({ value, rkey }) => ({ id: rkey, data: value });

When more than one source is configured and no transform is provided, the id is namespaced by repo.did, collection, and rkey so records sharing an rkey across repos or collections don't collide:

({ value, repo, collection, rkey }) => ({
  id: `${repo.did}/${collection}/${rkey}`,
  data: value,
});

The latter is exported as toNamespacedEntry if you'd like to compose it yourself.

Live-only options

defineAtProtoLiveCollection() also accepts:

queryFilter, optional. A request-time filter for getLiveCollection("collection", filter). It receives { entry, filter }. (This was loadCollectionFilter in v0.1)
cacheTtl, optional. Cache lifetime in milliseconds. Defaults to 300000 (5 minutes)

Support Us

You can check out more of our plugins here:

Authproto: AtProto authentication for Astro sites
Socials plugin
Alt text files plugin

You can also become a patron or buy some merch:

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

`@fujocoded/astro-atproto-loader`

What is `@fujocoded/astro-atproto-loader`?

What's included in `@fujocoded/astro-atproto-loader`?

What can you do with `@fujocoded/astro-atproto-loader`?

Setup

Okay how do I actually do stuff with this?

Configuring the loaders

Shared options

About limits

`parseRecord` vs `transform`

`fetchRecord`: hydrating records by AT-URI

Blob helpers: turning record blobs (and images) into URLs

Multi-source reads and `onSourceError`

`groupBy`: merging records from multiple sources

Default transforms

Live-only options

Support Us

Follow Us

Uh oh!

FilesExpand file tree

README.md

Latest commit

History

README.md

File metadata and controls

@fujocoded/astro-atproto-loader

What is @fujocoded/astro-atproto-loader?

What's included in @fujocoded/astro-atproto-loader?

What can you do with @fujocoded/astro-atproto-loader?

Setup

Okay how do I actually do stuff with this?

Configuring the loaders

Shared options

About limits

parseRecord vs transform

fetchRecord: hydrating records by AT-URI

Blob helpers: turning record blobs (and images) into URLs

Multi-source reads and onSourceError

groupBy: merging records from multiple sources

Default transforms

Live-only options

Support Us

Follow Us

`@fujocoded/astro-atproto-loader`

What is `@fujocoded/astro-atproto-loader`?

What's included in `@fujocoded/astro-atproto-loader`?

What can you do with `@fujocoded/astro-atproto-loader`?

`parseRecord` vs `transform`

`fetchRecord`: hydrating records by AT-URI

Multi-source reads and `onSourceError`

`groupBy`: merging records from multiple sources