Skip to main content

Working with Content Archives

When you upload files to Web3.Storage using the client library, your data is converted into a graph of data structures, which are then packed into a format called a Content Archive (CAR) before being sent to the Web3.Storage service.

For most use cases, you never need to know about this process, as the conversion happens behind the scenes when using the client library. However, if you're using the HTTP API, or if you want more control over the structure of the IPFS data graph, you may want to work with Content Archives directly.

This how-to guide will explain the basics of Content Archives and how they're used by the Web3.Storage API.

We'll also see several methods of creating and manipulating Content Archives using command line tools and an overview of the libraries you can use in your application's code.

What is a Content Archive?#

The Content Archive format is a way of packaging up content addressed data into archive files that can be easily stored and transferred. You can think of them like TAR files that are designed for storing collections of content addressed data.

The type of data stored in CARs is defined by IPLD, or InterPlanetary Linked Data. IPLD is a specification and set of implementations for structured data types that can link to each other using a hash-based Content Identifier (CID). Data linked in this way forms a Directed Acyclic Graph, or DAG, and you'll likely see a few references to DAGs in the documentation for IPLD and IPFS.

IPFS files are one example of IPLD data, but IPLD can also be used to access data from Ethereum, Git, and other hash-addressed systems. You can also use IPLD as a general purpose format for your structured data, sort of like a Web3-flavored JSON. See Advanced IPLD formats below for more information.

CARs and Web3.Storage#

When the Web3.Storage client packs up regular files into a CAR to store on IPFS, the CAR contains data encoded in the same format used by IPFS when importing files using the command line or other IPFS APIs.

This format uses an IPLD "codec" called dag-pb, which uses Protocol Buffers to encode an object graph. Inside the graph are UnixFS objects that describe the files and their contents.

Although the HTTP API also allows you to upload regular files, the client prefers to send CARs for a few reasons.

First, formatting everything on the client allows us to calculate the root Content Identifier for the data you're uploading before we send any data to the remote service. This means that you can compare the CID returned by the Web3.Storage service to the one you calculated locally, and you don't have to trust the service to do the right thing.

Another reason to use CARs is to support large files, which would otherwise hit size limits on the Web3.Storage backend platform. The data in a CAR is already chunked into small blocks, which makes CARs easy to split into small pieces that can be uploaded in batches.

Command line tools#

There are a few ways to create and interact with CAR files from the command line.


The ipfs-car JavaScript package includes a command-line tool for easily creating, unpacking, and verifying CAR files.

To install it, you'll need Node.js - we recommend the latest stable version.

You can install the command globally:

npm install -g ipfs-car

Or run the command with npx without installing it to your PATH:

npx ipfs-car --help

The --pack flag will create a new CAR file from a collection of input files:

ipfs-car --pack path/to/files --output path/to/write/

Or extract files from a CAR with --unpack:

ipfs-car --unpack path/to/ --output /path/to/unpack/files/to

You can also list the contents of a CAR with --list:

ipfs-car --list path/to/

For more usage information, run ipfs-car --help.


go-ipfs is the reference implementation of the IPFS protocol. Among many other features, go-ipfs supports exporting any IPFS object graph into a CAR file and importing data from CAR files into your local IPFS repository.

The ipfs dag export command will fetch an IPFS object graph by its Content ID (CID), writing a stream of CAR data to standard output.

To create a CAR file using go-ipfs, you can redirect the output of ipfs dag export to a file:

cid="bafybeigdmvh2wgmryq5ovlfu4bd3yiljokhzdep7abpe4c4lrf6rukkx4m"ipfs dag export $cid > path/to/

Note that you should replace the value of cid inside the quotes with the CID you want to export.

If you don't have the CID in your local IPFS repository, the dag export command will try to fetch it over the IPFS network.

To add the contents of a CAR file to your local IPFS repository, you can use ipfs dag import:

ipfs dag import path/to/

Libraries for application developers#


There are two JavaScript packages available for manipulating CARs inside your application.


The ipfs-car package includes library functions for packing and unpacking files into CARs, using the IPFS UnixFs data model. The library includes the same functionality as the ipfs-car command line utility described above.

See the ipfs-car README for API documentation and usage examples.


The @ipld/car package contains the main JavaScript implementation of the CAR specification and is used by ipfs-car under the hood. If you want to store non-file data using advanced IPLD formats, you should use @ipld/car directly.

@ipld/car also provides the CarReader interface used by the Web3.Storage client's putCar method.

Here's a simple example of loading a CAR file from a Node.js stream and storing it with Web3.Storage:

import { createReadStream } from 'fs'import { CarReader } from '@ipld/car'
async function storeCarFile(filename) {  const inStream = createReadStream(filename)  const car = await CarReader.fromIterable(inStream)    const client = makeStorageClient()  const cid = await client.putCar(car)  console.log('Stored CAR file! CID:', cid)}

CarReader.fromIterable accepts any iterable of Uint8Array data, including Node.js streams. If you have all your CAR data in a single Uint8Array already, you can use CarReader.fromBytes instead.

The CarReader type shown above will read the entire contents of the CAR into memory, which may cause issues with large files. On Node.js, you can use CarIndexedReader, which reads CAR data from disk directly and uses less memory than CarReader.


The go-car module provides the main Golang implementation of the CAR specification. We recommend using the v2 module version, which supports the latest version of the CAR spec.

See the API reference documentation for more information.

Splitting CARs for upload to Web3.Storage#

The Web3.Storage HTTP API accepts CAR uploads up to 100 MB in size, but the JavaScript client uses the HTTP API to upload files of any size. The client manages to do this by splitting CARs into chunks of less than 100 MB each and uploading each chunk separately.

The main tool available for splitting and joining CARs is called carbites, which has implementations in JavaScript and Go. The JavaScript implementation includes a command-line version that allows you to split and join CARs from your terminal or favorite scripting language.

This section will demonstrate a few ways to split CARs in a way that's acceptable to the Web3.Storage service, using the command line tool, as well as programmatically using the carbites libraries in JavaScript and Go.

The JavaScript carbites library includes a package called carbites-cli that can split and join CARs from the command line. You'll need a recent version of Node.js installed, preferably the latest stable version.

You can install the tool globally with npm:

npm install -g carbites-cli
added 71 packages, and audited 72 packages in 846ms20 packages are looking for funding  run `npm fund` for detailsfound 0 vulnerabilities

This will add a carbites command to your shell's environment:

carbites --help
  CLI tool for splitting a single CAR into multiple CARs from the comfort of your terminal.  Usage    $ carbites <command>    Commands      split      join
Running with npx

You can run the carbites command without installing it globally using the npx command, which is included with Node.js:

npx carbites-cli --help

The first time around, it will ask to make sure you want to install the package:

Need to install the following packages:  carbites-cliOk to proceed? (y)

After that, you can use npx carbites-cli instead of carbites for any of the commands below!

Splitting CARs#

The carbites split command takes a CAR file as input and splits it into multiple smaller CARs.

The --size flag sets the maximum size of the output CAR files. For uploading to Web3.Storage, --size must be less than 100MB.

The other important flag is --strategy, which determines how the CAR files are split. For Web3.Storage uploads, we need to use the treewalk strategy, so that all of our CARs share the same root CID. This will allow the Web3.Storage service to piece them all together again once they've all been uploaded.

Here's an example, using an input car file called that weighs in at 455MB:

carbites split --size 100MB --strategy treewalk

This will create five new files in the same directory as the input file, named through If you list their sizes, you can see that all the chunked cars are less than or equal to 100 MB:

ls -lh my-video*
-rw-r--r--  1 user  staff   100M Sep 15 13:56  1 user  staff   100M Sep 15 13:56  1 user  staff   100M Sep 15 13:56  1 user  staff   100M Sep 15 13:56  1 user  staff    56M Sep 15 13:56  1 user  staff   455M Sep 15 13:52

Joining CARs#

To combine CARs that have been previously split, you can use the carbites join command:

carbites join my-video-*.car --output

Advanced IPLD formats#

IPLD can also be used as a general purpose data format like JSON. In fact, you can use JSON directly as IPLD just by using a special convention for linking to other IPLD objects. This convention is defined in the dag-json "codec".

Here's an example of a dag-json object:

{  "name": "Have you seen this dog?",  "description": "I have now...",  "image": { "/": "bafybeihkqv2ukwgpgzkwsuz7whmvneztvxglkljbs3zosewgku2cfluvba" }}

The image field uses the special "link type" to reference another IPLD object. The link is just a regular JSON object with a single key named /, whose value is a Content Identifier.

Although dag-json is familiar and easy to use, we recommend using the similar dag-cbor codec instead. dag-cbor uses the Concise Binary Object Representation to more efficiently encode data, especially binary data which must be Base64-encoded when using dag-json.


Below are some examples of working with dag-cbor data and sending it to Web3.Storage.

First, you'll need to import some things:

import { Web3Storage } from ''import { CarReader } from '@ipld/car'import { encode } from 'multiformats/block'import * as cbor from '@ipld/dag-cbor'import { sha256 } from 'multiformats/hashes/sha2'

Now we'll define a convenience function to encode an IPLD block of CBOR data and hash with SHA2-256:

async function encodeCborBlock(value) {  return encode({ value, codec: cbor, hasher: sha256 })}

And a function to make a CAR from a collection of blocks and a root CID:

makeCar(rootCID, ipldBlocks)
async function makeCar (rootCID, ipldBlocks) {  return new CarReader(1, [rootCID], ipldBlocks)}

Storing simple CBOR data#

Using the helpers above, you can make a CAR file with a single block of simple CBOR data and send it to Web3.Storage:

async function simpleCborExample() {  // encode the value into an IPLD block and store with Web3.Storage  const block = await encodeCborBlock({ hello: 'world' })  const car = await makeCar(block.cid, [block])
  // upload to Web3.Storage using putCar  const client = new Web3Storage({ token: process.env.WEB3STORAGE_TOKEN })  console.log(`๐Ÿค– Storing simple CBOR object...`)  const cid = await client.putCar(car)  console.log(`๐ŸŽ‰ Done storing simple CBOR object. CID: ${cid}`)  console.log(`๐Ÿ’ก If you have ipfs installed, try: ipfs dag get ${cid}\n`)}

If you have the IPFS command line app installed, you can view the object you stored with the ipfs dag get command, for example:

ipfs dag get bafyreidykglsfhoixmivffc5uwhcgshx4j465xwqntbmu43nb2dzqwfvae
{  "hello": "world"}

Note that the example output has been indented with jq for clarity.The real command will output a compact dag-json representation of the CBOR data without any extra whitespace.

CBOR with IPLD links#

You can link from one CBOR object to another using CIDs:

async function cborLinkExample() {  // Encode a simple object to get its CID  const addressBlock = await encodeCborBlock({ email: '[email protected]' })
  // Now we can use the CID to link to the object from another object  const personBlock = await encodeCborBlock({    title: 'Galactic President',    description: 'Just this guy, you know?',    contact: addressBlock.cid,  })
  // pack everything into a CAR  const car = await makeCar(personBlock.cid, [personBlock, addressBlock])
  // upload to Web3.Storage using putCar  const client = new Web3Storage({ token: process.env.WEB3STORAGE_TOKEN })
  console.log(`๐Ÿค– Storing CBOR objects with CID links between them...`)  const cid = await client.putCar(car)  console.log('๐ŸŽ‰ Stored linked data using dag-cbor. Root CID:', cid)  console.log(`๐Ÿ’ก If you have ipfs installed, try: ipfs dag get ${cid}`)  console.log(`๐Ÿ”— You can also traverse the link by path: ipfs dag get ${cid}/contact\n`)}

As with simple objects, you can use ipfs dag get to show the outer object:

ipfs dag get bafyreieq6bftbe3o46lrdbzj6vrvyee4njfschajxgmpxwbqex3czifhry
{  "contact": {    "/": "bafyreicp2g6ez5exmw5uxsns7kkwtxr5z4vyx4xkdci6xpy2vou3zqc6me"  },  "description": "Just this guy, you know?",  "title": "Galactic President"}

The contact field above contains an IPLD link, which can be included in the ipfs dag get command to resolve the linked object:

ipfs dag get bafyreieq6bftbe3o46lrdbzj6vrvyee4njfschajxgmpxwbqex3czifhry/contact
{"email":"[email protected]"}

Linking from CBOR to an IPFS file#

Our final example is a little more complex. We're going to store a file in the same UnixFS format that IPFS uses, and link to it from a CBOR object.

First, we'll encode a file into UnixFS format. Normally, this is done by the client library, but we want to get the CID of the file object to use for our link before we send the file off to Web3.Storage, so we'll construct the UnixFS object ourselves.

Here's a helper function to make a UnixFS file and encode it to an IPLD block:

import { importer } from 'ipfs-unixfs-importer'import { MemoryBlockStore } from 'ipfs-car/blockstore/memory'async function makeUnixFsFile(source) {  const blockstore = new MemoryBlockStore()  // taken from  // but with wrapWithDirectory overriden to false  const unixFsOptions = {    cidVersion: 1,    chunker: 'fixed',    maxChunkSize: 262144,    hasher: sha256,    rawLeaves: true,    wrapWithDirectory: false,    maxChildrenPerNode: 174  }  const importStream = await importer(source, blockstore, unixFsOptions)  let root = null  for await (const entry of importStream) {    root = entry  }  const blocks = []  for await (const block of blockstore.blocks()) {    blocks.push(block)  }  await blockstore.close()  return { root, blocks }}

The helper returns a root block, which we can link to by CID, as well as a blocks array containing the encoded file data. When we create the CAR to send to Web3.Storage, it's important to include all the file blocks as well as the CBOR block.

async function cborLinkToFileExample() {  const source = [{    path: 'example.txt',    content: new TextEncoder().encode('Some plain text, encoded to UTF-8')  }]   const { root, blocks }  = await makeUnixFsFile(source)  const cborBlock = await encodeCborBlock({    description: 'A CBOR object that references a UnixFS file object by CID',    file: root.cid,  })
  blocks.push(cborBlock)  const car = await makeCar(cborBlock.cid, blocks)
  const client = new Web3Storage({ token: process.env.WEB3STORAGE_TOKEN })  console.log(`๐Ÿค– Storing a CBOR object that links to a UnixFS file by CID...`)  const cid = await client.putCar(car)  console.log('๐ŸŽ‰ Stored dag-cbor object that links to a unixfs file. Root CID: ', cid)  console.log(`๐Ÿ’ก If you have ipfs installed, try: ipfs dag get ${cid}`)  console.log(`๐Ÿ’พ You can view the linked file with ipfs: ipfs cat ${cid}/file`)  console.log('๐Ÿ”— View linked file via IPFS gateway: ', `https://${cid}`)}

As before, we can view the root block with ipfs dag get:

ipfs dag get bafyreid7hvce4pzcy56s4hwu7xrt3dnnzzfvilzfwsadvf6q4eqild6ndy
{  "description": "A CBOR object that references a UnixFS file object by CID",  "file": {    "/": "bafkreihmlglmfpadbk4fy72ljniveedbqicysoe5zhqqkgkuso3e6xyns4"  }}

Since the file data is plain text, you can use ipfs dag get to fetch its contents:

ipfs dag get bafyreid7hvce4pzcy56s4hwu7xrt3dnnzzfvilzfwsadvf6q4eqild6ndy/file
"Some plain text, encoded to UTF-8"

Notice that the file content is wrapped in quotes because dag get is interpreting the content as a JSON string.

To avoid this, or to fetch binary files, you can use ipfs get to download the file:

ipfs get bafyreid7hvce4pzcy56s4hwu7xrt3dnnzzfvilzfwsadvf6q4eqild6ndy/file
Saving file(s) to file 33 B / 33 B [===============================================================] 100.00% 0s

Note that the IPFS HTTP gateway currently does not support rendering CBOR data, so the root object is not directly viewable via the gateway. See the note about gateway support below for more information.

However, the gateway can traverse the IPLD links inside our CBOR object, so you can link to the file by path and the gateway will resolve the linked file. For example:

Gateway support

Although Web3.Storage supports storing CAR files with dag-cbor content by default and can accept other codecs with the decoders option, the IPFS HTTP gateway does not currently "speak" these formats and will not return such data over HTTP. Please follow this issue to track the development of this feature.

Enabling IPLD codecs in the client library#

By default, the client's putCar method will accept data encoded using the dag-pb, dag-cbor, or raw codecs. If you want to use another codec like dag-json, you must include the codec in the decoders option to putCar.

See the putCar parameter reference for more details and an example that uses dag-json.