README.md

ord

ord is an index, block explorer, and command-line wallet. It is experimental software with no warranty. See LICENSE for more details.

Ordinal theory imbues satoshis with numismatic value, allowing them to be collected and traded as curios.

Ordinal numbers are serial numbers for satoshis, assigned in the order in which they are mined, and preserved across transactions.

See the docs for documentation and guides.

See the BIP for a technical description of the assignment and transfer algorithm.

See the project board for currently prioritized issues.

See milestones to get a sense of where the project is and where it's going.

Join the Discord server to chat with fellow ordinal degenerates.

Donate

Ordinals is open-source and community funded. The current lead maintainer of ord is raphjaph. Raph's work on ord is entirely funded by donations. If you can, please consider donating!

The donation address is bc1qguzk63exy7h5uygg8m2tcenca094a8t464jfyvrmr0s6wkt74wls3zr5m3.

This address is 2 of 4 multisig wallet with keys held by raphjaph, erin, rodarmor, and ordinally.

Bitcoin received will go towards funding maintenance and development of ord, as well as hosting costs for ordinals.com.

Thank you for donating!

Wallet

ord relies on Bitcoin Core for private key management and transaction signing. This has a number of implications that you must understand in order to use ord wallet commands safely:

• Bitcoin Core is not aware of inscriptions and does not perform sat control. Using bitcoin-cli commands and RPC calls with ord wallets may lead to loss of inscriptions.

• ord wallet commands automatically load the ord wallet given by the --wallet option, which defaults to 'ord'. Keep in mind that after running an ord wallet command, an ord wallet may be loaded.

• Because ord has access to your Bitcoin Core wallets, ord should not be used with wallets that contain a material amount of funds. Keep ordinal and cardinal wallets segregated.

Pre-alpha wallet migration

Alpha ord wallets are not compatible with wallets created by previous versions of ord. To migrate, use ord wallet send from the old wallet to send sats and inscriptions to addresses generated by the new wallet with ord wallet receive.

Installation

ord is written in Rust and can be built from source. Pre-built binaries are available on the releases page.

You can install the latest pre-built binary from the command line with:

curl --proto '=https' --tlsv1.2 -fsLS https://ordinals.com/install.sh | bash -s

Once ord is installed, you should be able to run ord --version on the command line.

Building

On Debian and Ubuntu, ord requires libssl-dev when building from source:

sudo apt-get install libssl-dev

You'll also need Rust:

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

To build ord from source:

git clone https://github.com/ordinals/ord.git
cd ord
cargo build --release

Once built, the ord binary can be found at ./target/release/ord.

ord requires rustc version 1.67.0 or later. Run rustc --version to ensure you have this version. Run rustup update to get the latest stable release.

Contributing

If you wish to contribute there are a couple things that are helpful to know. We put a lot of emphasis on proper testing in the code base, with three broad categories of tests: unit, integration and fuzz. Unit tests can usually be found at the bottom of a file in a mod block called tests. If you add or modify a function please also add a corresponding test. Integration tests try to test end-to-end functionality by executing a subcommand of the binary. Those can be found in the tests directory. We don't have a lot of fuzzing but the basic structure of how we do it can be found in the fuzz directory.

We strongly recommend installing just to make running the tests easier. To run our CI test suite you would do:

just ci

This corresponds to the commands:

cargo fmt -- --check
cargo test --all
cargo test --all -- --ignored

Have a look at the justfile to see some more helpful recipes (commands). Here are a couple more good ones:

just fmt
just fuzz
just doc
just watch ltest --all

If the tests are failing or hanging, you might need to increase the maximum number of open files by running ulimit -n 1024 in your shell before you run the tests, or in your shell configuration.

We also try to follow a TDD (Test-Driven-Development) approach, which means we use tests as a way to get visibility into the code. Tests have to run fast for that reason so that the feedback loop between making a change, running the test and seeing the result is small. To facilitate that we created a mocked Bitcoin Core instance in test-bitcoincore-rpc.

Syncing

ord requires a synced bitcoind node with -txindex to build the index of satoshi locations. ord communicates with bitcoind via RPC.

If bitcoind is run locally by the same user, without additional configuration, ord should find it automatically by reading the .cookie file from bitcoind's datadir, and connecting using the default RPC port.

If bitcoind is not on mainnet, is not run by the same user, has a non-default datadir, or a non-default port, you'll need to pass additional flags to ord. See ord --help for details.

bitcoind RPC Authentication

ord makes RPC calls to bitcoind, which usually requires a username and password.

By default, ord looks a username and password in the cookie file created by bitcoind.

The cookie file path can be configured using --cookie-file:

ord --cookie-file /path/to/cookie/file server

Alternatively, ord can be supplied with a username and password on the command line:

ord --bitcoin-rpc-user foo --bitcoin-rpc-pass bar server

Using environment variables:

export ORD_BITCOIN_RPC_USER=foo
export ORD_BITCOIN_RPC_PASS=bar
ord server

Or in the config file:

bitcoin_rpc_user: foo
bitcoin_rpc_pass: bar

Logging

ord uses env_logger. Set the RUST_LOG environment variable in order to turn on logging. For example, run the server and show info-level log messages and above:

$ RUST_LOG=info cargo run server

New Releases

Release commit messages use the following template:

Release x.y.z

- Bump version: x.y.z → x.y.z
- Update changelog
- Update dependencies
- Update database schema version

Translations

To translate the docs we use this mdBook i18n helper. So read through their usage guide to see the structure that translations should follow.

There are some other things to watch out for but feel free to just start a translation and open a PR. Have a look at this commit for an idea of what to do. A maintainer will also help you integrate it into our build system.

To align your translated version of the Handbook with reference to commit #2427, here are some guiding commands to assist you. It is assumed that your local environment is already well-configured with Python, Mdbook, mdBook i18n helper and that you've clone this repo.

1. Run the following command to generate a new pot file, which is named as messages.pot:

MDBOOK_OUTPUT='{"xgettext": {"pot-file": "messages.pot"}}'
mdbook build -d po

2. Run msgmerge where xx.po is your localized language version following the naming standard of ISO639-1. This process will update the po file with the most recent original version:

msgmerge --update po/xx.po po/messages.pot

3. Look for #, fuzzy. The mdBook-i18n-helper tool utilizes the "fuzzy" tag to highlight sections that have been recently edited. You can proceed to perform the translation tasks by editing the "fuzzy"part.

4. Execute the mdbook command. A demonstration in Chinese (zh) is given below:

mdbook build docs -d build
MDBOOK_BOOK__LANGUAGE=zh mdbook build docs -d build/zh
mv docs/build/zh/html docs/build/html/zh
python3 -m http.server --directory docs/build/html --bind 127.0.0.1 8080

5. Upon verifying everything and ensuring all is in order, you can commit the modifications and progress to open a Pull Request (PR) on Github. (Note: Please ensure ONLY the 'xx.po' file is pushed, other files such as '.pot' or files ending in '~' are unnecessary and should NOT be included in the Pull Request.）