Metadata-Version: 2.4
Name: xorq
Version: 0.3.29
Summary: Data processing library built on top of Ibis and DataFusion to write multi-engine data workflows.
Project-URL: Homepage, https://www.xorq.dev/
Project-URL: Repository, https://github.com/xorq-labs/xorq/
Project-URL: Issues, https://github.com/xorq-labs/xorq/issues
Project-URL: Changelog, https://github.com/xorq-labs/xorq/blob/main/CHANGELOG.md
Project-URL: Documentation, https://docs.xorq.dev/
Author-email: Hussain Sultan <hussain@letsql.com>
Maintainer-email: Dan Lovell <dan@letsql.com>, Daniel Mesejo <mesejo@letsql.com>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Rust
Classifier: Topic :: Database :: Database Engines/Servers
Classifier: Topic :: Software Development :: User Interfaces
Requires-Python: <3.14,>=3.10
Requires-Dist: atpublic>=5.1
Requires-Dist: attrs>=24.1.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: cityhash<1,>=0.4.7; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: click>=8.0
Requires-Dist: cloudpickle>=3.1.1
Requires-Dist: cryptography>=45.0.3
Requires-Dist: filelock>=3.13
Requires-Dist: git-annex>=10.20250220
Requires-Dist: gitpython>=3.1.46
Requires-Dist: opentelemetry-exporter-otlp-proto-grpc>=1.32.1
Requires-Dist: opentelemetry-exporter-otlp>=1.32.1
Requires-Dist: opentelemetry-exporter-prometheus>=0.55b1
Requires-Dist: opentelemetry-sdk>=1.32.1
Requires-Dist: pandas<3,>=1.5.3; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: parsy>=2
Requires-Dist: prometheus-client>=0.22.1
Requires-Dist: py-yaml12
Requires-Dist: pyarrow-hotfix<1,>=0.4; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: pyarrow<22,>=13.0.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: python-dateutil>=2.8.2
Requires-Dist: pytz>=2022.7
Requires-Dist: rich>=13.9.4
Requires-Dist: sqlglot!=26.32.0,<28.7.0,>=23.4
Requires-Dist: strenum>=0.4.15; python_version <= '3.10'
Requires-Dist: structlog<26,>=24.2.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: textual>=1.0.0
Requires-Dist: tomlkit>=0.12
Requires-Dist: toolz>=0.11
Requires-Dist: typing-extensions>=4.3.0
Requires-Dist: uv>=0.7.20
Requires-Dist: xorq-dasher>=0.1.1
Requires-Dist: xorq-datafusion==0.2.7
Provides-Extra: bsl
Requires-Dist: boring-semantic-layer>=0.3.13; extra == 'bsl'
Provides-Extra: databricks
Requires-Dist: adbc-driver-manager>=1.0.0; extra == 'databricks'
Requires-Dist: databricks-sql-connector>=3.0.0; extra == 'databricks'
Provides-Extra: datafusion
Requires-Dist: datafusion<49,>=0.6; (python_version >= '3.10' and python_version < '4.0') and extra == 'datafusion'
Provides-Extra: duckdb
Requires-Dist: duckdb>=1.1.3; extra == 'duckdb'
Provides-Extra: examples
Requires-Dist: adbc-driver-postgresql>=1.4.0; extra == 'examples'
Requires-Dist: adbc-driver-sqlite>=1.4.0; extra == 'examples'
Requires-Dist: duckdb<2,>=0.10.3; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: matplotlib>=3.8.0; extra == 'examples'
Requires-Dist: mcp>=1.5.0; extra == 'examples'
Requires-Dist: openai>=1.65.4; extra == 'examples'
Requires-Dist: pins[gcs]<1,>=0.8.3; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: pyiceberg[sql-postgres,sql-sqlite]>=0.9.0; extra == 'examples'
Requires-Dist: requests>=2.32.3; extra == 'examples'
Requires-Dist: scikit-learn<2.0.0,>=1.4.0; extra == 'examples'
Requires-Dist: xgboost>=1.6.1; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: xorq-feature-utils; extra == 'examples'
Requires-Dist: xorq-weather-lib; extra == 'examples'
Provides-Extra: geospatial
Requires-Dist: geoarrow-types<1,>=0.2; extra == 'geospatial'
Provides-Extra: gizmosql
Requires-Dist: adbc-driver-gizmosql>=1.1.5; extra == 'gizmosql'
Requires-Dist: cryptography>=42; extra == 'gizmosql'
Requires-Dist: duckdb>=1.1.3; extra == 'gizmosql'
Requires-Dist: gizmosql<2,>=1.26.0; extra == 'gizmosql'
Provides-Extra: ibis
Requires-Dist: ibis-framework>=10.5.0; extra == 'ibis'
Provides-Extra: postgres
Requires-Dist: adbc-driver-postgresql>=1.4.0; extra == 'postgres'
Requires-Dist: psycopg[binary]>=3.2.0; extra == 'postgres'
Provides-Extra: pyiceberg
Requires-Dist: pyiceberg[sql-postgres,sql-sqlite]>=0.9.0; extra == 'pyiceberg'
Provides-Extra: snowflake
Requires-Dist: adbc-driver-snowflake>=1.5.0; extra == 'snowflake'
Requires-Dist: snowflake-connector-python<4,>=3.10.1; (python_version >= '3.10' and python_version < '4.0') and extra == 'snowflake'
Provides-Extra: sqlite
Requires-Dist: adbc-driver-sqlite>=1.4.0; extra == 'sqlite'
Provides-Extra: trino
Requires-Dist: trino==0.336.0; extra == 'trino'
Description-Content-Type: text/markdown

<div align="center">

![Xorq Logo](docs/images/Xorq_WordMark_RGB_Midnight.png#gh-light-mode-only)
![Xorq Logo](docs/images/Xorq_WordMark_RGB_BlueSky.png#gh-dark-mode-only)

![License](https://img.shields.io/github/license/xorq-labs/xorq)
![PyPI - Version](https://img.shields.io/pypi/v/xorq)
![CI Status](https://img.shields.io/github/actions/workflow/status/xorq-labs/xorq/ci-test.yml)


[Documentation](https://docs.xorq.dev) • [Website](https://www.xorq.dev) • [Claude Code plugin](https://github.com/xorq-labs/claude-plugins)
</div>

---
Xorq is an executable memory system for tabular data work. Xorq gives agents a
catalog of executable pipelines instead of markdown notes. It turns ephemeral
agent work such as pandas scripts, sklearn pipelines, ad-hoc tables into
durable, composable, executable artifacts that any future agent or human can
discover, reproduce and reuse.

It comes with a CLI for agents and a TUI for humans with a git-native catalog.
![xorq catalog TUI](docs/images/catalog-tui.png)

---
# The Problem

Coding agents are great at accomplishing closed-loop task but in the process
accumulate tech-debt and unnecessary complexity. For example, if you ask a
coding agent to build a dashboard, you are more likely than not to get a folder
of one-off Python scripts that import each other in non-obvious ways, an
embedded JSON holding intermediate state, and a `requirements.txt` that was
last regenerated two sessions ago. It may also execute end-to-end on your
laptop. Verifying by reproducing on another machine, or productionizing any of
it, means rewriting some of it. And every time you rewrite, more complexity
gets introduced.


| Pain | Symptom |
|------|---------|
| **Imperative, stateful artifacts** | An agent run leaves you with a folder of `.py`, `.json`, and `.html` files. Reproducing the result means re-running them in the right order without a declarative spec |
| **No discoverable, shared index** | "Team memory" today is `~/.claude/memory/*.md`, with a `MEMORY.md` index of one-liners pointing to the notes. There's no executable catalog two agents can both pull into context |
| **No lineage graph** | Rename a column upstream and a downstream model breaks at runtime. The dependency lived only in chat history, not in a graph that could have flagged it before it shipped. |
| **No portable environment** | A pipeline that ran in one agent session has no path to another sandbox, your machine, or production.|

# Two ways to start

**With an agent.** Install the Xorq plugin in Claude Code and let it build
catalogs for you:

```
/plugin marketplace add xorq-labs/claude-plugins
/plugin install xorq@xorq-plugins
```

The plugin adds four slash commands:

- `/xorq:init` — load CSV or Parquet files as catalog entries
- `/xorq:catalog-explore` — browse what's already in a catalog
- `/xorq:composer` — combine entries into new joined/aliased entries
- `/xorq:builder` — assemble ML pipelines and semantic-layer entries

The agent does the building; you keep the catalog.

**Manually.** Install the library and start composing expressions in Python:

```bash
❯ pip install xorq[examples]
❯ xorq init -t penguins
```
---

# Design choices

| Choice | What it enables |
|--------|-----------------|
| **[Ibis](https://ibis-project.org/) as expression system** | Declarative dataframe expressions that compile to many engines. |
| **[Git](https://git-scm.com/) for state and storage** | The catalog is a git repo of entries with git-annex support for large files  |
| **[uv](https://docs.astral.sh/uv/) for reproducible environments** | Each entry ships with a wheel and pinned `requirements.txt`. |
| **[DataFusion](https://datafusion.apache.org/) for embedded compute** | Pipelines execute in-process SQL and UDF execution |
| **[Arrow](https://arrow.apache.org) for IPC and network** | Operators exchange Arrow RecordBatches |


# Supported engines

The same expression can run against any of these backends, and `into_backend`
moves data between them.

| Category | Engines |
|----------|---------|
| **Embedded** | DataFusion, DuckDB, SQLite, pandas |
| **Warehouses** | Snowflake, Databricks, Trino, Postgres |
| **Lakehouse** | PyIceberg |
| **Arrow Flight** | GizmoSQL |


# Comparison

A Xorq memory is a computation you reason about by its invariants (schema,
lineage, content hash, deterministic execution), the way you reason about a
matrix by its properties rather than its entries.

| Approach | Memory item | Answer produced by | Provenance & reproducibility |
|----------|-------------|---------------------|-------------------------------|
| Agent memory (Mem0, etc) | Markdown snippets | LLM reading the prompt | None |
| MCP / open context servers | Tool bindings | Tool at runtime; LLM consumes as text | Per-tool |
| dbt | SQL model files | Warehouse executing compiled SQL | `manifest.json` captures lineage; env (warehouse, packages) pinned externally |
| **Xorq** | Content-addressed expression + pinned env | Engine executing the expression | `expr.yaml` + uv-pinned env shipped with the artifact |


# Benchmark

On [DABStep](https://huggingface.co/spaces/adyen/DABstep) — 450 data-analysis
questions over payment transaction data — a Xorq semantic catalog of 33 named
expressions takes Haiku from 50% to 84%, 8pp above the Sonnet baseline.

![DABStep accuracy: Haiku 4.5 50%, Sonnet 4.6 75%, Haiku 4.5 + Semantic Catalog
84%](docs/images/dabstep-benchmark.png)

Where the agent looks for context mattered more than which base model it
used. Full write-up:
[Orientation Over Reasoning](https://xorq.dev/blog/orientation-over-reasoning/).


# Under the hood

<details open>
<summary><b>The Expression</b> — declarative Ibis, multi-engine, Arrow-native</summary>

Write declarative Ibis expressions that run like a tool. Xorq extends Ibis with
caching, multi-engine execution, and UDFs. Below, `xo._` is the Ibis row
reference — `xo._.species` refers to the `species` column of the current table.

```python
import xorq.api as xo
from xorq.caching import ParquetCache

penguins = xo.examples.penguins.fetch()

penguins_agg = (
    penguins
    .filter(xo._.species.notnull())
    .group_by("species")
    .agg(avg_bill_length=xo._.bill_length_mm.mean())
)

expr = (
    penguins_agg
    .cache(ParquetCache.from_kwargs())
)
```

### One expression, many engines

```python
expr = penguins.into_backend(xo.sqlite.connect())
expr.ls.backends
```
```
(<xorq.backends.sqlite.Backend at 0x107debda0>,
 <xorq.backends.xorq_datafusion.Backend at 0x1669002c0>)
```

### Expressions are tools, Arrow is the pipe

Unix pipes text streams between small programs. Xorq pipes Arrow streams
between expressions.

`unix : programs :: xorq : arrow-transforms`

```
In [6]: expr.to_pyarrow_batches()
Out[6]: <pyarrow.lib.RecordBatchReader at 0x15dc3f570>
```

### Workflows, without state

Xorq executes expressions as Arrow RecordBatch streams — no DAG of tasks to
checkpoint, just data flowing through transforms.

### Scikit-learn pipelines

Xorq translates `scikit-learn` Pipeline objects to deferred expressions via
`Pipeline.from_instance(sklearn_pipeline)`. End-to-end sklearn examples live in
[xorq-labs/xorq-gallery](https://github.com/xorq-labs/xorq-gallery).

</details>

<details>
<summary><b>The Catalog</b> — a git repo of build artifacts on the filesystem</summary>

The catalog is a git repo of build artifacts on filesystem. `xorq catalog add`
packages a build directory -- manifest (`expr.yaml` + `*_metadata.json`),
Python environment via `uv` -- into an entry.

### Build and add

```bash
❯ xorq uv build expr.py
Building wheel...
Successfully built ...
builds/fa2122f6a9e9

❯ xorq catalog -p git-catalogs/penguins init
Initialized catalog at /git-catalogs/penguins

❯ xorq catalog add builds/fa2122f6a9e9/ -a penguins-agg
Added fa2122f6a9e9
```

### Git history

Every catalog operation is a commit you can read:

```
❯ git -C git-catalogs/penguins reflog
17dd4e9 (HEAD -> main) HEAD@{0}: add: fa2122f6a9e9 (aliases penguins-agg)
9f5d242 HEAD@{1}: add catalog.yaml
9915df3 HEAD@{2}: commit: Switching to main
```

### Catalog layout

```
❯ tree git-catalogs/penguins
git-catalogs/penguins
├── aliases
│   └── penguins-agg.zip -> ../entries/fa2122f6a9e9.zip
├── entries
│   └── fa2122f6a9e9.zip
├── metadata
│   └── fa2122f6a9e9.zip.metadata.yaml
└── catalog.yaml
```

Aliases are symlinks, entries are zipped builds, and metadata sidecars are
plain YAML. An agent that clones the repo can discover everything with file
operations — no service to call, no API to learn:

```bash
# List aliased entries
❯ ls git-catalogs/penguins/aliases/

# Find entries that emit an 'avg_bill_length' column
❯ grep -l 'avg_bill_length' git-catalogs/penguins/metadata/*.yaml

# Find entries running on DataFusion
❯ grep -l 'xorq_datafusion' git-catalogs/penguins/metadata/*.yaml

# Find source entries (vs. unbound, expr_builder kinds)
❯ grep -l 'kind: source' git-catalogs/penguins/metadata/*.yaml
```

### Inside an entry

A build directory contains the manifest plus everything needed to reproduce
it. The zipped build is the entry stored in the catalog.

```
❯ tree builds/fa2122f6a9e9
├── build_metadata.json
├── expr.yaml
├── expr_metadata.json
├── profiles.yaml
├── requirements.txt
└── xorq-0.3.24-py3-none-any.whl
```

The manifest (`expr.yaml` + `*_metadata.json`) is the content-addressed
specification of the pipeline. The **entry** packages it with deps and source
for reproducible execution.

```yaml
# Input-addressed, composable, portable
# Abridged expr.yaml
definitions:
  nodes:
    '@read_b5f228c91f16':
      op: Read
      method_name: read_parquet
      name: penguins
      read_kwargs:
        - [hash_path, .../penguins/20250703T145709Z-c3cde/penguins.parquet]
        - [table_name, penguins]
      schema_ref: schema_f11dda6745cc

    '@filter_fa4a3fde7765':
      op: Filter
      parent: { node_ref: '@read_b5f228c91f16' }
      predicates:
        - { op: NotNull, arg: { op: Field, name: species, ... } }

    '@aggregate_eb3109707390':
      op: Aggregate
      parent: { node_ref: '@filter_fa4a3fde7765' }
      by:
        species: { op: Field, name: species, ... }
      metrics:
        avg_bill_length:
          op: Mean
          arg: { op: Field, name: bill_length_mm, ... }

    '@cachednode_fa2122f6a9e9':
      op: CachedNode
      parent: { node_ref: '@aggregate_eb3109707390' }
      cache:
        type: ParquetCache
        relative_path: parquet
      schema_ref: schema_9271d5e9d443

expression:
  node_ref: '@cachednode_fa2122f6a9e9'
  schema_ref: { schema_ref: schema_9271d5e9d443 }
```

</details>

<details>
<summary><b>The Tools</b> — catalog, run, serve</summary>

The entry is the unit of executable memory that includes the manifest plus
environment to run it. The tools — catalog, run, serve — are how agents and
humans compose with it.

### Catalog

Once an entry is published, agents discover it straight from the catalog
filesystem — `metadata/*.yaml` sidecars sit next to the zipped entries, so
listing, filtering, and lookup-by-alias/hash all work with plain file reads
and `git` (no service required). Humans open the TUI to preview data,
schema, lineage, and git history side-by-side.

```bash
❯ xorq catalog list-aliases
penguins-agg

❯ xorq catalog list
fa2122f6a9e9
```

### Run

```bash
❯ xorq run builds/fa2122f6a9e9 -o out.parquet
```
Additionally, you can serve an unbound expression over Arrow Flight. with `xorq
serve-*` commands.

</details>

---

# Learn more

- [Quickstart](https://docs.xorq.dev/getting_started/quickstart)
- [Why xorq?](https://docs.xorq.dev/#why-xorq)
- [Claude Code plugin](https://github.com/xorq-labs/claude-plugins)
- [Scikit-learn ](https://github.com/xorq-labs/xorq-template-sklearn)
- [A Git-Native Semantic Layer](https://xorq.dev/blog/bsl-xorq/) — building a portable semantic catalog with Xorq
- [Orientation Over Reasoning](https://xorq.dev/blog/orientation-over-reasoning/) — Haiku + Xorq catalog hits 84% on DABStep, above the Sonnet baseline

---

Pre-1.0. Expect breaking changes with migration guides.
