spec-agents-lakehouse (lake_fabric)
Lakehouse domain pack for agent-fabric: turns CSV, JSON, XLSX, API or MCP-tool sources into generated
Airflow DAGs that load Trino/Iceberg tables in bronze, silver and gold layers. Components: source_inspect, medallion_plan,
airflow_dag_render, dag_check; pipelines ingest_to_lakehouse, medallion_design.
Generated code is never trusted twice: values are pprint-ed into a static template, SQL identifiers are validated and quoted, credentials
live in Airflow connections, and dag_check rejects unsafe files. Incremental loads and pagination never load partial data silently.
Status: pre-release. Until the first PyPI release, install a wheel from the GitHub Releases or use
uv sync --all-packagesin a checkout; thepip installlines below are the PyPI names.
Names
| PyPI distribution | spec-agents-lakehouse |
| Import name | lake_fabric |
| Directory in the monorepo | packages/lakehouse |
| Release tag / PR scope | lakehouse-vX.Y.Z / lakehouse |
The distribution is named spec-agents-lakehouse because the shorter names are taken on PyPI; the import name and the entry point do not change.
Install and use
pip install spec-agents-lakehouse
python -m lake_fabric.generate params.json --sample records.json --out dags # no LLM involved
Demo agent team (lakehouse_team, dag_engineer, dag_reviewer, schema_designer): config/ in the repository.
1 maintainer
Metadata
1 maintainer
Release files for spec-agents-lakehouse 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| spec_agents_lakehouse-0.2.1.tar.gz | 31.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| spec_agents_lakehouse-0.2.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 62.7 kB
Release files / spec_agents_lakehouse-0.2.1.tar.gz
| Download URL | spec_agents_lakehouse-0.2.1.tar.gz |
|---|---|
| Size | 31.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
628251ce6aa75ac33965574a62d77f74baee19711051bc17f4ab15ec6fd9d533
|
|
BLAKE2b-256 checksum How to use checksums |
492d35e110a73b77185fe2e4c13133b2e03c1e873ea335381981f6de61dc1c95
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 2, 2026.
Transparency logRelease files / spec_agents_lakehouse-0.2.1-py3-none-any.whl
| Download URL | spec_agents_lakehouse-0.2.1-py3-none-any.whl |
|---|---|
| Size | 30.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5999c1e35153d6f711dab32bf1ef956b9f32eebe59ac23618a88dbe66f988c97
|
|
BLAKE2b-256 checksum How to use checksums |
2ca2b76f120d1495e69ed32daaa6a2b4a93afbe87baa2e4299a1306fd455622b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 2, 2026.
Transparency log
