docs llms.txt codecov pypi cran stars downloads

LaminDB: Data management for traceable, multimodal AI .md

LaminDB is an open-source data management tool that makes it easy to query, trace and govern datasets across diverse storage formats and locations. Like git, LaminDB runs anywhere and captures relevant context about your work. This includes the data flow through models and analyses, the entities and notes defining your work, and the features & schemas of datasets. It takes about a minute to install LaminDB and create a database on your laptop or in the cloud.

Why?

  1. Untraceable results cannot be trusted, especially when non-verifiable tasks are delegated to agents.

  2. Without effective access to multimodal data, models burn tokens or fail entirely.

  3. Without governing changes to data akin to governing changes to software with git, it’s hard to evaluate agents, debug their mistakes, and safely merge their contributions.

Especially in life sciences, hard-to-verify tasks are abundant, data formats are heterogeneous, and teams need end-to-end traceability for GxP compliance (21 CFR Part 11 and EU Annex 11).

Existing data lakehouses aren’t a comprehensive solution. They only address the 2nd and 3rd of these problems for a single table or array format, such as parquet or zarr.

lamindb-schematic

How?

  • lineage → trace results across agent sessions, notebooks, scripts & workflows

  • lakehouse → manage datasets in any format (parquet, zarr, …) with time travel, schema evolution & ACID guarantees; load/query with your favorite engine (Polars, DuckDB, annbatch, …)

  • LIMS & ELN → unified schema-based records management with support for ontologies & notes

  • FAIR datasets → validate & annotate files, DataFrame, AnnData, SpatialData, …

  • governance → manage changes via branching & versioning

Architecture? → docs

  • zero lock-in → open source, using open standards (metadata in SQLite/Postgres, data in parquet, zarr, etc.)

  • scalable → hit storage & database directly through your pydata or R stack, no REST API involved

  • simple → pip install lamindb or install.packages('laminr') · no Docker required, no separate backend

  • unified access → local, S3, GCP, etc. · Postgres, SQLite · ontologies

  • distributed → zero-copy data sharing across databases & storage

  • reproducible → track agent traces, source code & compute environments

  • ACID → snapshot isolation & time travel via transactional metadata records across datasets in any format (parquet, zarr, etc.)

  • idempotent → re-run logic without worries about duplications or overwrites

  • decoupled compute → run your favorite engine (Polars, DuckDB, data loaders, …) with all its benefits

  • integrations → bio ontologies, git, nextflow, vitessce, redun, and more

  • extensible → create custom plug-ins based on the Django ORM, the basis for LaminDB’s registries

Who?

Scientists and engineers at leading research institutions and biotech companies, including:

  • Industry → Pfizer, Altos Labs, RefinedScience, Ensocell Therapeutics, …

  • Academia & Research → scverse, DZNE (National Research Center for Neuro-Degenerative Diseases), Helmholtz Munich (National Research Center for Environmental Health), …

  • Research Hospitals → Global Immunological Swarm Learning Network: Harvard, MIT, Stanford, ETH Zürich, Charité, U Bonn, Mount Sinai, …

From personal research projects to pharma-scale deployments managing petabytes of data across:

entities

OOMs

observations & datasets

10¹² & 10⁶

runs & transforms

10⁹ & 10⁵

proteins & genes

10⁹ & 10⁶

biosamples & species

10⁵ & 10²

…

…

UI, permissions, audit logs? LaminHub is a collaboration hub built on LaminDB similar to how GitHub is built on git.

Quickstart

To install the Python package with recommended dependencies, use:

pip install lamindb
Install with minimal dependencies.

The lamindb package adds data-science related dependencies through the [full] extra, see here.

For a minimal install of the lamindb namespace, use:

pip install lamindb-core

If you are an agent, see the library skill, the local docs, or llms.txt.

Query databases

You can explore public databases here. To query laminlabs/cellxgene, run:

import lamindb as ln

db = ln.DB("laminlabs/cellxgene")  # a database object for queries

→ connected lamindb: anonymous/lamindb

Get a single artifact in h5ad format:

artifact = db.Artifact.get("x4xsAnj6Uwbq7Bhq")  # a metadata object for an artifact
artifact.describe()                             # describe the metadata

Artifact: cell-census/2025-11-08/h5ads/d7476ae2-e320-4703-8304-da5c42627e71.h5ad (2025-11-08)
|   description: HTAPP-330-SMP-1082 scRNA-seq
├── uid: x4xsAnj6Uwbq7Bhq0001            run: 7FgSsR6 (annotate-register-new-release.py)
│   kind: None                           otype: AnnData                                 
│   hash: pL06B3YTzbHUdR1gAtDMlQ         size: 4.6 MB                                   
│   branch: main                         space: all                                     
│   created_at: 2026-02-17 13:39:26 UTC  created_by: zethson                            
│   n_observations: 565.0                schema: CELLxGENE AnnData of ontology_id       
├── storage/path: s3://cellxgene-data-public/cell-census/2025-11-08/h5ads/d7476ae2-e320-4703-8304-da5c42627e71.h5ad
├── Dataset features
│   ├── obs (11.0)                                                                                                 
│   │   assay_ontology_term_id         bionty.ExperimentalFactor.ontology…  EFO:0009922                            
│   │   cell_type_ontology_term_id     bionty.CellType.ontology_id          CL:0000057, CL:0000084, CL:0000115, CL…
│   │   development_stage_ontology_t…  bionty.DevelopmentalStage.ontology…  HsapDv:0000123                         
│   │   disease_ontology_term_id       bionty.Disease.ontology_id           MONDO:0007254                          
│   │   donor_id                       str                                                                         
│   │   is_primary_data                ULabel                                                                      
│   │   self_reported_ethnicity_onto…  bionty.Ethnicity.ontology_id         unknown                                
│   │   sex_ontology_term_id           bionty.Phenotype.ontology_id         PATO:0000383                           
│   │   suspension_type                ULabel                               cell                                   
│   │   tissue_ontology_term_id        bionty.Tissue.ontology_id|bionty.C…  UBERON:0002107                         
│   │   tissue_type                    ULabel                               tissue                                 
│   ├── uns (1.0)                                                                                                  
│   │   organism_ontology_term_id      bionty.Organism.ontology_id          NCBITaxon:9606                         
│   └── var (2.0)                                                                                                  
│       feature_is_filtered            bool                                                                        
│       var_index                      bionty.Gene.ensembl_gene_id[source…                                         
└── Entities
    └── .recreating_runs               Run                                  2026-02-17 13:43:36.195894+00:00, 2026…
        .ulabels                       ULabel                               cell, tissue                           
        .organisms                     bionty.Organism                      human                                  
        .tissues                       bionty.Tissue                        liver                                  
        .cell_types                    bionty.CellType                      fibroblast, T cell, endothelial cell, …
        .diseases                      bionty.Disease                       breast cancer                          
        .phenotypes                    bionty.Phenotype                     female                                 
        .experimental_factors          bionty.ExperimentalFactor            10x 3' v3                              
        .developmental_stages          bionty.DevelopmentalStage            29-year-old stage                      
        .ethnicities                   bionty.Ethnicity                     unknown
See the output.

Features are validated and annotated based on ontologies.

To explore the dataset on the UI, go here.

Access the content of the artifact via one of:

local_path = artifact.cache()  # return a local path from a cache
adata = artifact.load()        # load object into memory

! run input wasn't tracked, call `ln.track()` and re-run

! run input wasn't tracked, call `ln.track()` and re-run

Query a set of artifacts by entities using Django’s __ syntax:

db.Artifact.filter(tissues__name="liver").to_dataframe()

! truncated query result to limit=20 Artifact objects
uid key description suffix kind otype size hash n_files n_observations ... is_latest is_locked created_at branch_id created_on_id space_id storage_id run_id schema_id created_by_id
id
7158 KBW89Mf7IGcekja2hADw cell-census/2025-11-08/h5ads/fe52003e-1460-4a6... Myeloid compartment .h5ad None AnnData 700185500 GV-DXrZQeKlNidjC4P1rDA None 51552.0 ... True False 2026-02-17 13:39:54.893915+00:00 1 1 1 2 71 1573 8
7153 lfZD1fkdaALmNjIggnAw cell-census/2025-11-08/h5ads/fd072bc3-2dfb-46f... Full dataset of single-cell RNA-seq profiles f... .h5ad None AnnData 9670156174 KFGcryY_U9ed7Rb2WiSgzw None 908046.0 ... True False 2026-02-17 13:39:54.434709+00:00 1 1 1 2 71 1573 8
7133 OX929rXjWdWMP6Syru1F cell-census/2025-11-08/h5ads/fa27492b-82ff-4ab... Survey of human embryonic development (1 milli... .h5ad None AnnData 4941875651 KGmYoz3ZTb_kvswfXA9Kqg None 1001288.0 ... True False 2026-02-17 13:39:52.576072+00:00 1 1 1 2 71 1573 8
7113 Ntdynj9uX3LGLRCK2xcX cell-census/2025-11-08/h5ads/f7c1c579-2dc0-47e... Survey of human embryonic development .h5ad None AnnData 20030193091 2LDVjRD1tKtsO5eInc7wMQ None 4062980.0 ... True False 2026-02-17 13:39:50.501473+00:00 1 1 1 2 71 1573 8
7101 NiaMP8YQMbmkdOgnAa1V cell-census/2025-11-08/h5ads/f64e1be1-de15-4d2... Immune cells .h5ad None AnnData 3006586149 OWOJQ3trkCbDDt51gBuUhw None 73047.0 ... True False 2026-02-17 13:39:49.274736+00:00 1 1 1 2 71 1573 8
7072 G0fHmpO5qn0p1h8xGCV1 cell-census/2025-11-08/h5ads/f16a8f4d-bc97-43c... All - A single-cell transcriptomic atlas chara... .h5ad None AnnData 6028503643 tggg8mgi9YfV2kKVeq46rw None 356213.0 ... True False 2026-02-17 13:39:46.457830+00:00 1 1 1 2 71 1573 8
7055 CzPNijabQwkLn9Qe0000 cell-census/2025-11-08/h5ads/ef0d813e-b9b4-4d3... progressive_plasticity_during_crc_metastasis_k... .h5ad None AnnData 27750193 ShB0xEbMY0tQxr3-13Urnw None 1203.0 ... True False 2026-02-17 13:39:44.819859+00:00 1 1 1 2 71 1573 8
7029 6QKCg2OKiI8EOU2a0k7H cell-census/2025-11-08/h5ads/ec6ceff8-c8bc-488... Modeling Hepatoblastoma: Identification of Dis... .h5ad None AnnData 824372222 nCCVl3WqSsAlf1qO0H-7qw None 67110.0 ... True False 2026-02-17 13:39:42.293120+00:00 1 1 1 2 71 1573 8
7027 b22qnrisNscOA02I0001 cell-census/2025-11-08/h5ads/ec423499-4564-4ab... HTAPP-313-SMP-932 scRNA-seq .h5ad None AnnData 131448293 oLuZaQG3kG7T6xJjeKnP9Q None 12494.0 ... True False 2026-02-17 13:39:42.089943+00:00 1 1 1 2 71 1573 8
7009 q7rGFy5JQVC4FU4XT13n cell-census/2025-11-08/h5ads/e9175006-8978-441... Myeloid cells .h5ad None AnnData 649934333 oI2OI_nfWsE7AFxApiuZGA None 14072.0 ... True False 2026-02-17 13:39:40.265642+00:00 1 1 1 2 71 1573 8
7003 KPdvPezb9hjQ1HcFM7rG cell-census/2025-11-08/h5ads/e84f2780-51e8-4cf... All cells from human liver dataset .h5ad None AnnData 1026127182 TpqdNDqPv_RicLwXqDb5HA None 167598.0 ... True False 2026-02-17 13:39:39.676323+00:00 1 1 1 2 71 1573 8
6963 uLb9S4ITUolMEDfd0001 cell-census/2025-11-08/h5ads/e3a7e927-2632-457... MSK SPECTRUM - CD4+ T cells, CD8+ T cells, ILC... .h5ad None AnnData 1108715451 jzSZGYz44ROAHSnwOk8udg None 221315.0 ... True False 2026-02-17 13:39:35.853347+00:00 1 1 1 2 71 1573 8
6953 B8eo8Zjl0oZZL8PF0001 cell-census/2025-11-08/h5ads/e2824739-ea79-4ef... HTAPP-364-SMP-1321 Slide-seq .h5ad None AnnData 21637525 Or9vpeJLOur2un2b6KDIUA None 2958.0 ... True False 2026-02-17 13:39:34.903391+00:00 1 1 1 2 71 1573 8
6946 IfwUqbZcbx72i1cL0001 cell-census/2025-11-08/h5ads/e21487a3-936c-411... WSSS_F_IMMsp9838717 .h5ad None AnnData 142580981 SdSQrMcsch37NyPL4Y6ydg None 4992.0 ... True False 2026-02-17 13:39:34.203298+00:00 1 1 1 2 71 1573 8
6939 MCLIFZsK9WkW2xau0001 cell-census/2025-11-08/h5ads/e06e9bf3-81ef-434... HTAPP-944-SMP-7479 Slide-seq .h5ad None AnnData 38236263 YJC96ETJeQdVp_gTC3n2gA None 9422.0 ... True False 2026-02-17 13:39:33.450127+00:00 1 1 1 2 71 1573 8
6930 vOsBDoqtMFPl3JcmzUUv cell-census/2025-11-08/h5ads/dfdf1ae2-d624-400... Myeloid cells from human liver dataset .h5ad None AnnData 281128476 jkfzU2Cl2SecbmquyoVl3g None 40821.0 ... True False 2026-02-17 13:39:32.529754+00:00 1 1 1 2 71 1573 8
6863 x4xsAnj6Uwbq7Bhq0001 cell-census/2025-11-08/h5ads/d7476ae2-e320-470... HTAPP-330-SMP-1082 scRNA-seq .h5ad None AnnData 4863307 pL06B3YTzbHUdR1gAtDMlQ None 565.0 ... True False 2026-02-17 13:39:26.128910+00:00 1 1 1 2 71 1573 8
6845 boS3N9G4FT9FFwyYVWWf cell-census/2025-11-08/h5ads/d4cfefa0-3a35-44e... NSCLC epithelial cells .h5ad None AnnData 444983558 MFWcEJg3GvfNGs0d0jzhwg None 9778.0 ... True False 2026-02-17 13:39:24.443613+00:00 1 1 1 2 71 1573 8
6828 vvBVHvno5rrp8Rh5e682 cell-census/2025-11-08/h5ads/d224c8e0-c28e-436... Mesenchymal cells .h5ad None AnnData 332886342 PvSX3Qz0Hz8sya03r2QMXw None 8030.0 ... True False 2026-02-17 13:39:22.850106+00:00 1 1 1 2 71 1573 8
6827 tS3TXuffE5Nith5791MN cell-census/2025-11-08/h5ads/d1cbed97-d88f-495... CD45 negative cells from human liver dataset .h5ad None AnnData 194091384 kEbnQeqy4IqfvmIQJZ4mAw None 15481.0 ... True False 2026-02-17 13:39:22.760311+00:00 1 1 1 2 71 1573 8

20 rows × 22 columns

Query by features using expressions:

tissue_feature = db.Feature.get(name="tissue_ontology_term_id")
db.Artifact.filter(
    tissue_feature == db.bionty.Tissue.get(name="liver")
).to_dataframe()

! truncated query result to limit=20 Artifact objects
uid key description suffix kind otype size hash n_files n_observations ... is_latest is_locked created_at branch_id created_on_id space_id storage_id run_id schema_id created_by_id
id
7158 KBW89Mf7IGcekja2hADw cell-census/2025-11-08/h5ads/fe52003e-1460-4a6... Myeloid compartment .h5ad None AnnData 700185500 GV-DXrZQeKlNidjC4P1rDA None 51552.0 ... True False 2026-02-17 13:39:54.893915+00:00 1 1 1 2 71 1573 8
7153 lfZD1fkdaALmNjIggnAw cell-census/2025-11-08/h5ads/fd072bc3-2dfb-46f... Full dataset of single-cell RNA-seq profiles f... .h5ad None AnnData 9670156174 KFGcryY_U9ed7Rb2WiSgzw None 908046.0 ... True False 2026-02-17 13:39:54.434709+00:00 1 1 1 2 71 1573 8
7133 OX929rXjWdWMP6Syru1F cell-census/2025-11-08/h5ads/fa27492b-82ff-4ab... Survey of human embryonic development (1 milli... .h5ad None AnnData 4941875651 KGmYoz3ZTb_kvswfXA9Kqg None 1001288.0 ... True False 2026-02-17 13:39:52.576072+00:00 1 1 1 2 71 1573 8
7113 Ntdynj9uX3LGLRCK2xcX cell-census/2025-11-08/h5ads/f7c1c579-2dc0-47e... Survey of human embryonic development .h5ad None AnnData 20030193091 2LDVjRD1tKtsO5eInc7wMQ None 4062980.0 ... True False 2026-02-17 13:39:50.501473+00:00 1 1 1 2 71 1573 8
7101 NiaMP8YQMbmkdOgnAa1V cell-census/2025-11-08/h5ads/f64e1be1-de15-4d2... Immune cells .h5ad None AnnData 3006586149 OWOJQ3trkCbDDt51gBuUhw None 73047.0 ... True False 2026-02-17 13:39:49.274736+00:00 1 1 1 2 71 1573 8
7072 G0fHmpO5qn0p1h8xGCV1 cell-census/2025-11-08/h5ads/f16a8f4d-bc97-43c... All - A single-cell transcriptomic atlas chara... .h5ad None AnnData 6028503643 tggg8mgi9YfV2kKVeq46rw None 356213.0 ... True False 2026-02-17 13:39:46.457830+00:00 1 1 1 2 71 1573 8
7055 CzPNijabQwkLn9Qe0000 cell-census/2025-11-08/h5ads/ef0d813e-b9b4-4d3... progressive_plasticity_during_crc_metastasis_k... .h5ad None AnnData 27750193 ShB0xEbMY0tQxr3-13Urnw None 1203.0 ... True False 2026-02-17 13:39:44.819859+00:00 1 1 1 2 71 1573 8
7029 6QKCg2OKiI8EOU2a0k7H cell-census/2025-11-08/h5ads/ec6ceff8-c8bc-488... Modeling Hepatoblastoma: Identification of Dis... .h5ad None AnnData 824372222 nCCVl3WqSsAlf1qO0H-7qw None 67110.0 ... True False 2026-02-17 13:39:42.293120+00:00 1 1 1 2 71 1573 8
7027 b22qnrisNscOA02I0001 cell-census/2025-11-08/h5ads/ec423499-4564-4ab... HTAPP-313-SMP-932 scRNA-seq .h5ad None AnnData 131448293 oLuZaQG3kG7T6xJjeKnP9Q None 12494.0 ... True False 2026-02-17 13:39:42.089943+00:00 1 1 1 2 71 1573 8
7009 q7rGFy5JQVC4FU4XT13n cell-census/2025-11-08/h5ads/e9175006-8978-441... Myeloid cells .h5ad None AnnData 649934333 oI2OI_nfWsE7AFxApiuZGA None 14072.0 ... True False 2026-02-17 13:39:40.265642+00:00 1 1 1 2 71 1573 8
7003 KPdvPezb9hjQ1HcFM7rG cell-census/2025-11-08/h5ads/e84f2780-51e8-4cf... All cells from human liver dataset .h5ad None AnnData 1026127182 TpqdNDqPv_RicLwXqDb5HA None 167598.0 ... True False 2026-02-17 13:39:39.676323+00:00 1 1 1 2 71 1573 8
6963 uLb9S4ITUolMEDfd0001 cell-census/2025-11-08/h5ads/e3a7e927-2632-457... MSK SPECTRUM - CD4+ T cells, CD8+ T cells, ILC... .h5ad None AnnData 1108715451 jzSZGYz44ROAHSnwOk8udg None 221315.0 ... True False 2026-02-17 13:39:35.853347+00:00 1 1 1 2 71 1573 8
6953 B8eo8Zjl0oZZL8PF0001 cell-census/2025-11-08/h5ads/e2824739-ea79-4ef... HTAPP-364-SMP-1321 Slide-seq .h5ad None AnnData 21637525 Or9vpeJLOur2un2b6KDIUA None 2958.0 ... True False 2026-02-17 13:39:34.903391+00:00 1 1 1 2 71 1573 8
6946 IfwUqbZcbx72i1cL0001 cell-census/2025-11-08/h5ads/e21487a3-936c-411... WSSS_F_IMMsp9838717 .h5ad None AnnData 142580981 SdSQrMcsch37NyPL4Y6ydg None 4992.0 ... True False 2026-02-17 13:39:34.203298+00:00 1 1 1 2 71 1573 8
6939 MCLIFZsK9WkW2xau0001 cell-census/2025-11-08/h5ads/e06e9bf3-81ef-434... HTAPP-944-SMP-7479 Slide-seq .h5ad None AnnData 38236263 YJC96ETJeQdVp_gTC3n2gA None 9422.0 ... True False 2026-02-17 13:39:33.450127+00:00 1 1 1 2 71 1573 8
6930 vOsBDoqtMFPl3JcmzUUv cell-census/2025-11-08/h5ads/dfdf1ae2-d624-400... Myeloid cells from human liver dataset .h5ad None AnnData 281128476 jkfzU2Cl2SecbmquyoVl3g None 40821.0 ... True False 2026-02-17 13:39:32.529754+00:00 1 1 1 2 71 1573 8
6863 x4xsAnj6Uwbq7Bhq0001 cell-census/2025-11-08/h5ads/d7476ae2-e320-470... HTAPP-330-SMP-1082 scRNA-seq .h5ad None AnnData 4863307 pL06B3YTzbHUdR1gAtDMlQ None 565.0 ... True False 2026-02-17 13:39:26.128910+00:00 1 1 1 2 71 1573 8
6845 boS3N9G4FT9FFwyYVWWf cell-census/2025-11-08/h5ads/d4cfefa0-3a35-44e... NSCLC epithelial cells .h5ad None AnnData 444983558 MFWcEJg3GvfNGs0d0jzhwg None 9778.0 ... True False 2026-02-17 13:39:24.443613+00:00 1 1 1 2 71 1573 8
6828 vvBVHvno5rrp8Rh5e682 cell-census/2025-11-08/h5ads/d224c8e0-c28e-436... Mesenchymal cells .h5ad None AnnData 332886342 PvSX3Qz0Hz8sya03r2QMXw None 8030.0 ... True False 2026-02-17 13:39:22.850106+00:00 1 1 1 2 71 1573 8
6827 tS3TXuffE5Nith5791MN cell-census/2025-11-08/h5ads/d1cbed97-d88f-495... CD45 negative cells from human liver dataset .h5ad None AnnData 194091384 kEbnQeqy4IqfvmIQJZ4mAw None 15481.0 ... True False 2026-02-17 13:39:22.760311+00:00 1 1 1 2 71 1573 8

20 rows × 22 columns

Access sharded datasets

Access a validated, versioned collection of artifact shards in parquet format:

db = ln.DB("laminlabs/1000genomes")
collection = db.Collection.get("hVu9puwdRGskm1I6")
collection.schema.describe()

Schema: 1000_genomes_phase3_shapeit2_mvncall_integrated
|   description: These are the required columns for the VCFs ingested from 1000 genomes project from Phase 3
├── uid: us6vnu91oS5xNMpl                suffix: .parquet         
│   created_at: 2025-12-02 18:17:52 UTC  created_by: raaghavpillai
└── Features (12)
    └── name          dtype  optional  nullable  coerce  default_value
        chrom         str    ✗         ✓         ✗       unset        
        pos           int    ✗         ✓         ✗       unset        
        ref           str    ✗         ✓         ✗       unset        
        alt           str    ✗         ✓         ✗       unset        
        variant_type  str    ✗         ✓         ✗       unset        
        variant_id    str    ✗         ✓         ✗       unset        
        af            float  ✗         ✓         ✗       unset        
        eas_af        float  ✗         ✓         ✗       unset        
        eur_af        float  ✗         ✓         ✗       unset        
        afr_af        float  ✗         ✓         ✗       unset        
        amr_af        float  ✗         ✓         ✗       unset        
        sas_af        float  ✗         ✓         ✗       unset
Ad-hoc query a sharded dataset.

See the validating schema of the collection (explore):

This example uses polars to filter the collection of parquet files:

chrom = "1"
lo, hi = 150_000_000, 200_000_000

with collection.open(engine="polars") as df:
    filtered = df.filter(
        (pl.col("chrom") == chrom) & (pl.col("pos") >= lo) & (pl.col("pos") <= hi)
    ).collect()

Access a collection of artifact shards in zarr format:

db = ln.DB("laminlabs/arrayloader-benchmarks")
collection = db.Collection.get(key="Tahoe100M_zarr")
collection.artifacts.to_dataframe()

! truncated query result to limit=20 Artifact objects
uid key description suffix kind otype size hash n_files n_observations ... is_latest is_locked created_at branch_id created_on_id space_id storage_id run_id schema_id created_by_id
id
759 lByuPO4cyv1tUpPP0000 dataloader_v2/tahoe100M_2025-09-20/chunk_3.zarr None .zarr dataset AnnData 7262549993 RcKVdHtj-1KQtO1tg7CdFA 190.0 2096850.0 ... True False 2025-09-05 15:37:39.051331+00:00 1 1 1 3 215 None 4
758 LdpaMENOkIDUaazo0000 dataloader_v2/tahoe100M_2025-09-20/chunk_11.zarr None .zarr dataset AnnData 7345197698 BMF8BC-bDtHquMFSe5i8zA 190.0 2096850.0 ... True False 2025-09-05 15:35:46.605291+00:00 1 1 1 3 215 None 4
757 uufhs5xZdTNYTiHm0000 dataloader_v2/tahoe100M_2025-09-20/chunk_7.zarr None .zarr dataset AnnData 7312449805 pvajgxJS1eq1o5NH8LjcWQ 190.0 2096850.0 ... True False 2025-09-05 15:33:52.003755+00:00 1 1 1 3 215 None 4
756 tGskg24EdQlIJVdV0000 dataloader_v2/tahoe100M_2025-09-20/chunk_9.zarr None .zarr dataset AnnData 7303240195 VEZ47oEtvai4WLpy9kwkrg 190.0 2096850.0 ... True False 2025-09-05 15:31:55.885379+00:00 1 1 1 3 215 None 4
755 9whMHngwtjWJa3nl0000 dataloader_v2/tahoe100M_2025-09-20/chunk_33.zarr None .zarr dataset AnnData 7314113238 TX5OL1bmmbVMqkQLVXzUzg 190.0 2096850.0 ... True False 2025-09-05 15:30:01.287742+00:00 1 1 1 3 215 None 4
754 0o24NtMUZePxUhWe0000 dataloader_v2/tahoe100M_2025-09-20/chunk_47.zarr None .zarr dataset AnnData 7248042947 -55lbdU3DWx1ysjO10_V6Q 190.0 2096849.0 ... True False 2025-09-05 15:28:05.385504+00:00 1 1 1 3 215 None 4
753 JfvNNvUirNapG92A0000 dataloader_v2/tahoe100M_2025-09-20/chunk_35.zarr None .zarr dataset AnnData 7245468711 4ibWdIXr0VOr1lMjqbrjTg 190.0 2096850.0 ... True False 2025-09-05 15:26:09.152826+00:00 1 1 1 3 215 None 4
752 E5SzFOLgTBa9dzY50000 dataloader_v2/tahoe100M_2025-09-20/chunk_24.zarr None .zarr dataset AnnData 7305383884 Dk6EKvmd30HIe1Fm1Yur2Q 190.0 2096850.0 ... True False 2025-09-05 15:24:10.988926+00:00 1 1 1 3 215 None 4
751 KaTzrtlnLgjrja9n0000 dataloader_v2/tahoe100M_2025-09-20/chunk_44.zarr None .zarr dataset AnnData 7181484850 vAV6868V69jA2k28cdDBRg 190.0 2096849.0 ... True False 2025-09-05 15:22:17.112030+00:00 1 1 1 3 215 None 4
750 gK1OzTRBUXw5jzlS0000 dataloader_v2/tahoe100M_2025-09-20/chunk_37.zarr None .zarr dataset AnnData 7242951030 pDKJc_1vreh2_wM_dpHs9Q 190.0 2096850.0 ... True False 2025-09-05 15:20:21.075081+00:00 1 1 1 3 215 None 4
749 Nc9jrdhL8e73MpjC0000 dataloader_v2/tahoe100M_2025-09-20/chunk_4.zarr None .zarr dataset AnnData 7224742301 s7ZPcjI_MwHv6R3iOdBUTA 190.0 2096850.0 ... True False 2025-09-05 15:18:26.496678+00:00 1 1 1 3 215 None 4
748 0o4FKGK8yOMoVkgS0000 dataloader_v2/tahoe100M_2025-09-20/chunk_43.zarr None .zarr dataset AnnData 7335472463 9EPVszN6LJYERI4d8QxIoQ 190.0 2096849.0 ... True False 2025-09-05 15:16:31.587752+00:00 1 1 1 3 215 None 4
747 QyXRZNnBIxJnINok0000 dataloader_v2/tahoe100M_2025-09-20/chunk_15.zarr None .zarr dataset AnnData 7266323516 FEexIlwYDnzya57wg42Qqg 190.0 2096850.0 ... True False 2025-09-05 15:14:37.262797+00:00 1 1 1 3 215 None 4
746 2Bm8DbeqGB8aKeA60000 dataloader_v2/tahoe100M_2025-09-20/chunk_13.zarr None .zarr dataset AnnData 7273417687 oXHjCD1ZvcxKy2wnRGCS6A 190.0 2096850.0 ... True False 2025-09-05 15:12:40.380512+00:00 1 1 1 3 215 None 4
745 j7pZ9wptjrGIYKyV0000 dataloader_v2/tahoe100M_2025-09-20/chunk_21.zarr None .zarr dataset AnnData 7288341989 gou_WmQf8ZsAkN70T_xMpA 190.0 2096850.0 ... True False 2025-09-05 15:10:42.987398+00:00 1 1 1 3 215 None 4
744 U282mkIvbIxkNzDE0000 dataloader_v2/tahoe100M_2025-09-20/chunk_41.zarr None .zarr dataset AnnData 7293733483 efhi3tfhDpfQBgwRPtknoQ 190.0 2096849.0 ... True False 2025-09-05 15:08:48.438538+00:00 1 1 1 3 215 None 4
743 9pXvRdi5bS2j0rVt0000 dataloader_v2/tahoe100M_2025-09-20/chunk_14.zarr None .zarr dataset AnnData 7186241525 uYCPwG01XyoU4jliwdHk3w 190.0 2096850.0 ... True False 2025-09-05 15:06:56.680640+00:00 1 1 1 3 215 None 4
742 SvsSCpz0KIagAzA70000 dataloader_v2/tahoe100M_2025-09-20/chunk_12.zarr None .zarr dataset AnnData 7276706534 v-4KiHKct8KFc-vfUAjLqA 190.0 2096850.0 ... True False 2025-09-05 15:05:04.261178+00:00 1 1 1 3 215 None 4
741 qXwO88JVeaassVsL0000 dataloader_v2/tahoe100M_2025-09-20/chunk_39.zarr None .zarr dataset AnnData 7231159022 q2K4oKxa32obsEExQ7wWNg 190.0 2096849.0 ... True False 2025-09-05 15:03:10.018519+00:00 1 1 1 3 215 None 4
740 Xw5vR5LWjCCIT0EG0000 dataloader_v2/tahoe100M_2025-09-20/chunk_0.zarr None .zarr dataset AnnData 7319507900 mos2g1Wg4VZEHzHTjJXZZQ 190.0 2096850.0 ... True False 2025-09-05 15:01:11.223282+00:00 1 1 1 3 215 None 4

20 rows × 22 columns

Train a model on a sharded dataset.

This example uses annbatch with the pre-shuffled sharded Tahoe100M_zarr collection (explore):

import anndata as ad
import zarr
from annbatch import Loader

paths = [artifact.cache() for artifact in collection.artifacts.all()]
loader = Loader(shuffle=True, batch_size=4096, chunk_size=256, preload_nchunks=64)
loader.add_datasets(
    datasets=[ad.io.sparse_dataset(zarr.open(p)["X"]) for p in paths],
    obs=[ad.io.read_elem(zarr.open(p)["obs"]) for p in paths],
)
for batch in loader:
    pass

Create artifacts

To initialize a new database in a development directory, run:

lamin init --modules bionty  # mount module bionty

To connect to an existing database - you can create a hosted one at lamin.ai - run:

lamin login
lamin connect account/name  # tip: add flag `--here` to scope to current directory

To save a file or folder:

import lamindb as ln
# → connected lamindb: account/instance

open("sample.fasta", "w").write(">seq1\nACGT\n")        # create dataset
ln.Artifact("sample.fasta", key="sample.fasta").save()  # save dataset

! no run & transform got linked, call `ln.track()` & re-run

! did not find database on hub, but you're not logged in, so will miss private databases

Artifact(uid='6jkGCL4r8v7WTDY90000', key='sample.fasta', description=None, suffix='.fasta', kind=None, otype=None, size=11, hash='83rEPcAoBHmYiIuyBYrFKg', n_files=None, n_observations=None, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:05 UTC, is_locked=False, version_tag=None, is_latest=True)

Or via the CLI:

lamin save sample.fasta --key sample.fasta
Load it.

To load an artifact via the CLI into a local cache, run:

lamin load --key sample.fasta

Read more about the CLI: docs.lamin.ai/cli.

Trace data, code & agents

To track an agent session, run: uvx library-skills --skill lamindb.

To track a script or notebook run with source code, inputs, outputs, logs, and environment:

import lamindb as ln
# → connected lamindb: account/instance

ln.track()                                              # track code execution
open("sample.fasta", "w").write(">seq1\nACGT\n")        # create dataset
ln.Artifact("sample.fasta", key="sample.fasta").save()  # save dataset
ln.finish()                                             # mark run as finished

→ created Transform('BmfhBUrxBHXj0000', key='docs/README.ipynb'), started new Run('HBLXnJcyojww6T00') at 2026-11-02 14:17:06 UTC

• tip: to identify the notebook across renames, pass the uid: ln.track("BmfhBUrxBHXj")

→ returning artifact with same hash: Artifact(uid='6jkGCL4r8v7WTDY90000', key='sample.fasta', description=None, suffix='.fasta', kind=None, otype=None, size=11, hash='83rEPcAoBHmYiIuyBYrFKg', n_files=None, n_observations=None, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:05 UTC, is_locked=False, version_tag=None, is_latest=True); to track this artifact as an input, use: ln.Artifact.get()

! run was not set on Artifact(uid='6jkGCL4r8v7WTDY90000', key='sample.fasta', description=None, suffix='.fasta', kind=None, otype=None, size=11, hash='83rEPcAoBHmYiIuyBYrFKg', n_files=None, n_observations=None, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:05 UTC, is_locked=False, version_tag=None, is_latest=True), setting to current run

! cells [(8, 10), (22, 24)] were not run consecutively

→ finished Run('HBLXnJcyojww6T00') after 2s at 2026-11-02 14:17:08 UTC

Explore data lineage after running this snippet as a script (python create_fasta.py):

artifact = ln.Artifact.get(key="sample.fasta")  # get artifact by key
artifact.describe()      # context of the artifact
artifact.view_lineage()  # fine-grained lineage

Artifact: sample.fasta (0000)
├── uid: 6jkGCL4r8v7WTDY90000            run: HBLXnJc (docs/README.ipynb)
│   hash: 83rEPcAoBHmYiIuyBYrFKg         size: 11 B                      
│   branch: main                         space: all                      
│   created_at: 2026-11-02 14:17:05 UTC  created_by: anonymous           
└── storage/path: /home/runner/work/lamindb/lamindb/storage/.lamindb/6jkGCL4r8v7WTDY90000.fasta
_images/9a25b9f616850ceddf11b9d852113b7497462c1b1527f8cc0129666f8eb6c836.svg

Watch a mini video: youtu.be/yK3ODFZLL1A

Access run & transform.
run = artifact.run                     # get the run object
transform = artifact.run.transform     # get the transform object
run.describe()                  # context of the run

Run: HBLXnJc (docs/README.ipynb)
├── uid: HBLXnJcyojww6T00                transform: docs/README.ipynb (0000) 
│   started_at: 2026-11-02 14:17:06 UTC  finished_at: 2026-11-02 14:17:08 UTC
│   status: completed                                                        
│   branch: main                         space: all                          
│   created_at: 2026-11-02 14:17:06 UTC  created_by: anonymous               
└── environment: XMQGx0j
    │ aiobotocore==3.10.0
    │ aiohappyeyeballs==2.7.1
    │ aiohttp==3.14.5
    │ aioitertools==0.13.0
    │ …

transform.describe()  # context of the transform

Transform: docs/README.ipynb (0000)
|   description: LaminDB: Data management for traceable, multimodal AI
├── uid: BmfhBUrxBHXj0000                                     
│   hash: hclArs0p71QMvPyP4tN5cw         type: notebook       
│   branch: main                         space: all           
│   created_at: 2026-11-02 14:17:06 UTC  created_by: anonymous
└── source_code: 
    │ # %% [markdown]
    │ # [![docs](https://img.shields.io/badge/docs-yellow)](https://docs.lamin.ai) [![ …
    │ #
    │ #
    │ #
    │ # LaminDB is an open-source data management tool that makes it easy to query, tr …
    │ # Like git, LaminDB runs anywhere and captures relevant context about your work.
    │ # This includes the data flow through models and analyses, the entities and note …
    │ # It takes about a minute to install LaminDB and create a database on your lapto …
    │ #
    │ # <details>
    │ # <summary>Why?</summary>
    │ #
    │ # 1. Untraceable results cannot be trusted, especially when non-verifiable tasks …
    │ # 2. Without effective access to multimodal data, models burn tokens or fail ent …
    │ # 3. Without governing changes to data akin to governing changes to software wit …
    │ #
    │ # Especially in life sciences, hard-to-verify tasks are abundant, data formats a …
    │ #
    │ # Existing data lakehouses aren't a comprehensive solution. They only address th …
    │ #
    │ # </details>
    │ #
    │ # <img width="800" alt="lamindb-schematic" src="https://lamin-site-assets.s3.ama …
    │ #
    │ # How?
    │ #
    │ # - **lineage** → trace results across agent sessions, notebooks, scripts & work …
    │ # - **lakehouse** → manage datasets in any format (`parquet`, `zarr`, ...) with  …
    │ # - **LIMS & ELN** → unified schema-based records management with support for on …
    │ …

To track a workflow, decorate a function:

import lamindb as ln

@ln.flow()
def create_fasta(fasta_file: str = "sample.fasta"):
    open(fasta_file, "w").write(">seq1\nACGT\n")    # create dataset
    ln.Artifact(fasta_file, key=fasta_file).save()  # save dataset

if __name__ == "__main__":
    pass

Beyond what you get for scripts & notebooks, this automatically tracks function & CLI params and integrates well with established Python workflow managers: docs.lamin.ai/track. To integrate pipeline managers like Nextflow, see docs.lamin.ai/pipelines.

A richer example.

Here is a re-construction of the project of Schmidt et al. (Science, 2022):

A phenotypic CRISPRa screening result is integrated with scRNA-seq data. Here is the result of the screen input:

You can explore it here.

Annotate & query artifacts

To annotate and query by entities:

# create entities
my_label = ln.ULabel(name="My universal label").save()
my_project = ln.Project(name="My project label").save()

# annotate
artifact.ulabels.add(my_label)
artifact.projects.add(my_project)

# query
ln.Artifact.filter(ulabels=my_label, projects=my_project).to_dataframe()

! tip: pass `type` to map ulabel into a type hierarchy

! tip: pass `type` to map project into a type hierarchy
uid key description suffix kind otype size hash n_files n_observations ... is_latest is_locked created_at branch_id created_on_id space_id storage_id run_id schema_id created_by_id
id
1 6jkGCL4r8v7WTDY90000 sample.fasta None .fasta None None 11 83rEPcAoBHmYiIuyBYrFKg None None ... True False 2026-11-02 14:17:05.761+00:00 1 1 1 1 1 None 1

1 rows × 22 columns

This also works for entities imported from modules, for example, ontology terms:

import bionty as bt

# import an entity from a public ontology source, e.g., by name or an ontology ID
hek293 = bt.CellLine.from_source(name="HEK293").save()
hras = bt.Gene.from_source(ensembl_gene_id="ENSG00000174775").save()

# annotate
artifact.cell_lines.add(hek293)
artifact.genes.add(hras)

# query
ln.Artifact.filter(cell_lines=hek293, genes=hras).to_dataframe(
    include=["cell_lines__name", "genes__symbol"]
)

✓ created 1 CellLine record from Bionty matching name: 'HEK293'

✓ created 1 Organism record from Bionty matching ontology_id: 'NCBITaxon:9606'

✓ created 1 Gene record from Bionty matching ensembl_gene_id: 'ENSG00000174775'
uid key cell_lines__name genes__symbol
id
1 6jkGCL4r8v7WTDY90000 sample.fasta {HEK293} {HRAS}

To annotate & query by features:

from datetime import date

# define a feature type and features
sequences = ln.Feature(name="Sequences", is_type=True).save()
gc_content = ln.Feature(name="gc_content", dtype=float, type=sequences).save()
seq_date = ln.Feature(name="seq_date", dtype=date, type=sequences).save()

# annotate
artifact.features.set_values({
    gc_content: 0.55,
    seq_date: date.today(),
})

# query
ln.Artifact.filter(seq_date == date.today()).to_dataframe(include="features")

! tip: pass `type` to map feature into a type hierarchy
uid key gc_content seq_date
id
1 6jkGCL4r8v7WTDY90000 sample.fasta 0.55 2026-11-02

To query by auto-tracked metadata:

# by storage location and size
ln.Artifact.filter(storage__root=ln.settings.storage.root)
ln.Artifact.filter(size__gt=1e6).to_dataframe()

# by data lineage
ln.Artifact.filter(run=run).to_dataframe()
ln.Artifact.filter(run__transform=transform).to_dataframe()

# include more information in resulting dataframe
ln.Artifact.to_dataframe(include=["run__transform__key", "storage__root"])
uid key run__transform__key storage__root
id
1 6jkGCL4r8v7WTDY90000 sample.fasta docs/README.ipynb /home/runner/work/lamindb/lamindb/storage

Read more: docs.lamin.ai/organize or docs.lamin.ai/query-search

Create records & notes

You can create record types to model metadata for any entity:

# create record types
experiment_type = ln.Record(name="Experiments", is_type=True).save()
sample_type = ln.Record(name="Samples", is_type=True).save()

# create an experiment
experiment1 = ln.Record(
    name="Experiment 1",
    features={seq_date: date.today()},
    type=experiment_type
).save()

# create a sample that links to "Experiment 1" via a feature
experiment = ln.Feature(name="experiment", dtype=experiment_type).save()
sample1 = ln.Record(
    features={gc_content: 0.5, experiment: experiment1},
    type=sample_type
).save()

# export all experiments and all samples
experiment_type.to_dataframe()
sample_type.to_dataframe()

! tip: pass `type` to map record into a type hierarchy

! tip: pass `type` to map record into a type hierarchy

! tip: pass `type` to map feature into a type hierarchy

→ exporting 1 records of 'Experiments'

→ exporting 1 records of 'Samples'
experiment gc_content __lamindb_record_uid__ __lamindb_record_name__
__lamindb_record_id__
4 Experiment 1 0.5 yhl0zJlldYEnWDKp None

You can save markdown notes as records:

lamin save <topic>/<my-note.md>
Load it.

To load a record back as a markdown file, run:

lamin load https://lamin.ai/laminlabs/lamindata/record/mNDJgWFrkWQVW3ox

Watch a mini video: youtu.be/NRzVQXJaRH8

Read more: docs.lamin.ai/manage-records.

Validate datasets

Here is how you ingest a DataFrame:

import pandas as pd

df = pd.DataFrame({
    "seq_str": ["ACGT", "TGCA"],
    "gc_content": [0.55, 0.54],
    "experiment_note": ["Looks great", "Ok"],
    "seq_date": [date(2025, 10, 24), date(2025, 10, 25)],
})
ln.Artifact.from_dataframe(df, key="my_datasets/sequences.parquet").save()  # no validation

Artifact(uid='eVGzEEkpGOIkNpHy0000', key='my_datasets/sequences.parquet', description=None, suffix='.parquet', kind='dataset', otype='DataFrame', size=3290, hash='lsS0KCvEUfy46pY1OxBnXA', n_files=None, n_observations=2, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:16 UTC, is_locked=False, version_tag=None, is_latest=True)

Let’s now define a schema that validates the columns of the dataframe against the feature type sequences that we defined above:

ln.Feature(name="seq_str", dtype=str, type=sequences).save()
ln.Feature(name="experiment_note", dtype=str, type=sequences).save()
schema = ln.Schema(itype=sequences).save()

If we pass it from_dataframe(), the resulting artifact is validated and auto-anntotated:

artifact = ln.Artifact.from_dataframe(
    df,
    key="my_datasets/sequences.parquet",
    schema=schema,
).save()
artifact.describe()

→ returning artifact with same hash: Artifact(uid='eVGzEEkpGOIkNpHy0000', key='my_datasets/sequences.parquet', description=None, suffix='.parquet', kind='dataset', otype='DataFrame', size=3290, hash='lsS0KCvEUfy46pY1OxBnXA', n_files=None, n_observations=2, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:16 UTC, is_locked=False, version_tag=None, is_latest=True); to track this artifact as an input, use: ln.Artifact.get()

→ loading artifact into memory for validation

Artifact: my_datasets/sequences.parquet (0000)
├── uid: eVGzEEkpGOIkNpHy0000  kind: dataset                      
│   otype: DataFrame           hash: lsS0KCvEUfy46pY1OxBnXA       
│   size: 3.2 KB               branch: main                       
│   space: all                 created_at: 2026-11-02 14:17:16 UTC
│   created_by: anonymous      n_observations: 2                  
│   schema: wVHoOve                                               
├── storage/path: /home/runner/work/lamindb/lamindb/storage/.lamindb/eVGzEEkpGOIkNpHy0000.parquet
└── Dataset features
    └── columns (4 Feature[Rne0aQToA…                                                                              
        experiment_note                str                                                                         
        gc_content                     float                                                                       
        seq_date                       date                                                                        
        seq_str                        str

You can filter for datasets by schema and then launch distributed queries or batch load distributed datasets. For tables, see: docs.lamin.ai/tables. For arrays, see: docs.lamin.ai/arrays.

Watch a mini video: youtu.be/Ji6E7hTnReQ

To validate and auto-annotate an AnnData, use a feature type for the obs columns and Ensembl gene ids for var:

import anndata as ad
import bionty as bt
import numpy as np
import pandas as pd

# define the schema
cells = ln.Feature(name="Cells", is_type=True).save()
ln.Feature(name="cell_type_by_model", dtype=bt.CellType, type=cells).save()
obs_schema = ln.Schema(itype=cells).save()
var_schema = ln.Schema(itype=bt.Gene.ensembl_gene_id).save()
anndata_schema = ln.Schema(
    otype="AnnData", slots={"obs": obs_schema, "var.T": var_schema}
).save()

# define the AnnData object
adata = ad.AnnData(
    X=np.ones((21, 3)),
    obs=pd.DataFrame({"cell_type_by_model": ["T cell", "B cell", "T cell"] * 7}),
    var=pd.DataFrame(
        index=["ENSG00000153563", "ENSG00000010610", "ENSG00000170458"]
    ),
)

# validate, annotate, and ingest the AnnData object
artifact = ln.Artifact.from_anndata(
    adata,
    key="my_datasets/scrna.h5ad",
    schema=anndata_schema,
).save()
artifact.describe()

! tip: pass `type` to map feature into a type hierarchy

→ loading artifact into memory for validation

/opt/hostedtoolcache/Python/3.14.9/x64/lib/python3.14/functools.py:982: ImplicitModificationWarning: Transforming to str index.
  return dispatch(args[0].__class__)(*args, **kw)
/opt/hostedtoolcache/Python/3.14.9/x64/lib/python3.14/re/_compiler.py:320: RuntimeWarning: coroutine '_wait_for_close' was never awaited
  break
RuntimeWarning: Enable tracemalloc to get the object allocation traceback

✓ added 2 records from_public with bionty.CellType for "cell_type_by_model": 'T cell', 'B cell'

✓ added 3 records from_public with bionty.Gene for "columns": 'ENSG00000153563', 'ENSG00000010610', 'ENSG00000170458'

Artifact: my_datasets/scrna.h5ad (0000)
├── uid: sXshiZrji4nkdQpG0000  kind: dataset                      
│   otype: AnnData             hash: O2ePNFFY9txr66huIosUng       
│   size: 22.0 KB              branch: main                       
│   space: all                 created_at: 2026-11-02 14:17:20 UTC
│   created_by: anonymous      n_observations: 21                 
│   schema: HCaB0zc                                               
├── storage/path: /home/runner/work/lamindb/lamindb/storage/.lamindb/sXshiZrji4nkdQpG0000.h5ad
├── Dataset features
│   ├── obs (1 Feature[xcM955jzl97N])                                                                              
│   │   cell_type_by_model             bionty.CellType                      B cell, T cell                         
│   └── var.T (3 bionty.Gene.ensembl…                                                                              
│       CD14                           num                                                                         
│       CD4                            num                                                                         
│       CD8A                           num                                                                         
└── Entities
    └── .cell_types                    bionty.CellType                      T cell, B cell

To validate a SpatialData or any other array-like dataset, you need to construct a Schema. You can do this by composing simple pandera-style schemas: docs.lamin.ai/curate.

Use branching & versioning

LaminDB versions transforms, artifacts, and collections. If you edit and run the create_fasta.py script, you’ll automatically create a new version of the transform and the sample.fasta artifact.

The edited script.
# create_fasta.py
import lamindb as ln

ln.track()
open("sample.fasta", "w").write(">seq1\nTGCA\n")  # a new sequence
ln.Artifact("sample.fasta", key="sample.fasta", features={"experiment": "Experiment 1"}).save()  # annotate with the new experiment
ln.finish()

→ found notebook docs/README.ipynb, making new version -- anticipating changes

→ created Transform('BmfhBUrxBHXj0001', key='docs/README.ipynb'), started new Run('lPDYF2sPdmX3CkmC') at 2026-11-02 14:17:20 UTC

• tip: to identify the notebook across renames, pass the uid: ln.track("BmfhBUrxBHXj")

→ creating new artifact version for key 'sample.fasta' in storage '/home/runner/work/lamindb/lamindb/storage'

! cells [(8, 10), (22, 24)] were not run consecutively

→ returning artifact with same hash: Artifact(uid='yBjw53iCABRo0yxR0000', key=None, description='Report of run HBLXnJcyojww6T00', suffix='.html', kind='__lamindb_run__', otype=None, size=361091, hash='apf6RBJ_qMEGp1HpDvHm7Q', n_files=None, n_observations=None, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:08 UTC, is_locked=False, version_tag=None, is_latest=True); to track this artifact as an input, use: ln.Artifact.get()

! run was not set on Artifact(uid='yBjw53iCABRo0yxR0000', key=None, description='Report of run HBLXnJcyojww6T00', suffix='.html', kind='__lamindb_run__', otype=None, size=361091, hash='apf6RBJ_qMEGp1HpDvHm7Q', n_files=None, n_observations=None, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=1, run_id=None, schema_id=None, created_by_id=1, created_at=2026-11-02 14:17:08 UTC, is_locked=False, version_tag=None, is_latest=True), setting to current run

! updated description from Report of run HBLXnJcyojww6T00 to Report of run lPDYF2sPdmX3CkmC

! returning transform  with same hash & key: Transform(uid='BmfhBUrxBHXj0000', key='docs/README.ipynb', description='LaminDB: Data management for traceable, multimodal AI', kind='notebook', hash='hclArs0p71QMvPyP4tN5cw', reference=None, reference_type=None, environment=None, plan=None, branch_id=1, created_on_id=1, space_id=1, run_id=None, created_by_id=1, created_at=2026-11-02 14:17:06 UTC, is_locked=False, version_tag=None, is_latest=False)

! run was not set on Transform(uid='BmfhBUrxBHXj0000', key='docs/README.ipynb', description='LaminDB: Data management for traceable, multimodal AI', kind='notebook', hash='hclArs0p71QMvPyP4tN5cw', reference=None, reference_type=None, environment=None, plan=None, branch_id=1, created_on_id=1, space_id=1, run_id=None, created_by_id=1, created_at=2026-11-02 14:17:06 UTC, is_locked=False, version_tag=None, is_latest=False), setting to current run

• new latest Transform version is: BmfhBUrxBHXj0000

→ finished Run('lPDYF2sPdmX3CkmC') after 1s at 2026-11-02 14:17:21 UTC

artifact_latest = ln.Artifact.get(key="sample.fasta")  # pass version for a previous version: ln.Artifact.get(key="sample.fasta", version="1.0")
artifact_latest.versions.to_dataframe()                # all versions of that artifact
artifact_latest.run.transform.versions.to_dataframe()  # all versions of the transform that created the artifact
uid key description kind source_code hash reference reference_type version_tag is_latest is_locked created_at branch_id created_on_id space_id environment_id plan_id run_id created_by_id
id
1 BmfhBUrxBHXj0000 docs/README.ipynb LaminDB: Data management for traceable, multim... notebook # %% [markdown]\n# [![docs](https://img.shield... hclArs0p71QMvPyP4tN5cw None None None True False 2026-11-02 14:17:06.082+00:00 1 1 1 None None None 1

If you create a branch and switch to it as in git, you’ll create new objects and new versions of objects on it:

lamin switch -c my_branch

To merge a contribution branch into main, run:

lamin switch main  # switch to the main branch
lamin merge my_branch  # merge contribution branch into main

Read more: docs.lamin.ai/manage-changes.

Watch a mini video: youtu.be/rzRwcMj6-fc

Share datasets

To share data in a lineage-aware way, transfer objects from a source database to your default database:

db = ln.DB("laminlabs/lamindata")
artifact = db.Artifact.get(key="example_datasets/mini_immuno/dataset1.h5ad")
artifact.save()

• tip: to work with the additional module (pertdb) of database laminlabs/lamindata, configure your environment for it: lamin settings modules set bionty,pertdb

/opt/hostedtoolcache/Python/3.14.9/x64/lib/python3.14/inspect.py:2689: RuntimeWarning: coroutine '_wait_for_close' was never awaited
  def __init__(self, name, kind, *, default=_empty, annotation=_empty):
RuntimeWarning: Enable tracemalloc to get the object allocation traceback

→ Artifact example_datasets/mini_immuno/dataset1.h5ad: 5 transferred, 0 already on target

Artifact(uid='9K1dteZ6Qx0EXK8g0000', key='example_datasets/mini_immuno/dataset1.h5ad', description='Flow cytometry readouts on invitro cell culture', suffix='.h5ad', kind='dataset', otype='AnnData', size=31672.0, hash='FB3CeMjmg1ivN6HDy6wsSg', n_files=None, n_observations=3.0, extra_data=None, branch_id=1, created_on_id=1, space_id=1, storage_id=2, run_id=3, schema_id=8, created_by_id=3, created_at=2025-07-29 12:27:25 UTC, is_locked=False, version_tag=None, is_latest=True)

This is zero-copy for the artifact’s data in storage. Read more: docs.lamin.ai/transfer.

Manage ontologies

You can use Record to build your ELN & LIMS, your own ontologies, and even a knowledge graph with slow graph queries. If you instead want to build on public biological ontologies: bionty gives you >20 public ontologies so that you don’t have to build ontologies for basic biological entities from scratch. For example, the Gene registry was used to validate the ENSG ids in the AnnData object above.

Here is how you import a public ontology into the CellType registry:

import bionty as bt

bt.CellType.import_source()  # import the default ontology
bt.CellType.to_dataframe()   # your extensible cell type ontology in a simple registry

✓ import is completed!

! truncated query result to limit=20 CellType objects
uid name ontology_id abbr synonyms description is_locked created_at branch_id created_on_id space_id created_by_id run_id source_id
id
3545 1ChUsEzDZXWW4B beam B cell, human CL:7770006 None nan A Trabecular Meshwork Cell Within The Eye'S Tr... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3544 5xoxfxIf7WrLdU beam cell CL:7770005 None nan A Trabecular Meshwork Cell That Is Part Of The... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3543 2j5mhhFoV2vBDV suprabasal cell CL:7770004 None nan An Epithelial Cell That Resides In The Layer(S... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3542 RBCFqAmkM1oaaZ beam A cell CL:7770003 None nan A Beam Cell Within The Eye'S Trabecular Meshwo... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3541 79Ow7BGPRP018I juxtacanalicular tissue cell CL:7770002 None nan A Trabecular Meshwork Cell Of The Juxtacanalic... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3540 4qJMS0d5FyIXQK OB FRMD7 GABA GABAergic neuron (Primate) CL:4310148 None OB FRMD7 GABA A Gabaergic Neuron Of The Primates Brain. Thes... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3539 6iU1Q2FIIkrgND OB Dopa-GABA OB-Dopa-GABA (Primate) CL:4310147 None OB Dopa-GABA A Ob-Dopa-Gaba Of The Primates Brain. These Ce... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3538 100qUn3IH1Ksw2 AMY-SLEA-BNST GABA GABAergic interneuron (Prim... CL:4310146 None AMY-SLEA-BNST GABA A Gabaergic Interneuron Of The Primates Brain.... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3537 QJ8929f49Ncfrf AMY-SLEA-BNST D1 GABA GABAergic interneuron (P... CL:4310145 None AMY-SLEA-BNST D1 GABA A Gabaergic Interneuron Of The Primates Brain.... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3536 2RruqlADchF4D3 VTR-HTH Glut glutamatergic neuron of the basal... CL:4310144 None F M Glut|VTR-HTH Glut A Glutamatergic Neuron Of The Basal Ganglia Of... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3535 44qrwytpXARNMz ZI-HTH GABA GABAergic interneuron (Primate) CL:4310143 None ZI-HTH GABA A Gabaergic Interneuron Of The Primates Brain.... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3534 3dVBqPp88IUIib STRv D2 MSN nucleus accumbens shell and olfact... CL:4310138 None STRv D2 MSN|D2-Shell/OT A Nucleus Accumbens Shell And Olfactory Tuberc... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3533 4RRtGKe1oGoVGV STRv D1 NUDAP MSN D1-NUDAP medium spiny neuron... CL:4310137 None D1-NUDAP|STRv D1 NUDAP MSN A D1-Nudap Medium Spiny Neuron Of The Primates... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3532 1Tw4GET7C0W2Az STRv D1 MSN nucleus accumbens shell and olfact... CL:4310136 None D1-Shell/OT|STRv D1 MSN A Nucleus Accumbens Shell And Olfactory Tuberc... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3531 3taUBSHOL3ffx3 STR Cholinergic GABA striatal cholinergic-GABA... CL:4310135 None STR Cholinergic GABA A Striatal Cholinergic-Gabaergic Neuron Of The... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3530 2OzOl5s6HeWYYM STRd D2 Striosome MSN striosomal D2 medium spi... CL:4310134 None D2-Striosome|STRd D2 Striosome MSN A Striosomal D2 Medium Spiny Neuron Of The Pri... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3529 3ZypczMtxf4KQu STRd D2 StrioMat Hybrid MSN indirect pathway m... CL:4310133 None STRd D2 StrioMat Hybrid MSN A Indirect Pathway Medium Spiny Neuron Of The ... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3528 2Mk5r9Xsi24yLc STRd D2 Matrix MSN matrix D2 medium spiny neur... CL:4310132 None D2-Matrix|STRd D2 Matrix MSN A Matrix D2 Medium Spiny Neuron Of The Primate... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3527 5e4cn19DcnuNH0 STR D1D2 Hybrid MSN D1/D2-hybrid medium spiny ... CL:4310131 None STR D1D2 Hybrid MSN|D1/D2 Hybrid A D1/D2-Hybrid Medium Spiny Neuron Of The Prim... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26
3526 67anmsVZv7HmGa STRd D1 Striosome MSN striosomal D1 medium spi... CL:4310130 None D1-Striosome|STRd D1 Striosome MSN A Striosomal D1 Medium Spiny Neuron Of The Pri... False 2026-11-02 14:17:29.075+00:00 1 1 1 1 None 26

You can then create objects, e.g. for labeling, analogous to ULabel or Project:

t_cell = bt.CellType.get(name="T cell")  # get a T cell label
artifact.cell_types.add(t_cell)          # annotate an artifact

Read more: docs.lamin.ai/manage-ontologies.

Watch a mini video: youtu.be/3vpWjHj3Kw8