Cargo CLI — Storage

Data layer management: inspecting and modifying models, datasets, columns, relationships, unification, and records, and running SQL queries against workspace storage.

See references/response-shapes.md for full JSON response structures. See references/troubleshooting.md for common errors and how to fix them. See references/examples/models.md for model CRUD, DDL inspection, and schema discovery examples. See references/examples/datasets.md for dataset listing and navigation examples. See references/examples/columns.md for column creation and management examples. See references/examples/queries.md for storage query execute / storage query download SQL examples (WHERE, aggregations, joins, pagination, exports). See references/examples/ingest-webhook.md for ingest (webhook-fed) models — deriving the webhook URL and POSTing records.

Bootstrap

Already signed in (cargo-ai whoami returns a workspace)? Skip to the next section.

npm install -g @cargo-ai/cli            # no global install? prefix every command with `npx @cargo-ai/cli`
cargo-ai login --email you@company.com  # emailed code, no browser; creates the account on first use
                                        # alternatives: --oauth (browser) · --token <api-token> (CI)
cargo-ai whoami                         # confirm the active workspace before any write

Every command prints JSON to stdout; failures exit non-zero with {"errorMessage": "..."}. Anything that creates a run or a batch is async — pass --wait-until-finished or poll the matching get. When the full skill bundle is installed, ../cargo/references/prerequisites.md adds the CLI version pin, token scopes, and the admin-only surface.

Discover resources first

Always list before inspecting or modifying.

cargo-ai storage dataset list              # all datasets (uuid, slug)
cargo-ai storage model list                # all models (uuid, name, slug, columns, datasetUuid)
# `model list` takes no flags — filter its output instead:
cargo-ai storage model list | jq '[.models[] | select(.datasetUuid == "<uuid>")]' 

Retrieve in the UI: models live at app.getcargo.io/workspaces/<WORKSPACE_UUID>/models/<MODEL_UUID>. Get <WORKSPACE_UUID> from cargo-ai whoami under workspace.uuid.

Quick reference

cargo-ai storage model list
cargo-ai storage model get <model-uuid>
cargo-ai storage model get-ddl <model-uuid>
cargo-ai storage dataset list
cargo-ai storage column list --model-uuid <uuid>
cargo-ai storage relationship list
cargo-ai storage record list --model-uuid <uuid>
cargo-ai storage record create-bulk --model-uuid <uuid> --records '[{"data":{...}}]'
cargo-ai storage model preview --dataset-uuid <uuid> --slug <extractor-slug> --config '{...}'
cargo-ai storage query execute "SELECT * FROM default.companies LIMIT 10"
cargo-ai storage query download --query "SELECT * FROM default.companies"

Models

Models are structured tables in your workspace (e.g. Companies, Contacts).

# List all models
cargo-ai storage model list

# List models in a dataset — every model carries `datasetUuid`, and
# `model list` has no flags of its own, so filter client-side
cargo-ai storage model list | jq '[.models[] | select(.datasetUuid == "<uuid>")]' 

# Get a single model (includes columns)
cargo-ai storage model get <model-uuid>

# Get the DDL (full schema, table name and SQL dialect)
cargo-ai storage model get-ddl <model-uuid>
# → Useful for column discovery and SQL dialect (BigQuery vs Snowflake) before writing queries

# Create a model
cargo-ai storage model create \
  --slug contacts \
  --name "Contacts" \
  --dataset-uuid <uuid> \
  --extractor-slug <extractor-slug> \
  --config '{}'

# Update a model (--position moves its node on the app's data canvas)
cargo-ai storage model update --uuid <model-uuid> --name "New Name"
cargo-ai storage model update --uuid <model-uuid> --position '{"x":0,"y":0}'

# Remove a model
cargo-ai storage model remove <model-uuid>

# Is a slug taken in this dataset? → {"exists": true|false}
cargo-ai storage model exists-by-slug --dataset-uuid <uuid> --slug contacts

Dry-run an extractor config before creating the model

model preview and model preview-count run an extractor's config without creating anything. --slug is the extractor slug (not a model slug), and --dataset-uuid is the connector's dataset (kind: "connector") — the dataset names the connector.

# Sample rows + the extractor's total, for extractors that preview records
cargo-ai storage model preview \
  --dataset-uuid <connector-dataset-uuid> --slug <extractor-slug> --config '{...}'

# Count only, for extractors that preview a count
cargo-ai storage model preview-count \
  --dataset-uuid <connector-dataset-uuid> --slug <extractor-slug> --config '{...}'

Each extractor supports one of the two (preview: "records" or "count" on the integration's extractor), and the other answers count: 0 rather than an error — a 0 is not "nothing matches" until you've tried both. preview asks the extractor for a short dry page; on a credits connector it bills whatever that page reports, which is nothing for extractors that zero their dry fetch (Store Leads fetchDomains, for one) and per item for the rest. Check the extractor's playbook before previewing a priced one. An invalid config comes back as invalidConfig with the validator's message — the cheapest way to debug a config before model create.

Querying: Use cargo-ai storage query execute "<sql>" (or storage query download --query "<sql>" for full exports) to run SQL against storage. Tables are referenced as <datasetSlug>.<modelSlug> (e.g. default.companies) and rewritten to the underlying storage table under the hood. See Query with SQL below.

Ingest models (webhook-fed)

A model whose extractor has mode.kind === "ingest" — http.listenHook and friends — is filled by pushing records to Cargo. The app shows a "Webhook URL" on the model settings screen; no CLI command or API field returns it, but it's assembled from values the CLI already exposes:

<baseUrl>/v1/models/<model-uuid>/records/ingest?token=<api-token>

MODEL_UUID=<model-uuid>
BASE=$(cargo-ai whoami | jq -r '.baseUrl')
TOKEN=$(cargo-ai workspaceManagement token list | jq -r '.tokens[0].token')
echo "$BASE/v1/models/$MODEL_UUID/records/ingest?token=$TOKEN"

Not for workflows. A Cargo workflow writes to a model with the native modelUpsert / modelInsert action (see cargo-orchestration → references/nodes.md → "Storage"). An HTTP node calling this URL costs an extra node, a payload script, and an API token pasted into the node config. The webhook is for systems outside Cargo.

Check the extractor's mode first — when it reports "autoIngest": true (calendly, smartlead, instantlyV2, heyReach, cargoSignals, explorium's listen extractors) Cargo registers the hook with the provider itself and the URL must not be handed out. Full flow, payload shapes, and limits: references/examples/ingest-webhook.md.

Datasets

Datasets are logical groupings of models.

# List all datasets
cargo-ai storage dataset list

# Get a single dataset
cargo-ai storage dataset get <dataset-uuid>

Columns

Columns define the schema of a model.

# List columns for a model
cargo-ai storage column list --model-uuid <uuid>

# Create a column
cargo-ai storage column create \
  --model-uuid <uuid> \
  --column '{"slug":"my_column","type":"string","label":"My Column","kind":"custom"}'

# Update a column (pass the full column object — columns are identified by slug, not UUID)
cargo-ai storage column update \
  --model-uuid <uuid> \
  --column '{"slug":"my_column","type":"string","label":"Updated Label","kind":"custom"}'

# Remove a column
cargo-ai storage column remove --model-uuid <uuid> --column-slug <slug>

# Reorder a column (move to a specific index)
cargo-ai storage column reorder --model-uuid <uuid> --column-slug <slug> --to-index 2

# Is a slug taken on this model? → {"exists": true|false}
cargo-ai storage column exists-by-slug --model-uuid <uuid> --column-slug <slug>

# Values a column holds ([{label, value}]) — what a filter on it can match
cargo-ai storage column autocomplete --model-uuid <uuid> \
  --column '{"slug":"industry","type":"string","label":"Industry","kind":"custom"}'

# Write custom-column values onto existing records (custom column slugs only;
# a model's own extracted fields are refused)
cargo-ai storage column insert-custom-values --model-uuid <uuid> --id <record-id> --data '{"ai_fit_score":82}'
cargo-ai storage column insert-custom-values-bulk --model-uuid <uuid> \
  --records '[{"id":"rec_1","data":{"ai_fit_score":82}},{"id":"rec_2","data":{"ai_fit_score":40}}]'

insert-custom-values is how a value computed outside Cargo (a score from your own pipeline, a manual tag) lands on a connector-synced model: the sync owns the extracted fields, custom columns are yours. Create the column first.

Column types: string, number, boolean, date, object, array, vector, any.

Column kinds: custom (user-defined), computed (expression over other columns), metric (aggregated from a related model), lookup (single field pulled from a related model via a join).

Preview what you built

A column list doesn't tell the user whether the model is right — rows do. Two checkpoints (the pack-wide convention lives in ../cargo/references/interaction.md §4):

1. Right after model create / column create — show the schema, not rows. A new model is empty; a LIMIT 10 here returns nothing and reads as failure. Echo the columns as a compact table instead (column, type, what will fill it).

2. As soon as data lands — show the rows. After a batch, play, or import writes into the model, preview it:

cargo-ai storage query execute \
  "SELECT * FROM <dataset-slug>.<model-slug> LIMIT 10"

Show ~10 rows and only the columns that carry meaning. Storage queries are free, so this costs nothing but a few lines of output — and it's the first moment the user can actually see what they built. When a play fills a new column, preview that column next to the record's identifying fields (name, domain) so filled vs. empty is obvious.

If the preview comes back empty or all-null when it shouldn't, that's a finding — surface it rather than reporting the write as a success. See cargo-diagnostics to trace why.

Relationships

Relationships link models together (e.g. Contacts belong to Companies). They are authored from the CLI, not just the UI.

relationship list takes no flags — it returns every relationship in the workspace. Filter client-side on fromModelUuid / toModelUuid.

cargo-ai storage relationship list

relationship set replaces the dataset's whole relationship set. It takes a dataset and the complete list that should exist within it: entries carrying a uuid are updated, entries without one are created, and any existing relationship whose uuid is absent from the payload is deleted. Sending one relationship to a dataset that has five removes the other four. Always list first, then send back the full array with your addition:

cargo-ai storage relationship set \
  --dataset-uuid <dataset-uuid> \
  --relationships '[
    {"uuid":"<existing-uuid>","fromModelUuid":"<contacts-uuid>","fromColumnSlug":"account_id","fromPropertySlug":null,"toModelUuid":"<companies-uuid>","toColumnSlug":"id","toPropertySlug":null,"fromSelectedColumnSlugs":null,"toSelectedColumnSlugs":null,"relation":"manyToOne"},
    {"fromModelUuid":"<deals-uuid>","fromColumnSlug":"company_id","fromPropertySlug":null,"toModelUuid":"<companies-uuid>","toColumnSlug":"id","toPropertySlug":null,"fromSelectedColumnSlugs":null,"toSelectedColumnSlugs":null,"relation":"manyToOne"}
  ]'

fromPropertySlug, toPropertySlug, fromSelectedColumnSlugs and toSelectedColumnSlugs are required on every entry (pass null when unused); leaving one out fails validation with an errorMessage. Copying the entries from relationship list keeps them.

relation is oneToOne, manyToOne, or oneToMany. Both models must live in the dataset you pass — relationships never span datasets, so fromDatasetUuid and toDatasetUuid on the response always equal --dataset-uuid.

Failure reasons: datasetNotFound; invalidRelationships (a column slug or model UUID that doesn't resolve, or a duplicate — including the same pair stated in reverse); modelNotCompatible (see below).

Unify models refuse manual relationships. In the native dataset, a unify model's relationships are generated during sync, so naming one as fromModelUuid or toModelUuid returns modelNotCompatible. Those auto-generated rows are also excluded from the replace above, so a set call cannot delete them.

Unification

Unification is what merges records from several source models into one canonical account/contact — and it is configurable from the CLI, via --unification on model update. Pass null to clear it.

# Connector-driven: the integration decides how records unify
cargo-ai storage model update --uuid <model-uuid> --unification '{"source":"integration"}'

# Custom: you name the type, the matching keys, and optionally a parent
cargo-ai storage model update --uuid <model-uuid> --unification '{
  "source": "custom",
  "type": "account",
  "uniqueColumns": [{"slug":"domain","reference":"domain"}],
  "selectedColumnSlugs": ["name","industry","employee_count"],
  "parent": {"kind":"model","columnSlug":"account_id","parentModelUuid":"<accounts-uuid>"}
}'

Writing the config does not recompute anything. The unified rows are rebuilt by the model's sync run, so follow the update with a run and poll it:

cargo-ai storage run create --model-uuid <model-uuid>
cargo-ai storage run list --model-uuid <model-uuid>

run create is refused with upToDate when the last successful sync is inside the extractor's minimum interval, and with alreadyRunning while one is in flight. Two flags override that:

• --is-force true — cancels an in-flight sync (waiting up to 60 s for it to stop) and starts a new one regardless of freshness.
• --is-reset true — clears the extractor's incremental cursor and rebuilds the model from the source, as a first sync would. On a per-item-priced extractor that re-bills the whole result set, so quote it before running.

Get the current config from storage model get <uuid> → unification (null when the model doesn't unify). Once the run finishes, check the row count with storage query execute before treating the change as done — a too-narrow uniqueColumns under-merges and a too-broad one collapses distinct entities, and both look like a successful run.

Records

# List records in a model (sortable on _id, _title, or _emitted_at — the last
# only on models built from ingested records)
cargo-ai storage record list --model-uuid <uuid>
cargo-ai storage record list --model-uuid <uuid> --limit 100 --sort-column-slug _emitted_at --sort-kind desc
cargo-ai storage record get --model-uuid <uuid> --id <record-id>

# Write records — one at a time, or up to 1,000 per bulk call
cargo-ai storage record create --model-uuid <uuid> --data '{"name":"Ada","email":"ada@acme.com"}'
cargo-ai storage record update --model-uuid <uuid> --id <record-id> --data '{"status":"done"}'
cargo-ai storage record remove --model-uuid <uuid> --id <record-id>
cargo-ai storage record create-bulk --model-uuid <uuid> --records '[{"data":{"name":"Ada"}},{"data":{"name":"Lin"}}]'
cargo-ai storage record update-bulk --model-uuid <uuid> --records '[{"id":"rec_1","data":{"status":"done"}}]'
cargo-ai storage record remove-bulk --model-uuid <uuid> --ids '["rec_1","rec_2"]'

Record writes go to native models and ingest models only. On an ingest model a write takes the same path as a webhook POST — through the extractor, so its per-item credits apply and its payload validation can reject the batch (invalidRecords). A fetch-mode model (one a connector syncs) refuses them with integrationNotCompatible: its rows belong to the sync. To annotate synced rows, use column insert-custom-values instead. Inside a workflow, write with the native modelUpsert / modelInsert action rather than shelling out.

For advanced record queries (filtering, sorting, pagination), use segmentation segment fetch from the cargo-segmentation skill.

Query with SQL

Run SQL against workspace storage with storage query execute. Tables are referenced as <datasetSlug>.<modelSlug> (e.g. default.companies) and rewritten to the underlying storage table under the hood — no DDL lookup is needed for the table name.

cargo-ai storage query execute \
  "SELECT name, domain FROM default.companies LIMIT 10"
# → { "isRefreshing": false, "rows": [...] } on success; non-zero exit with { "errorMessage": "..." } on error

For full exports, use storage query download — it returns signed URLs (urls, an array) to CSV (default) or Parquet files:

cargo-ai storage query download \
  --query "SELECT name, domain, revenue FROM default.companies ORDER BY revenue DESC"

cargo-ai storage query download \
  --query "SELECT * FROM default.companies" --format parquet

Get column names from storage column list --model-uuid <uuid> (storage names: added columns carry a custom__ / computed__ / metric__ / lookup__ prefix) (or run storage model get-ddl <model-uuid> for the full schema and SQL dialect). Page through large result sets with LIMIT / OFFSET directly in the SQL.

See references/examples/queries.md for WHERE clauses, aggregations, joins, date queries, pagination, and the failure shapes returned on error.

Help

Every command supports --help:

cargo-ai storage model list --help
cargo-ai storage column create --help
cargo-ai storage relationship set --help
cargo-ai storage query execute --help
cargo-ai storage query download --help