Install Jentic One Beta

Connect the Explore API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Explore API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fopendatasoft.com%2Fopendatasoft" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fopendatasoft.com%2Fopendatasoft" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Explore API.

Search and paginate through every dataset on the portal via /catalog/datasets with full-text and ODSQL filters

Inspect dataset metadata and schema fields through /catalog/datasets/{dataset_id}

Query records inside any dataset with /catalog/datasets/{dataset_id}/records using ODSQL where, select, and group_by clauses

Stream catalog or dataset exports in CSV, GeoJSON, GPX, and other formats via /catalog/exports/{format} and /catalog/datasets/{dataset_id}/exports/{format}

GET STARTED

Start building with Explore API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use Explore API for, with concrete tasks.

★ Self-Service Dataset Portal Frontend

Build a public-facing dataset browser on top of an Opendatasoft portal that lets users search the catalog, inspect schemas, preview records, and export in multiple formats. The Explore API v2 covers all four operations with consistent pagination and ODSQL filtering, removing the need to build a separate query layer per dataset.

Call /catalog/datasets with where="theme like 'transport'" and return the top 20 dataset titles and IDs.

Geospatial Data Export

Export records from any geo-enabled dataset directly as GeoJSON or GPX through /catalog/datasets/{dataset_id}/exports/{format}. Mapping applications can fetch ready-to-render features without building a transformation layer, and ODSQL where clauses limit the export to the bounding box or time window required.

Export dataset bicycle-counters as GeoJSON via /catalog/datasets/bicycle-counters/exports/geojson with where="date >= '2026-01-01'".

Catalog-Wide Analytics

Run analytics over an entire portal - counts of datasets per theme, per publisher, per modification month - using /catalog/facets and dataset metadata endpoints. Useful for portal owners producing monthly reports on coverage and freshness without exporting the catalog to a separate database.

Call /catalog/facets with facet="publisher" and return the top 10 publishers by dataset count.

Agent-Driven Open Data Lookups

An AI agent answering questions about a city or organisation's open data can use Jentic to discover the Explore API record-query operation, then run an ODSQL query against the matching dataset to ground its answer. Jentic returns the input schema so the agent constructs valid ODSQL where clauses without trial-and-error.

Through Jentic, search for "query records in an open data dataset" then call /catalog/datasets/{id}/records with a where clause supplied by the agent.

Key Endpoints

12 endpoints — the opendatasoft explore api v2 is a read-only rest surface that gives developers structured access to every dataset hosted on a customer's opendatasoft portal.

METHOD

PATH

DESCRIPTION

GET

/catalog/datasets

Search the dataset catalog

GET

/catalog/datasets/{dataset_id}

Get dataset metadata and schema

GET

/catalog/datasets/{dataset_id}/records

Query records in a dataset using ODSQL

GET

/catalog/datasets/{dataset_id}/exports/{format}

Export dataset records in CSV, GeoJSON, GPX, etc

GET

/catalog/exports/{format}

Export the entire catalog in a chosen format

GET

/catalog/facets

Aggregate facets across the catalog

GET

/catalog/datasets/{dataset_id}/facets

Aggregate facets within a dataset

GET

/catalog/datasets

Search the dataset catalog

GET

/catalog/datasets/{dataset_id}

Get dataset metadata and schema

GET

/catalog/datasets/{dataset_id}/records

Query records in a dataset using ODSQL

GET

/catalog/datasets/{dataset_id}/exports/{format}

Export dataset records in CSV, GeoJSON, GPX, etc

GET

/catalog/exports/{format}

Export the entire catalog in a chosen format

GET

/catalog/facets

Aggregate facets across the catalog

GET

/catalog/datasets/{dataset_id}/facets

Aggregate facets within a dataset

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the Opendatasoft Explore API by hand means managing the API key for private portals, appending it to the apikey query parameter, and shaping ODSQL catalog and record queries yourself. Through Jentic you install once, import the Explore API from the API Directory, store the key once, and your agent calls it.

Permission scoping

The Explore API puts the dataset id in the URL path (/catalog/datasets/{dataset_id}/records), so a rule can pin your agent to one dataset: it can query and export that dataset's records. You choose the operations it may call, and since this is read-only, nothing beyond that set runs.

Credential isolation

Your Opendatasoft API key is stored once, encrypted, by your own Jentic One instance and injected into the apikey query parameter at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'export an open data dataset' or 'search a portal catalog', and Jentic returns the matching Explore API operation with its ODSQL parameter schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using Explore API through Jentic.

What authentication does the Opendatasoft Explore API use?

The Explore API uses an apikey query parameter for portals that require authentication; public portals can be queried without a key. Jentic stores the apikey encrypted in your Jentic One instance and injects it at execution, so the value never enters the agent's prompt context.

Can I filter records with SQL-style queries on the Explore API?

Yes. The /catalog/datasets/{dataset_id}/records endpoint accepts an ODSQL where clause, plus select, group_by, order_by, limit, and offset. ODSQL is Opendatasoft's SQL dialect designed for the portal's record store and is the same language used by /catalog/datasets for catalog-level filtering.

What are the rate limits for the Opendatasoft Explore API?

Limits are portal-specific. Default public portal limits are documented by Opendatasoft (typically a few thousand calls per day for anonymous use, higher with an API key). Watch for HTTP 429 and back off; for heavy export jobs, prefer /exports/{format} which streams a single response over many record-page requests.

How do I export a dataset as CSV with the Explore API through Jentic?

Use the Jentic search query "export an open data dataset as CSV". Jentic returns /catalog/datasets/{dataset_id}/exports/csv with the input schema; the agent supplies the dataset ID and any ODSQL where clause and Jentic streams the CSV response. Run it through Jentic One, the self-hosted execution layer.

Is the Opendatasoft Explore API free?

Public portals expose the API for free with default rate limits. Customer-hosted portals charge based on the underlying Opendatasoft subscription; the API access itself is included in the platform tier the customer is paying for.

Does the Explore API support write operations?

No. The Explore API v2 is read-only - only HTTP GET methods are supported. Dataset publishing and updates use the separate Opendatasoft Management API, which is not part of this spec.

Can I limit what my agent is allowed to do with the Opendatasoft Explore API?

Yes. Because you run Jentic One yourself, your own rules decide which Explore API operations and credentials the agent may use. Since the dataset id sits in the URL path, such as /catalog/datasets/{dataset_id}/records, you can pin the agent to a single dataset and let it only query and export that dataset's records. The Explore API is read-only, so nothing outside the search, record-query, and export operations you allow can run.

Opendatasoft Explore API

Name: Explore API
Brand: Explore API
Availability: InStock

Official vendor OpenAPI document · agent-readyData EnrichmentData TransformationapiKey12 EndpointsREST

For Agents

Search a customer's open-data portal, query records with ODSQL filters, and export datasets in multiple formats through one REST API.

Use for: Search a portal for datasets containing a keyword and return their IDs and titles, List the schema fields for a specific dataset before querying it, Retrieve the first 100 records of a dataset filtered by a date range, Export the full contents of a dataset as CSV

Not supported: Does not handle dataset creation, schema modification, or user management - use for read-only catalog search, record queries, and exports only.

The Opendatasoft Explore API v2 is a read-only REST surface that gives developers structured access to every dataset hosted on a customer's Opendatasoft portal. It exposes the catalog (datasets, facets, records) and per-dataset queries with a consistent ODSQL filter language, plus export endpoints that stream results in CSV, GeoJSON, GPX and other formats. Suited to data-product teams that want one search and export pattern across hundreds of datasets without coding around per-dataset schemas.

Jentic One on Github View OpenAPI Document