Know of an official OpenAPI document?
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the data.gov.au CKAN 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%2Fdata.gov.au%2Fdata-gov-au" | shStep 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%2Fdata.gov.au%2Fdata-gov-au" | sh
jentic register # connects your agent to your Jentic One instanceJentic 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.
What an agent can do with data.gov.au CKAN API.
Search datasets with full-text and faceted queries
List all dataset, tag, group, and organization names
Read dataset and resource details
Browse datasets within a group or organization
Track recently changed packages and activity
Patterns agents use data.gov.au CKAN API for, with concrete tasks.
★ Open-data discovery
Analysts and apps need to find relevant government datasets fast. The data.gov.au CKAN API searches packages with full-text and faceted queries and returns dataset details, so a tool can surface the right dataset for a question.
Search packages for a keyword and return the matching datasets with their resource details
Dataset update monitoring
Data teams watch for new and updated datasets. The API lists recently changed packages and package activity, so a monitor can detect updates to a dataset of interest and trigger a refresh.
List recently changed packages and flag any update to a watched dataset
Agent-driven research assistant
A research agent can gather open data on request. Through Jentic, an agent resolves a question into searching packages, reading the top dataset's details, and following its resources to the underlying files.
Search for datasets on a topic, read the best match's details, and return its resource links
15 endpoints — jentic publishes the only available openapi specification for data.
METHOD
PATH
DESCRIPTION
/action/package_search
Search datasets
/action/package_show
Get dataset details
/action/package_list
List all dataset names
/action/resource_show
Get resource details
/action/organization_list
List organizations
/action/group_package_show
List datasets in a group
What agents get from Jentic-routed access to this vendor.
Setup
data.gov.au needs no key, so the work is just CKAN's action-style query parameters and JSON. With Jentic One you install once, import the read operations from the API Directory, and point an agent at them.
Permission scoping
Every operation is a public read, and datasets and resources are addressed by id or name parameters, so you can scope an agent to specific searches and reads.
Credential isolation
There is no credential to handle: the portal is public, so nothing is stored and no secret ever reaches the agent's prompt or logs.
Intent-based discovery
Agents find the right CKAN read through Jentic's intent search, matching a request like searching Australian open data to the matching data.gov.au operation.
Alternatives and complements available in the Jentic catalogue.
Specific to using data.gov.au CKAN API through Jentic.
Do I need an API key for the data.gov.au API?
No. The CKAN portal is a public read service, so there is no key to request and nothing to store. Jentic One sends each request straight through.
Can I limit what my agent is allowed to do with the data.gov.au API?
Yes. Every operation is a public read, and you import only the ones an agent needs, so it can search datasets while every other operation stays unavailable.
What is CKAN?
CKAN is the open-source data-portal platform behind data.gov.au. Its action API exposes datasets (packages), resources, tags, groups, and organizations through consistent read operations.
How current is the data?
The portal reflects what Australian agencies have published, and the recently-changed and activity operations let a tool see when datasets were last updated.
Why is there no official OpenAPI spec for data.gov.au?
data.gov.au documents its CKAN action API in prose rather than publishing a machine-readable spec. Jentic generated this OpenAPI description from that documentation and keeps it validated so agents can call it reliably.
GET STARTED
/action/package_search
Search datasets
/action/package_show
Get dataset details
/action/package_list
List all dataset names
/action/resource_show
Get resource details
/action/organization_list
List organizations
/action/group_package_show
List datasets in a group
For Agents
Lets an AI agent search and read public datasets, resources, groups, and organizations from Australia's data.gov.au CKAN portal without any credentials.
Use for: I need to search Australian government datasets, Show me the details of this dataset, List the organizations publishing open data, Which datasets changed recently?
Not supported: Does not create, edit, or delete datasets and needs no login: use it to search and read public data.gov.au datasets only.
Jentic publishes the only available OpenAPI specification for data.gov.au CKAN API, keeping it validated and agent-ready. The Australian Government open-data portal runs on CKAN and lets anyone search and read public datasets: list and search packages, inspect dataset and resource details, browse tags, groups, and organizations, and track recently changed packages and activity. Every operation is a public read that needs no authentication.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>