Install Jentic One Beta

Connect the NextGen Catalog API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the NextGen Catalog 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%2Fcatalog.archives.gov%2Fnara-catalog" | 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%2Fcatalog.archives.gov%2Fnara-catalog" | 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 NextGen Catalog API.

Search the National Archives Catalog by keyword and metadata filters

Walk the catalog hierarchy by retrieving the immediate children of a parent NaId

Search records by tag or by the contribution metadata around them

Add a tag to a National Archives record on behalf of a registered userId

Submit a comment against a record for citizen annotation workflows

GET STARTED

Start building with NextGen Catalog API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use NextGen Catalog API for, with concrete tasks.

★ Digital humanities research portal

Academic and library projects can use GET /records/search and GET /records/parentNaId/{parentNaId} to embed live National Archives metadata in their research portals, walking record hierarchies and surfacing extracted text alongside the user's own annotations. This lets a niche audience search NARA without scraping the public website.

GET /records/search with q='Apollo 11' and pageSize=25, then return the title and naId of each result.

Citizen transcription workflows

Crowdsourced transcription platforms can submit user-contributed text via POST /transcriptions/ and tags via POST /tags/, attached to a UUID userId in the body. This makes it possible to build a transcription UI on top of NARA records that writes back to the canonical catalog.

POST /transcriptions/ with naId of the target record, the transcribed text, and the contributor's userId UUID.

Tag-driven record discovery

Educators and journalists can pull records associated with topical tags using GET /records/search/by-tag and present curated collections that update as new contributions land. Combined with GET /tags/search, this turns the National Archives into a tag-faceted research surface for classroom use.

GET /records/search/by-tag with tag='vietnam-war' to retrieve the matching records for a classroom resource page.

AI agent archival research via Jentic

An AI research assistant can call the National Archives Catalog to retrieve primary sources and submit transcriptions as a citizen contributor through Jentic. The x-api-key issued by NARA stays in your Jentic One instance and is injected at execution time, so the agent never holds the key directly.

Search Jentic for 'search the National Archives Catalog', load GET /records/search, and execute it with the user's research query.

Key Endpoints

14 endpoints — jentic publishes the only available openapi specification for the nextgen catalog api, keeping it validated and agent-ready.

METHOD

PATH

DESCRIPTION

GET

/records/search

Keyword search across catalog records

GET

/records/parentNaId/{parentNaId}

Get child records under a parent NaId

GET

/records/search/by-tag

Search records by applied tag

POST

/tags/

Add a tag to a record

POST

/comments/

Add a comment to a record

POST

/transcriptions/

Submit a transcription against a record

GET

/contributions/search

Search citizen-contribution metadata

GET

/records/search

Keyword search across catalog records

GET

/records/parentNaId/{parentNaId}

Get child records under a parent NaId

GET

/records/search/by-tag

Search records by applied tag

POST

/tags/

Add a tag to a record

POST

/comments/

Add a comment to a record

POST

/transcriptions/

Submit a transcription against a record

GET

/contributions/search

Search citizen-contribution metadata

Why Jentic?

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

Setup

Wiring the NextGen Catalog API by hand means sending your x-api-key header on every call and supplying the required userId UUID on write calls against the catalog.archives.gov host yourself. Through Jentic you install once, import the NextGen Catalog API from the API Directory, store the key once, and your agent calls it.

Permission scoping

The NARA write operations carry tags, comments, and transcriptions in the request body rather than a resource path, so you scope by operation: limit the agent to the ones it needs, such as searching records and browsing by parentNaId, and leave tag, comment, and transcription writes out of the allowed set until you want them.

Credential isolation

Your NARA x-api-key is stored once, encrypted, by your own Jentic One instance and injected into the x-api-key header at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'search the National Archives Catalog' or 'submit a transcription', and Jentic returns the matching operation with its input schema, including the required userId UUID for write calls, so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using NextGen Catalog API through Jentic.

Why is there no official OpenAPI spec for the NextGen Catalog API?

The U.S. National Archives publishes a Swagger description but no curated, validated OpenAPI 3 specification. Jentic generates and maintains this spec so that AI agents and developers can call the NextGen Catalog API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

What authentication does the NextGen Catalog API use?

The NextGen Catalog API uses an API key passed in the x-api-key header. You request a key by emailing Catalog_API@nara.gov. For write operations to /tags/, /comments/, and /transcriptions/, you must also include a registered UUID userId in the request body. Through Jentic, the x-api-key is held in your Jentic One instance.

Can I post tags, comments, or transcriptions through this API?

Yes. POST /tags/, POST /comments/, and POST /transcriptions/ accept user contributions, but each requires a valid UUID userId in the request body that has been registered with NARA. Read endpoints do not require this userId.

What are the rate limits for the NextGen Catalog API?

NARA does not publish explicit numeric rate limits for the NextGen Catalog API in this OpenAPI spec. Be conservative with paginated /records/search calls and contact Catalog_API@nara.gov if you need elevated quota for a research project.

How do I search the National Archives Catalog through Jentic?

Run pip install jentic, search Jentic with the query 'search the National Archives Catalog', load the GET /records/search schema, and execute it with q and any pagination parameters. Jentic injects the x-api-key from the vault at execution time.

Is the NextGen Catalog API free to use?

Yes. The National Archives provides the catalog API at no charge for civic and research use; you only need to email Catalog_API@nara.gov to request an API key.

Can I limit what my agent is allowed to do with the NextGen Catalog API?

Yes. Because you self-host Jentic One, your own rules decide which NextGen Catalog operations and credentials the agent may use. Since the write calls (POST /tags/, POST /comments/, POST /transcriptions/) carry their data in the request body rather than a resource path, you scope by operation: allow only what the agent needs, such as GET /records/search and GET /records/parentNaId/{parentNaId} for reading records, and leave the tag, comment, and transcription writes out of the allowed set. Your NARA x-api-key stays in your instance and is injected only when a permitted operation runs.

Catalog Archives Gov NextGen Catalog API

Name: NextGen Catalog API
Brand: NextGen Catalog API
Availability: InStock

Agent-ready OpenAPI document · curated by JenticProductivityNote TakingapiKey14 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For Agents

Search the U.S. National Archives Catalog for historical records and submit citizen contributions such as tags, comments, and transcriptions against records.

Use for: Search the National Archives Catalog for World War II photographs, Find all immediate child records of a National Archives parent NaId, Get records that contain a specific extracted text phrase, List all tags applied to a National Archives record

Not supported: Does not handle digital file downloads, FOIA requests, or user account management - use for catalog search and citizen contributions on the NARA NextGen Catalog only.

Jentic publishes the only available OpenAPI specification for the NextGen Catalog API, keeping it validated and agent-ready. The NextGen Catalog API is the U.S. National Archives (NARA) Catalog interface for searching records, parent-child record hierarchies, and citizen contributions such as tags, comments, and transcriptions. Read endpoints expose the catalog's metadata, while authenticated write endpoints accept new tags, comments, and transcriptions tied to a UUID userId. Researchers, civic-tech tools, and digital humanities projects use it to embed primary source material from the National Archives directly into their applications.

Jentic One on Github View OpenAPI Document

Connect the NextGen Catalog API to your agent

Capabilities

Start building with NextGen Catalog API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Catalog Archives Gov NextGen Catalog API