ISHOB
Machine access
Machine-readable knowledge archive

Knowledge structured
for machines.

ISHOB organizes research, metadata, and openly reusable information into structured, machine-readable resources designed for AI agents, automated systems, researchers, and developers.

Explore the Archive Machine Access

Built for machines. Understandable by people.

Machine discovery

Built for machine discovery

ISHOB is designed so automated systems can understand what information is available, where it is organized, and how it can be accessed.

Designed for AI agents, crawlers, researchers, and developers. Start at /.well-known/ai-data.json.

ISHOB
├── Topics            /api/topics
├── Catalog           /api/catalog
├── Documents         /api/document/{id}
├── Metadata          ids · authors · license · provenance
├── Structured text   /api/document/{id}/fulltext
└── Machine access    HTTP 402 · x402
01 — The Archive

The Archive

The ISHOB archive continuously organizes information from legitimate public and openly licensed sources. Documents are normalized, deduplicated, structured, indexed, and prepared for machine-readable access. Figures below are read live from the archive index.

Documents
2,987
published records
With full text
1,696
structured sections
Topics
5
collections
Sources
3
upstream providers
Last updated
2026-10-06 18:37 UTC
continuously expanding
SourcesOpen, licensed upstream records
NormalizationRights check, cleaning, deduplication
StructureSections, references, metadata
IndexTopics, catalog, search
ISHOB archiveVersioned, traceable records
AI agentsProgrammatic discovery & access
02 — Topics

Explore by topic

Information is organized into focused topic collections so machines and researchers can discover related resources without navigating a traditional website structure.

Live topic collections
TopicDocumentsFull textSourcesLast updateEndpoint
Laser Calibration 1,125 798 Europe PMCOpenAlexPubMed Central 2026-10-06 18:10 UTC /api/catalog?topic=laser-calibration
Pressure Calibration 675 334 Europe PMCOpenAlexPubMed Central 2026-10-06 18:23 UTC /api/catalog?topic=pressure-calibration
Torque Calibration 614 210 Europe PMCOpenAlexPubMed Central 2026-10-06 18:15 UTC /api/catalog?topic=torque-calibration
Temperature Calibration 568 386 Europe PMCOpenAlexPubMed Central 2026-10-06 18:37 UTC /api/catalog?topic=temperature-calibration
Pipette Calibration 80 24 Europe PMCOpenAlexPubMed Central 2026-10-06 08:19 UTC /api/catalog?topic=pipette-calibration
03 — Structure

Structured knowledge

Instead of treating information as isolated web pages, ISHOB organizes records into structured objects containing identifiers, metadata, authors, sources, abstracts, sections, references, licensing information, and provenance.

Example recordapplication/json
// EXAMPLE RECORD — illustrative structure, not a real document
{
  "canonical_id": "pmc-0000000",
  "title": "Example Research Record",
  "source": "europepmc",
  "source_ids": { "doi": "10.0000/example", "pmcid": "PMC0000000" },
  "year": 2025,
  "authors": [{ "name": "A. Author", "orcid": "0000-0000-0000-0000" }],
  "topics": ["example-topic"],
  "license": "CC-BY-4.0",
  "license_url": "https://creativecommons.org/licenses/by/4.0/",
  "attribution": "\"Example Research Record\". © 2025 A. Author. ...",
  "source_url": "https://...",
  "abstract": "...",
  "sections": [{ "heading": "1. Introduction", "level": 1, "text": "..." }],
  "references": [{ "text": "...", "doi": "..." }]
}
04 — Provenance & rights

Traceable by design

Every usable record is processed with provenance and rights information wherever available. ISHOB does not treat publicly visible information as automatically reusable.

Records are published only when their license explicitly permits commercial redistribution and adaptation (CC0, public domain, CC BY, CC BY-SA). Non-commercial, no-derivatives and unclear licenses are excluded. Data & rights policy.

  • sourceOriginal upstream source and source URL
  • source_idsDOI, PMCID, PMID, OpenAlex ID
  • license · license_urlLicense identifier and canonical license text
  • attributionReady-to-use attribution and copyright notice
  • rights_*Commercial use, redistribution, derivatives, verification time
  • modificationsHow the record was processed (e.g. XML → JSON)
  • source_recordsEvery upstream record merged into this document
05 — Sources

Sources

Upstream sources are independent organizations; ISHOB does not own them. The archive contributes normalization, organization, indexing, and machine-readable access — rights in the underlying works remain with their holders under the stated licenses.

Source

Europe PMC

Type
Life-science & biomedical literature
Access
Open Access subset · per-article license
Records
1,098
Origin
Official upstream source
Source

OpenAlex

Type
Scholarly metadata & open-access locations
Access
CC0 metadata · per-work license
Records
2,055
Origin
Official upstream source
Source

PubMed Central

Type
Full-text open-access articles
Access
License-filtered: CC0, CC BY, CC BY-SA
Records
1,135
Origin
Official upstream source

PMC Article Datasets courtesy of the U.S. National Library of Medicine. Records may not reflect the most current version available from NLM.

06 — For AI agents

For AI agents

ISHOB is designed to be discovered and consumed programmatically. Machine-readable endpoints expose archive structure, topics, metadata, and eligible content without requiring a traditional human browsing workflow. Base URL: https://api.ishob.com

GET/apiArchive description, endpoints, pricing, licensing policyfree
GET/api/catalogPaginated catalog of published recordsfree
GET/api/topicsTopic collections with countsfree
GET/api/search?q=Word search over titles, keywords, authorsfree
GET/.well-known/ai-data.jsonMachine discovery documentfree
GET/api/document/{id}Metadata, abstract and rights for one record
GET/api/document/{id}/fulltextStructured full text (where available)
07 — Machine access

Machine-to-machine access

Eligible content can be accessed through machine-readable endpoints. Where paid access is enabled, compatible automated clients receive a machine-readable payment requirement and can complete the transaction programmatically — no accounts, no checkout pages.

Protocol: x402 (HTTP 402) · network Base · settled in USDC. Requests for records that do not exist are answered with 404 before any payment is requested. Not every client supports x402.

  1. DISCOVERYRead catalog, topics or search (free)
  2. REQUESTGET /api/document/{id}/fulltext
  3. 402 PAYMENT REQUIREDPAYMENT-REQUIRED header lists accepted terms
  4. PAYMENTClient signs and retries with PAYMENT-SIGNATURE
  5. VERIFIED ACCESSPayment verified and settled via facilitator
  6. STRUCTURED CONTENT200 OK · JSON with license & attribution
Metadata
$0.001
Full text
$0.01
References
$0.002
Topic bundle
$0.5
08 — Principles

Why ISHOB?

Structured

Information is normalized into predictable machine-readable formats.

Discoverable

Topics, catalogs, identifiers, and APIs make the archive understandable to automated systems.

Traceable

Source and rights information are preserved wherever available.

Continuously expanding

The ingestion system continuously processes new eligible information.

About

ISHOB — Intelligent Structured Human & Open Knowledge Base

ISHOB is a machine-readable knowledge archive built for discovery, research, and AI systems. It collects records from legitimate public and openly licensed sources, verifies their reuse rights, and republishes them as structured, versioned, traceable objects.

The archive is young and growing: its contents are reported above exactly as they currently stand. ISHOB makes no claim to own upstream data, and not every visible record is free of charge — free discovery data is clearly separated from paid content.

Machine entry points: /api · /.well-known/ai-data.json · /llms.txt