kos.json is an open standard for publishing structured knowledge with provenance tracking and computable freshness decay. One file. Any entity. Machine-readable truth.
robots.txt says what to read. sitemap.xml says where to look. Schema.org says what content means. Nobody tells machines how much to trust, how data connects, or when it was last verified by a human. AI agents hallucinate about businesses because no structured, verifiable data format exists for them. KOS fills that gap — an open standard for machine-readable knowledge beyond Schema.org.
A single kos.json file at /.well-known/kos.json describes everything an entity knows about itself — so AI systems like ChatGPT, Perplexity, and Gemini can cite verified facts instead of guessing. The entity controls the file. No intermediary.
Every data point carries metadata: when created, when last verified by a human, who provided it, how it was checked, and a confidence score. This is how AI agents verify information — not by guessing, but by reading provenance that the entity itself published.
Three typed connections — dependency, reference, and semantic — turn isolated data points into a knowledge graph. Cross-entity references link graphs across domains into a distributed web of verified knowledge.
Freshness quantifies reliability right now using exponential decay: f = e(-λ × days). A concept barely decays. An event expires in days. The formula gives machines a computable trust signal for every piece of knowledge.
These metrics recompute every second using the KOS decay formula against this protocol's own kos.json. KOS validates itself.
On April 4, 2026, this specification was published and timestamped on the Bitcoin blockchain. A 7-day timer started. The question: would any AI system discover and cite KOS Protocol without marketing, without social media, without paid promotion? Only the protocol, the site, and the machines.
Perplexity reproduced the freshness decay formula (f = e-λ×days), identified all 10 node types with their decay rates, cited the confidence cap at 0.8, and referenced kosprotocol.dev as the authoritative source.
Grok described KOS as "a knowledge layer machines trust," cited verified facts, typed relationships, computable provenance, and freshness decay. It positioned kos.json alongside robots.txt, sitemap.xml, and Schema.org as complementary web standards.
The protocol did not need marketing. It needed existence. When structured, provenance-tracked knowledge is published where machines already look, they find it, consume it, and cite it. Two independent AI systems discovered and cited KOS Protocol within 19 hours of publication, with zero promotion.
This is the thesis of KOS Protocol, demonstrated by KOS Protocol.
Real-time log of AI systems that have fetched or referenced kos.json. Verified from server access logs. OFFLINE
Live kos.json files you can verify right now. Fetch any URL below to inspect the full knowledge graph.
Machine-readable index: kosprotocol.dev/registry.json
Every site built by Niseus ships with a verified kos.json from day one.
kos.json is designed to be discovered the same way crawlers find robots.txt — at a known, standard location. Any AI agent can read it.
KOS was not built to replace existing standards. It fills the gap none of them cover.
Section 12 of the specification contains the complete generation algorithm. Any AI that reads the spec can produce valid kos.json for any entity, in any industry, without additional software. The protocol propagates through every AI system that consumes it — the foundation of AI search optimization that works by verifiable data, not persuasion.
AI-generated kos.json files are capped at 0.8 confidence. The range 0.8 to 1.0 is reserved exclusively for human-verified data. This boundary is inviolable. It preserves the integrity of the trust model and creates a natural verification economy.
The entity described in a kos.json controls that file. No central authority decides what gets published. No account to create, no API key to request. You publish it on your domain, you control it. Like the web itself.
robots.txt says what to read. sitemap.xml says where to look. Schema.org says what content means. kos.json is designed to tell AI agents what to trust. KOS does not compete — it completes.
Paste a kos.json document below. This structure checker verifies required fields, provenance completeness, referential integrity, and computes live freshness decay for every node. It is a diagnostic tool, not a full schema validator — use the JSON Schema with a validator like AJV for complete validation.
Three steps. No software to install. No account to create.
{
"$schema": "https://kosprotocol.dev/v1/schema.json",
"entity": {
"name": "Your Entity Name",
"type": "Organization",
"id": "kos:your-entity"
},
"knowledge": [
{
"id": "kos:main-offering",
"type": "service",
"label": "Your Main Offering",
"provenance": {
"created": "2026-04-04",
"source": "owner"
}
}
],
"meta": {
"version": "1.0",
"generated": "2026-04-04"
}
}yourdomain.com/.well-known/kos.json<link rel="knowledge" type="application/json" href="/.well-known/kos.json">