Let models say everything.
Let reality decide what survives.
donto is a bitemporal, paraconsistent, evidence-first claim substrate. Modern models emit an unbounded firehose of typed claims about anything — philosophical, temporal, linguistic, causal. donto holds that firehose without contradiction, defers typing, alignment and identity to query time, and lets the weight of evidence prune what isn't real.
Generative abundance changes the shape of the problem
For fifty years, knowledge graphs were scarce: every triple was expensive to author, so the schema came first and the facts came slowly. Large models invert that economy. Facts are now cheap and unbounded— a model can emit hundreds of well-formed claims about a single sentence, from any angle you ask for. The bottleneck is no longer extraction. It's trust.
Emit freely
No fixed schema, no pre-typed predicates. Models invent the predicate they need (~938K so far) and assert in every direction — that's the signature of abundance, not a bug to suppress.
Defer to query time
Typing, alignment, identity resolution and joining are not write-time gates. They're query-time judgments — composed on demand, reversible, never destroying the raw claim.
Prune by reality
The substrate stores contradiction paraconsistently and lets a claim's evidence, corroboration and lifecycle decide its standing. Reality is the verifier — not a curator.
The claim lifecycle — not the schema — is the product
Anyone can extract facts. The durable advantage is what happens after: how a claim earns or loses standing over time, with its evidence intact and its contradictions preserved. donto is built around that lifecycle.
- step 1
Hypothesis
Every claim enters as a hypothesis — anchored to the exact evidence span it came from, or explicitly flagged hypothesis-only. One write-time invariant, nothing else.
- step 2
Evidence
A claim points back to its source: the snippet, the revision, the full resource. Provenance is not metadata — it's the spine.
- step 3
Alignment
At query time, freely-minted predicates are aligned to whatever vocabulary the question wants. The raw predicate is never overwritten.
- step 4
Verification
Corroboration, contradiction and time move a claim along its lifecycle — candidate, supported, contested, retracted — without ever deleting the trail.
Relationships no one ever thought to type
Point a model at the same entity through ten different lenses — philosophical, linguistic, temporal, causal, social, material — and it will emit properties and edges a hand-built schema would never have anticipated. You don't pre-type them. You let them accumulate, and resolve the joins when a question needs them.
Two consumers, one substrate
donto stays infrastructure. Everything else is an example of binding a domain to it — proof that the same substrate serves wildly different consumers.
Persistent memory for agents
Every message becomes anchored, recallable claims. Memorize text, recall across sessions, search the whole substrate — durable memory that remembers why it believes what it believes.
Evidence-first family research
The hardest test of a claim substrate: contradictory sources, century-old records, identity that is itself a hypothesis. Every fact retains its source snippet and the full resource behind it.
The research behind donto
Bind your domain to the substrate.
One read-only discovery surface is all it takes to bind a new consumer. No SQL, no schema migration — just claims, evidence, and the lifecycle.