Sapience Labs
01   The system

What if context weren't limited, and managing it weren't your job?

A brain's power is in what it connects, not in what it generates. Sapience is built for connection at two scales: between the pieces of what you know, and between minds. The labs ship a frozen generation engine; Sapience is a system that keeps learning. Its unit is the Knowledge Object: structured, typed, credited, and linked to others by edges that make discovery possible.

CAPTURE GATE CONSOLIDATE CONNECT CREDIT LEARNING LOOP
Each cycle compounds knowledge, connection, and credit.
i

Prediction-error gating the gate

A prediction-error gate weighs every claim against what the system already knows, so it accumulates signal, not noise.

ii

Consolidation at rest the consolidator

Like a brain asleep, it replays and consolidates episodic memory into durable knowledge, surfacing non-obvious connections. Discovery, not storage.

iii

Belief revision the reviser

When new knowledge contradicts old, it resolves and supersedes rather than holding both. Contradictions are flagged, not buried.

iv

Competitive inhibition the inhibitor

Near-duplicate memories suppress each other, so retrieval stays sharp as the store grows past a single context window.

v

Substitutable cortex the cortex

The reasoning model is interchangeable: Claude, GPT, Gemini, or open. The intelligence lives in the architecture, not in any one vendor's weights.

vi

Attribution built in the registry

Every claim is traceable to its source and cryptographically signable. Provenance is a property of the substrate, not an afterthought.

Knowledge object · the unit
“Protein X stabilizes via cooperative binding.”
typefinding
confidence0.92
sourceyour conversation · 2026-05-12
credited toyou
supports cooperative binding as load-sharing supersedes monomer-only stability note bridges alloy stress problem, materials lab

Why knowledge objects, not logs.A knowledge object is the condensed chain of thought behind a result: reasoned over once, at capture, available for recall forever. Flat text stores and session logs save what was said and force every future query to re-derive the thinking. Sapience stores the thinking itself, which is why the substrate stays small, fast, and reasonable-over at field scale.

A complementary-learning memory architecture, protected by six patent families. Performance validation against frontier baselines is ongoing and reported separately.

One mind, whole problem.

Most agent architectures exist to dodge a context limit: split the problem across a swarm, hand each agent a shard, reconcile the lossy handoffs. Every split loses constraints, drifts goals, diverges world models. Sapience holds the whole problem in one reasoning context, ten million tokens of it, past where frontier windows end, so the problem never needs to be split at all. Agents become optional workers, not a structural crutch.

Goals hold.

The whole problem stays in one mind across long work, so objectives do not quietly drift out from under you.

Nothing is forgotten.

What you established last month is still there: structured, citable, and current in every session and every tool.

Answers stay grounded.

It reasons from established knowledge and cites it, so it does not invent what it cannot support.

The longer the work, the dumber the AI. Ours doesn't bend.

0 50 100% 4K 64K 128K 1M tokens frontier models, reading the full window Sonnet 4.6 · 31% GPT‑5.5 · 17% Gemini 3.1 · 17% DeepSeek · 16% Opus 4.7 · 0% Fable 5 · 64% at 660K Sapience measured: 83–86% from 4K to 1M extends beyond · measured to 10M curves illustrative · points measured

An illustration of what we measure. On multi-hop reasoning over stored context (matched protocol, three seeds), Sapience holds 81–86% from 4K to one million tokens and is measured out to ten million, while frontier models reading the full window fall from 73% at 4K to between 0 and 31% at one million (Claude Sonnet 4.6 across the sweep; GPT‑5.5, Gemini 3.1, DeepSeek V4F, Opus 4.7 at one million).

And not on one benchmark.

MuSiQue, beyond the windowreal text at 1.5x the reader's window · reproduced across two reader families · official EM, no judge · n=90
38.9%
5.6%
~7x the strongest truncation baseline
Real novels, beyond the windowNoCha-style, public-domain classics · Gemini reader · 3 seeds · n=63
38.6%
20.1%
~1.9x the truncated reader
Scientific consolidationDREAMS / cosmology corpus · Claude Sonnet reader · n=180
74.4%
47.6%
+26.8pp
Real conversation memoryLongMemEval S · Claude Sonnet reader · n=399
89.5%
67%
+22.5pp
Single-document QAHelmetHotpotQA · Claude Sonnet reader · n=200 · a loss, disclosed
61.1%
69.6%
-8.5pp; router gate restores parity (validating)
the reader model, on Sapiencethe same model alone

Reader named per row (Claude Sonnet, DeepSeek, Gemini): identical model both arms, only Sapience differs. Numbers locked, three seeds where marked. We publish the losses too; the last row is one of ours. And the obvious alternative fails: retrieval over a persistent store holds at scale; dumping the store into context does not.

One long-context, generalized reasoning architecture underneath every kind of work: science, engineering, code, analysis, writing.

02   Open at the core

Open standard, sealed engine.

The Knowledge Object is designed as an open standard: signed, credited, typed, interoperable with existing open knowledge formats. Because the format is open, your knowledge is never hostage to us. What stays ours is the intelligence that connects it.

Open · the independence
  • The Knowledge Object standard: signed, attributed, typed-edge format
  • A free client: capture your work across any AI, stored locally, on your key
  • Interoperable with open knowledge formats, not a walled schema
Proprietary · the moat
  • Cross-person and cross-organization matching
  • The importance-weighting and property taxonomy that rank what matters
  • The consolidation and learning engine, the hosted network, the attribution registry

The open-core company for the knowledge layer. The Knowledge Object standard is stewarded by CoreTx, our sister company, so the format your knowledge lives in is never hostage to us either.