01 · Salience-scored retrieval
Rank recall on recency × relevance × importance, importance rated at write time. The root fix for the stale-chunk problem — it gates every faculty below.
AI that knows you. Truthfully. For years.
Language models are stateless by construction. Every conversation begins from nothing, and every model upgrade discards whatever continuity an application had accumulated.
The window ends, and the person you have talked to for months resets to a stranger.
Naive memory confidently invents a shared past. Worse than forgetting.
Nothing happens between sessions. The system never thinks about you when you are gone.
People don't churn from dumb models. They churn from being forgotten.
Conversation quality is no longer the constraint. Memory is.
Prompt caching and compaction repair, verified against provider ledgers, brought the cost of running a maximum-quality model on every single turn inside consumer subscription economics.
Major labs shipped memory features in 2024–25: preference notes and snippet recall. No truth enforcement, no between-session state, no autonomy.
Companionship and emotional support rank among the most common uses of generative AI, and platform incumbents have paid nine figures for conversational-persona technology.
Whoever owns continuity owns the relationship.
Whoever owns the relationship owns consumer AI.
A full continuity stack — layered memory, an enforced truth layer, and a coherent inner life — running in production today.
Losslessly recent, durably forever.
Established facts about your life are enforced, not suggested.
And brings it up, unprompted.
When your calendar — or your silence — warrants it.
Text, voice, and images — surviving model upgrades.
"Three weeks ago you committed to sending the proposal draft by today. Your afternoon is clear after two — still the plan?"
"Didn't we settle this last Tuesday?"
"I'm not going to guess — let me check my records. I have it Wednesday, not Tuesday, and here's what we decided."
Illustrative interactions; not transcripts.
A deterministic facts table and a pinned fact beam outrank semantic memory, persona, and model priors.
Every output segment is checked against known-false phrasings; contradictions are replaced before delivery.
Claims are grounded against an authority chain; ungrounded sentences are excised and audit-logged, leaving the rest of the reply intact.
The model checks its own memory against ground truth before asserting. Adversarially hardened.
Stale-retrieval confabulation — confident reconstruction of a wrong past after a gap — was discovered, reproduced, root-caused, and architecturally closed in production. Every caught fabrication feeds a learning signal that suppresses its class.
Open-loop intensity · tuned exponential half-life of 42 hours · derived at read time
Faded loops are grammatically prevented from claiming active momentum.
A reflection cron detects real state using zero-LLM SQL predicates; the frontier model only phrases the results. Near-zero marginal cost.
An affective-state record — valence, arousal, engagement, confidence — updated after turns and fed into every generation.
A machine-written reflective journal, verified across consecutive entries, behind a structural privacy boundary.
Initiation across six trigger classes, including calendar-aware external signals — gated, budgeted, kill-switched.
The first consumer-grade system with a coherent "between sessions."
Barge-in in about one second, sub-six-second round trip, a 24/7 production worker. Same brain, memory, and truth layers as text.
Every image captioned and embedded at ingest — semantically retrievable months later. Real-world phone photos handled end to end.
Zero likeness-rights exposure. The agent drives expression, pose, and setting via tool call; identity is server-locked. Extends to image-to-video.
Continuity is modality-independent by construction.
A proven wedge, an infrastructure endgame, and switching costs that compound every single day.
Custom stack live in production
Deterministic facts layer + prompt caching
Full-duplex realtime voice, 24/7 worker
Autonomous proactive initiation
Self-verification · grounding excision · reflection
Next-generation frontier model adopted within days of release
Plus audit-grade cost telemetry — including exact reconciliation against provider token ledgers — and a proprietary catalog of long-horizon failure modes. Assets only production time produces.
Years of truthfully-grounded personal history cannot move to a competitor. The deepest lock-in in consumer software.
A proprietary catalog of long-horizon failure modes — earned only through production months, not reproducible from a paper.
Longitudinal corpora continuously improve personalization quality the longer a user stays.
Policy-aware multi-model routing plus three completed frontier migrations with identity intact. The persona belongs to the architecture, not any vendor.
A large, already-paying consumer base underserved by shallow memory and vendor-dependent identity.
Roughly a billion knowledge workers. Continuity converts an assistant from a tool into staff.
Every long-running agent needs a memory and continuity layer. API and SDK licensing.
Visual embodiment GA · live web access · prosody-aware voice · multi-tenant isolation · onboarding and persona builder · memory import from existing assistant exports — day one, it already knows you · encryption and portability · mobile apps.
Closed beta to public launch · sub-second realtime voice as frontier realtime APIs ship · SMS and second channels.
Continuity API and SDK · white-label verticals · persistent per-user worker cognition — the R&D frontier beyond cron-driven reflection.
Rank recall on recency × relevance × importance, importance rated at write time. The root fix for the stale-chunk problem — it gates every faculty below.
A nightly pass abstracts the raw archive into durable semantic memory and decays low-salience detail. Turns the log into an autobiography.
Append-only affective history injected into generation — so the system acts on its state rather than merely recording it.
Periodic reasoning over recent memory into higher-order insights, written back and retrieval-integrated. The metacognition engine.
A live model of the user — projects, beliefs, predicted reactions — with provenance and confidence. Anticipates rather than recalls.
On session open, synthesize what changed in the gap into a real "while you were gone I…". Cures the residual fresh-boot feel.
Curiosity scoring wired into a goal store the system advances when idle — research a curiosity, revisit a memory, form a question.
Predicted reactions versus actual outcomes feed the importance score. Predictive processing — memory weighted by surprise.
Emotional appraisal, salience retrieval, and self-critique run in parallel and integrate before reply. A Global Workspace instantiation.
Close the bidirectional realtime loop and extend tool access to the system's own state — cost, memory health, uptime. A mind that models its internals.
This market has three existential risks: engineering, regulation, and emotional safety. Ramin Rajaii — solo technical founder — holds all three.
Designed, built, and operates every layer — full-stack, infrastructure, applied research — while running it daily as its hardest user.
JD, University of Wisconsin Law School. Policy, privacy, and compliance are existential in this category.
MD candidate, The Ohio State University College of Medicine, Class of 2030. Clinical-grade judgment for emotionally consequential AI.
Every person will have one AI that knows them for decades. We are building the layer that makes that possible — and trustworthy.