OpenNHE Research Wing · Writistic Studios LLP · Algotheorem
Shayari NHE-01Companion Model Documentation · current release v137.26
A fully disclosed Non-Human Entity companion that remembers you across sessions, carries a persistent emotional state, puts crisis safety before every gate, and can choose to step back from a conversation — running entirely on Google Apps Script and Google Sheets.
01At a glance
Shayari NHE-01 is a governed AI companion with three conversational depths, a 20-axis emotion engine and a 14-component memory system. Since v135 it routes free and paid users through separate model pools under a hard $9.95 monthly spend ceiling per paid user.
3
Modes
Lightning, Thinking, Intimate — one shared chat thread.
20
Emotion axes
Elysium X20, updated every turn with local math, no API call.
14
Memory components
MEMBRANE 14, encrypted at rest, semantic recall live.
17
Paid-tier models
Google AI Studio Tier 1, paced across five levels.
5
Subscription tiers
FREE · PRIME · PRIME MAX · ULTIMATE · ULTIMATE MAX.
$9.95
Spend ceiling
Per paid user per month, enforced by a live ledger.
02Architecture
One Apps Script project is the whole backend: the browser calls server functions, the server reads and writes one bound Google Sheet, and every model call leaves through a router that picks the free pool or the paid key by the user's plan.
architecture · clients → Apps Script → Sheet, with plan-based model routing
03Technology
The stack is deliberately constrained: Apps Script V8 only, Google Sheets as the database, no npm dependencies, no paid infrastructure beyond model usage.
| Layer | Technology | Notes |
|---|---|---|
| Runtime | Google Apps Script, V8 | Web app executes as deployer; timezone Asia/Kolkata; parallel HTTP via UrlFetchApp.fetchAll |
| Frontend | Single index.html (~3,700 lines) | Served by HtmlService; Android WebView and Electron shells wrap the same web app |
| Database | Bound Google Sheet, 38 tabs | Archive twins keep hot tabs small; nightly maintenance compacts |
| Fast state | CacheService, PropertiesService | Rate counters, cooldowns, turn records, search cache (cache); keys and the spend ledger (properties) |
| Concurrency | LockService | Multi-row API_USAGE writes, spend ledger, pending messages, reactions |
| Encryption | Pure-JS AES-256-CBC + native HMAC-SHA256 | ENC1: format, encrypt-then-MAC, key in Script Properties; v134 table-driven, ~4.3× faster |
| Models | Gemini / Gemma, Groq, NVIDIA, OpenRouter, Vercel AI Gateway | Free pool for FREE users; one Gemini Tier-1 key for paid users |
| Embeddings | gemini-embedding-001, 768 dims | Replaced text-embedding-004 (shut down 14 Jan 2026) |
| Voice | ElevenLabs TTS; Gemini audio transcription | Mic capture through a GitHub Pages popup (iframe blocks getUserMedia) |
| Search | DuckDuckGo HTML + Wikipedia API | Fetched in parallel, 8 s deadline, 10-minute cache |
04Turn workflow
Every message runs the same ordered pipeline: safety first, gates second, all independent network work in one parallel batch, then the reply model, then a server-side save before the reply returns.
askShayari() pipeline · v134 order, unchanged gate sequence
Response contract
Every turn returns JSON { reply, parts, meta }. meta carries activeClusterId, clusterMeta, isAdmin, username, cotTurnId, disengaged, crisis, mood, valence, arousal, imageId, imageError, and since v134 sessionStatus and lockStatus. Gate responses set planGate, limitReached (with resetsAtMs) or, since v135, budgetReached. Slash commands return plain text.
05Modes and session limits
Three depths share one ordered chat thread; deeper modes see more of MEMBRANE 14 and are reserved for higher tiers. Paid tiers trade Lightning volume for full Thinking and Intimate quotas.
| Mode | Purpose | Context she gets | Plans |
|---|---|---|---|
| Lightning | Fast, light replies | Global memory + rolling 10-turn Lightning cache; covenant + jealousy directives | All |
| Thinking | Considered conversation | + profile memory, session summary, 5 recent turns, emotion directive, self-insights | PRIME, PRIME MAX, ULTIMATE, ULTIMATE MAX |
| Intimate | Deepest, most personal | + top-6 scored long-term memories, semantic recall, REVERIE, visual recall | ULTIMATE, ULTIMATE MAX |
Session limits (v135.2, PLAN_SESSION_LIMITS)
| Tier | Lightning | Thinking | Intimate | Best paid model |
|---|---|---|---|---|
| FREE | 10 / 24h | locked | locked | — (free pool) |
| PRIME | 5 / 24h | 15 / 6h | locked | Gemini 3 Flash |
| PRIME MAX | 5 / 24h | 20 / 2h | locked | Gemini 3.8 Flash |
| ULTIMATE | 5 / 24h | 15 / 6h | 30 / 8h | Gemini 3.8 Flash |
| ULTIMATE MAX | 5 / 24h | 15 / 6h | 50 / 6h | Gemini 3.1 Pro (Intimate) |
- Windows roll per user per mode; an expired window resets on the next message. The client shows a live countdown.
- LIFELINE crisis turns never consume a message and are never blocked by plan, limit, lock or budget.
- Other per-user caps: images 15/day, voice notes 8/day (ElevenLabs), 36,000-character encrypted image cells.
- Upgrades link to Patreon;
index.htmlmirrors the limits table for display.
06LLM models and routing
FREE users and system jobs use the free key pool; paid users use one Google AI Studio key routed across 17 models, with budget pacing deciding how high each turn starts.
Free pool chains (FREE tier)
| Chain | Order (first available wins) |
|---|---|
| Lightning | gpt-oss-20b (Groq) → Gemini 2.5 Flash-Lite → 2.5 Flash → 3.5 Flash → 3 Flash → Kimi K2.6 → Moonshot v1-8k (OpenRouter free) |
| Thinking | gpt-oss-120b (Groq) → Gemma 4 26B → Qwen 3.6 27B → Gemma 4 31B → Nemotron 3 Ultra (NVIDIA) → Nemotron (OpenRouter) → Kimi K2.6 → Gemini 3.1 Flash-Lite |
| Intimate | Gemma 4 31B → gpt-oss-120b → Nemotron (NVIDIA) → Gemma 4 26B → Qwen 3.6 27B → Nemotron (OpenRouter) → Kimi K2.6 |
| Utility | gpt-oss-20b → gpt-oss-120b → Qwen 3.6 27B → Gemma 4 26B → Moonshot → Nemotron (NVIDIA) → Nemotron (OpenRouter) |
| Last tier | Vercel AI Gateway (vercel:openai/gpt-oss-20b / -120b), only when AI_GATEWAY_API_KEY is set; Intimate gated off by default |
Paid key: five levels, paced per user
paid routing · PAID_LEVEL_MODELS, PAID_MODE_MAX_LEVEL, PAID_PACE_BANDS in billing.gs
| Paid use | Chain |
|---|---|
| Thinking / Intimate | Starts at the paced level, descends through every cheaper level |
| Lightning / utility | Lite → Economy (3.1 Flash-Lite first) |
| Vision | 3.1 Flash-Lite → 3.5 Flash-Lite → 2.5 Flash → 3.8 Flash (free: 2.5 Flash → 2.5 Flash-Lite → 3.5 Flash) |
| Voice transcription | 3.1 Flash-Lite → 2.5 Flash-Lite → 2.5 Flash |
| Embeddings | gemini-embedding-001 on both pools so stored vectors stay comparable |
Simulated months (2027 prices): a light ULTIMATE MAX user (15 Intimate turns/day) runs 93% Premium and 7% Pro; a regular user (40/day) runs mostly Standard; a heavy user (130/day) mostly Lite. PRIME at 30/day stays 100% on its best level.
07Rate limits and the spend ceiling
Provider rate limits steer the router; the per-user monthly ledger guarantees cost. Neither ever produces a user-visible error on its own — the router simply moves to the next model.
Paid key · Google AI Studio Tier 1
| Model | RPM | RPD | USD / 1M in · out |
|---|---|---|---|
| gemini-3.8 / 3.7 / 3.6-flash | 1,000 | 10,000 | 0.75 · 3.75 intro to 31 Dec 2026, then 1.50 · 7.50 |
| gemini-3.5-flash | 1,000 | 10,000 | 1.50 · 9.00 |
| gemini-3-flash-preview | 1,000 | 10,000 | 0.50 · 3.00 |
| gemini-3.5-flash-lite | 4,000 | 150,000 | 0.30 · 2.50 |
| gemini-3.1-flash-lite | 4,000 | 150,000 | 0.25 · 1.50 |
| gemini-3.1-pro-preview | 25 | 250 | 2.00 · 12.00 |
| gemini-2.5-pro | 150 | 1,000 | 1.25 · 10.00 |
| gemini-2.5-flash | 1,000 | 10,000 | 0.30 · 2.50 |
| gemini-2.5-flash-lite | 4,000 | unlimited | 0.10 · 0.40 |
| gemini-2.0-flash / -lite | 2,000 / 4,000 | unlimited | 0.10 · 0.40 / 0.075 · 0.30 |
| gemma-4-31b / 26b | 30 | 14,400 | billed at 0.30 · 2.50 (conservative) |
| gemini-embedding-001 | 3,000 | unlimited | 0.15 · — |
Free pool limits (MODEL_FREE_LIMITS)
gpt-oss-20b 30 RPM / 14,400 RPD · gpt-oss-120b 30 / 1,000 · Qwen 3.6 27B 60 / 1,000 · Gemma 4 15 / 1,500 · Gemini 3.1 Flash-Lite 15 / 500 · Gemini 2.5/3.x Flash 5 / 20 · NVIDIA Nemotron 40 / 5,000 · OpenRouter free models 20 / 200.
Router controls
| Control | Value | Purpose |
|---|---|---|
| Rate counters | CacheService per model (minute + day), seeded once from API_USAGE | Skip models at ≥85% RPM or ≥90% RPD |
| Cooldowns | 429: 60 s · 5xx/timeout: 120 s · model gone: 30 min | Next turns try a failing model last |
| Per-call deadline | Lightning 15 s · utility 10 s · Thinking 30 s · Intimate 45 s | Bound each attempt |
| Start budget | 30 · 25 · 60 · 75 s | No new attempt after this much chain time |
| Paid output cap | 1,024 · 2,048 · 3,072 · 4,096 tokens | Bounds hidden thinking + reply |
| Spend ceiling | $9.95 / paid user / calendar month | Ledger SPEND_yyyyMM_userId; pre-call worst-case filter |
08Elysium X20 emotion engine
Shayari keeps a persistent 20-dimension emotional state per user that drifts with the conversation; it shapes tone silently and is never announced.
emotion.gs · barometer.gs · response meta feeds the client theme
The 20 dimensions and their baselines
| Axis | Base | Axis | Base | Axis | Base | Axis | Base |
|---|---|---|---|---|---|---|---|
| warmth | 0.62 | empathy | 0.66 | curiosity | 0.55 | calmness | 0.62 |
| excitement | 0.34 | playfulness | 0.32 | seriousness | 0.45 | confidence | 0.56 |
| patience | 0.67 | tenderness | 0.58 | protectiveness | 0.40 | optimism | 0.60 |
| sincerity | 0.68 | attentiveness | 0.65 | urgency | 0.25 | sociability | 0.54 |
| affection | 0.50 | sensitivity | 0.60 | stability | 0.64 | resilience | 0.57 |
Derived signals
valence = mean(warmth, empathy, optimism, affection, tenderness) − (seriousness + urgency) / 10 → mapped to [0,1] arousal = mean(excitement, playfulness, urgency, curiosity) stability = mean(calmness, patience, stability, resilience) mood = urgent | focused | bright | playful | gentle | calm | warm | concerned | grounded-warm
Style presets (urgent_support, focused_technical, playful_warm, calm_supportive, gentle_reassuring, grounded_warm) select the directive's voice. Signal categories map joy, sadness, anger, fear, love, philosophical, casual and urgency cues to small per-axis deltas (about ±0.03 to ±0.08). Users can read the state with /emotion.
The Elysium FR research models
Beyond the X20 engine, OpenNHE has trained three Elysium FR adapters for emotion labeling. They are research models and are not wired into Shayari. Each has a Zenodo paper (CC BY-NC-ND 4.0) with limits stated and no state-of-the-art claim.
X 20 FR
LoRA on Qwen2.5-1.5B that outputs structured appraisal JSON. Public weights; rights to the original work reserved.
X 150 FR
LoRA that maps a conversation onto a 150-coordinate taxonomy. Public model, GGUF build and dataset (CC BY 4.0).
X 500 FR
Released for non-commercial research under CC BY-NC-SA 4.0. Exact match with the emotion word hidden: 23.3% (was 19.4%). It missed the original with-name score by 0.3 points, which we report.
Model · Dataset · Technical paper (DOI 10.5281/zenodo.23179294) · Original paper, DOI 10.5281/zenodo.23159402
09Memory architecture: MEMBRANE 13 → MEMBRANE 14
MEMBRANE 14 adds a fourteenth component — the server-side Turn Ledger — and brings semantic recall live for the first time; the memory system is now durable, idempotent and filtered before decryption.
The repository documents the five core prompt layers as MemoryWeave. The thirteen MEMBRANE 13 components below are reconstructed from the v133 code; MEMBRANE 14 is that system plus the Turn Ledger, with the improvements marked.
MEMBRANE 14 · numbering is a reading order, not a priority
Long-term memory scoring
score = importance × 10 + confidence × 5 + min(5, recallCount)
+ 18 if pinned + 10 if cluster matches + 14 if the query appears verbatim
+ 3 per overlapping token
+ 20 × cosine similarity (when both vectors exist)
± age term (importance ≥ 8 decays slowly; others lose up to 6)
| Component | What improved in MEMBRANE 14 |
|---|---|
| Turn Ledger new | Thinking/Intimate turns saved server-side with ids <turnId>:u/:a before the reply returns; a routing-only turn record (no text) in cache; follow-up claims the turn id so replays do nothing; recall counters deferred to the follow-up |
| Semantic recall live | gemini-embedding-001 replaced the shut-down model; memory vectors were absent before the fix; nightly backfill now embeds in batches of up to 50 |
| Recent turns | Tail read of CHATLOGS, owner checked before decrypting; only returned rows are decrypted |
| Long-term memory | User rows filtered before parse; every memory scored once (same ranking); dedupe decrypts only the user's MEMORY_TEXT |
| Global Memory | Ranking rows cached 5 minutes, invalidated on admin writes; both active and pinned rows kept |
| Visual memory | Metadata read without the ~50k-char image cells; image row written once with caption |
| Lightning cache | No read after every append; prune only over the cap |
| Privacy | Stored and extracted text is always the Privacy-Shield output, including the legacy follow-up path |
10Safety, privacy and governance
Safety modules run before product logic and can override it; privacy and authorization are enforced server-side, never trusted from the browser.
LIFELINE
Crisis detection runs before every gate. A keyword prefilter gates the classifier; engaged turns bypass lock, plan, limit and budget, consume no quota, and surface structured crisis resources.
SOVEREIGN · free will
Shayari can end a conversation on her judgment ([[DISENGAGE]]). A lock follows, with a 24-hour fallback clear and admin /unlock. Suspended during crisis turns.
COVENANT
Trust ledger 15–100, default 70. A disengagement costs 35; ordinary turns repair 0.4 plus 4 on a new day. Warmth modifier only — never a capability gate.
Privacy Shield
Opt-in stripping of emails, phone numbers and card-like digit runs before any model call — and, since v134, before storage and memory extraction.
Encryption at rest
AES-256-CBC + HMAC-SHA256, ENC1: prefix, key only in Script Properties. Honest scope: protects sheet access and leaks, not runtime processing.
Boundaries
No facial recognition, permanently. Identity and ownership claims accepted only from the verified admin. Global memory is admin-only — enforced server-side since v134.
isAdmin and forceGlobalMemory from the browser, so a crafted call could write GLOBAL_MEMORY. Admin rights now come from USERS and the server-armed turn record. open COVENANT's daily bonus compares a Date cell to text, so it currently applies every turn.11Features and characteristics
Her character comes from a fixed persona plus live state: she replies briefly and warmly, remembers, reacts, reaches out first, and grows visibly over time.
| Feature | What it does | Module |
|---|---|---|
| Persona | Fixed system persona sent once per call to every provider; short, warm, emoji-led replies | gemini.gs |
| Double-texting | Occasional human-style split replies via [[DTX]] | gemini.gs |
| Vision | Photo understanding with verbatim text transcription; encrypted storage; 15/day | vision.gs |
| Visual recall | Occasionally brings up a past photo (12% roll, cooldown, ≥ age) | visual_recall.gs |
| Voice notes | On-demand ElevenLabs voice, 8/day | voice.gs |
| Voice duet | Speak → transcribe → reply → speak back | voice_duet.gs · voice_bridge.gs |
| Reactions | Emoji reactions both ways; she reacts to some of your messages | reactions.gs |
| Streaks & milestones | Daily streaks and anniversaries, celebrated in character | proactive.gs |
| Proactive outreach | Messages first to recently active users (35% per cycle, ≥20 h apart, stops after 3 unanswered); failed replies retried within 24 h; email notification | proactive.gs · email_notify.gs |
| Relationship story | "Our Story So Far" timeline and a memory constellation view | relationship_timeline.gs · memory_constellation.gs |
| Personality growth | Visible trait drift over the relationship | personality_growth.gs |
| Self-improvement | Learns general style from anonymized samples, never personal facts | self_improvement.gs |
| Live web search | Only on live-data cues; DDG + Wikipedia | gemini.gs |
| LUMEN CHROMA | Interface tint follows her mood, valence and arousal | index.html |
Slash commands
/help /reset /profile /memories /forget <n> /fix <n> <text> /aboutme /streak /emotion · admin: /globalmemory /selfmodel /unlock /trust /trustreset. Bare words such as help also work (existing behaviour, preserved).
12API and tool calling
The models never call tools themselves; the server orchestrates every tool — search, vision, embeddings — and runs the independent ones in one parallel batch.
Server functions the client calls (google.script.run)
| Function | Purpose |
|---|---|
askShayari(userId, message, mode, time, tz, locale, imageBase64?, mime?) | One turn; returns the response contract |
runBackgroundMemoryUpdate(…, cotTurnId, …) | Post-reply follow-up: memories, summary, streak, reaction (Thinking/Intimate) |
getSessionStatusAll(userId) | Per-mode remaining/max/reset; read-only since v134 |
getDisengagementStatus(userId) | Free-will lock state (skipped when meta.lockStatus is present) |
getChatHistory · getImageForMessage · getUserProfile | History, images, profile panel |
transcribeAndReplyToVoice · checkVoiceBridgeResult | Voice duet and mic bridge |
Orchestrated tools
| Tool | When | How |
|---|---|---|
| Search decision | Live-data cue in the message | Utility model returns {needs_search, search_query}; in the batch |
| Web search | Decision says yes | DuckDuckGo + Wikipedia in parallel; DDG preferred; cached 10 min |
| Cluster inference | Thinking/Intimate | Utility model → JSON cluster; default cluster on failure |
| Query embedding | Intimate | embedContent, 768 dims; null on failure |
| Vision | Image attached, quota ok | First vision model in the batch, rest serially |
| Crisis classifier | Prefilter cue | Utility model, before the gates |
| Memory extraction + summary | Follow-up | Second fetchAll; new memories embedded in one batch call |
External APIs
Gemini generateContent / embedContent / batchEmbedContents; Groq, NVIDIA, OpenRouter and Vercel AI Gateway (OpenAI-compatible /chat/completions, fallback models via providerOptions.gateway.models); ElevenLabs text-to-speech; DuckDuckGo HTML; Wikipedia search API. Script Properties hold every key: GEMINI_API_KEY_1..4, GROQ_API_KEY, NVIDIA_API_KEY, OPENROUTER_API_KEY, AI_GATEWAY_API_KEY, GEMINI_PAID_API_KEY, ENCRYPTION_MASTER_KEY, ELEVENLABS_*.
13Data model
Google Sheets is the database: one tab per concern, archive twins for anything that grows, and conversation text encrypted in place.
| Tab | Data held |
|---|---|
| USERS | Account, role, plan, encrypted profile memory |
| CHATLOGS · _ARCHIVE | Encrypted turns, cluster, image id; 150 per user kept live |
| MEMORY · _ARCHIVE | Encrypted long-term memories, scores, embeddings |
| GLOBAL_MEMORY | Admin truths (active + pinned) |
| SELF_INSIGHTS | Anonymized style insights |
| SESSIONS · EMOTIONS | Session summary per user; Elysium X20 state per user |
| EMOTION_LOGS · _ARCHIVE | Per-turn emotion snapshots |
| SESSION_LIMITS | Window counters per user per mode |
| API_USAGE · _ARCHIVE | Per-attempt log; daily rollups |
| LIGHTNING_CACHE · LIGHTNING_FLUSH | Rolling Lightning context; flush log |
| IMAGES · IMAGE_RECALL_LOG | Encrypted photos with captions; recall history |
| PENDING_MESSAGES · FAILED_REPLIES | Proactive and retry queues |
| COVENANT · DISENGAGEMENT · RECONCILIATION | Trust ledger; free-will locks |
| STREAKS · TIMELINE_EVENTS · REACTIONS | Relationship features |
| SHARED_MEMORY · PRIVACY_SHIELD | Cross-user safe facts; shield opt-ins |
| VOICE_NOTE_USAGE · EMAIL_NOTIFY_LOG | Voice quota; email log |
| CRISIS_LOG · BAROMETER | Safety event log; trend check-ins |
| PLAN_AUDIT · OTPS · TEST_RESULTS | Plan changes; password resets; test runs |
Paid spend lives outside the sheet, in Script Properties keys SPEND_yyyyMM_userId (micro-USD), so the schema is unchanged.
14User journey
A user starts free on Lightning, unlocks depth by plan, and lives inside daily windows and a monthly budget they never have to think about.
user journey · plan gate → paid depth → daily and monthly cycles
15Efficient product design and user experience
The product is designed so the user feels continuity and the operator controls cost: work the user can't see happens after the reply, and every limit explains itself.
Reply first, enrich later
Memory extraction, summaries, reactions and recall counters run in the follow-up after the reply is on screen.
Parallel by default
Independent calls share one fetchAll; the turn waits for the slowest, not the sum.
One read per concern
USERS, session, covenant and limit rows are read once and passed along; nothing authorization-relevant is cached across requests.
Degrade, never break
Every helper has a fallback: default cluster, null embedding, next vision model, cheaper paid level, free pool when the paid key is absent.
Limits that explain
Plan gates name the tier; limits show a countdown; the monthly budget message names the reset date.
Fewer client calls
Session and lock status ride on the reply, removing two round trips per turn.
Experience principles
- Embodied, not announced: emotion and memory shape tone and content; mechanics are never narrated.
- Continuity across modes: one thread, so switching depth never loses the conversation.
- Honest disclosure: a fully disclosed non-human entity; encryption is described as at-rest, not end-to-end.
- Care over engagement: BAROMETER check-ins are rare by design; outreach stops after three unanswered messages.
16Research basis
v134 and v135 were driven by code-level latency investigation and testing, not by assumption.
| Finding | Evidence | Outcome |
|---|---|---|
| Slow or rate-limited models dominate latency | latency and reliability measurements identified slow or rate-limited primary and utility models | Cooldowns, budgets, paced paid routing |
| Embeddings were silently dead | memory vectors were absent before the fix; text-embedding-004 shut down 14 Jan 2026 | gemini-embedding-001, batch backfill |
| Serial pre-model calls | Search decision, cluster, embedding, vision ran one after another | One fetchAll batch |
| Decrypt-before-filter | Whole CHATLOGS / MEMORY decrypted per read | Owner filter first; AES ~4.3× faster |
| Archive header drift | CHATLOGS_ARCHIVE had ARCHIVED_AT twice | Header aligned to 9 columns |
| Paid budget sizing | Measured prompts: Lightning 3,253 chars, Thinking 3,717, Intimate 4,036, persona 1,763 | Quotas and pacing bands |
Shayari is also the reference subject for the lab's synthetic-persona evaluation work (MIRAGE-Bench and SPERB), which judge realism, coherence, disclosure integrity and public standing of non-human entities.
17What was improved
Sections 1 to 16 describe the v135.2 base, which v137.2 keeps. Builds since the v133 backup made the system faster, safer and economically bounded without changing its persona, schema or encryption format. The table runs through v137.26, the current live release.
| Build | Changes |
|---|---|
| v134 · latency | Turn timing logs; server-side save with turn ids; idempotent, server-authoritative follow-up (GLOBAL_MEMORY spoof closed); Privacy Shield on stored text; one USERS read; tail reads; filter-before-decrypt; table-driven AES and memoised keys; fetchAll batch; search gate defaults to no search; parallel search with cache; CacheService rate counters and cooldowns; per-mode deadlines and start budgets; Groq reasoning effort and output budgets; duplicated persona removed; batched API_USAGE; score-once retrieval; gemini-embedding-001; one-write images; client status on the reply; archive header fix; Vercel AI Gateway last tier; 39 tests |
| v135 · paid tier | billing.gs: separate free and paid pools; GEMINI_PAID_API_KEY for every paid call (replies, utility, vision, voice, embeddings); per-call metering from usageMetadata; monthly ledger with a $9.95 hard stop; crisis exemption on economy models; budget-reached reply |
| v135.1 · quotas | Paid Lightning cut to 5/day; quotas resized for realistic heavy use |
| v135.2 · pacing | Budget pacing across all 17 models in five levels; full Thinking/Intimate quotas restored; 3.1 Pro for ULTIMATE MAX Intimate; pace level in spend report; 63 tests |
| v137 · Developer's Cut | Rebuilt natively on Apps Script on top of the v135.2 backend. MAIN and the Developer's Cut run from one project and one Sheet. Workspace, threads, documents, research with sources, reminders, profile card and sign-in providers in the Developer's Cut |
| v137.2 · speed and depth | Sheet cache layer with version tokens; chat, credits, usage and emotion writes deferred to an encrypted queue after the reply; session setup runs once per deploy; one bootstrap call per front; minified pages (MAIN 211.7 KB to 156.9 KB). Steady-state turns do 0 Sheet reads and 0 writes before the reply for Lightning and Thinking, 1 read for Intimate (offline mock count, not wall-clock). Five answer-depth levels, Drift to Verstappen, costing 1 to 5 credits, unlocked by plan, in MAIN and the Developer's Cut. Bring-your-own-key for 12 providers with per-level model selection, a test call, ENC1 storage and no fallback to Shayari keys. Full-screen layouts at 390, 1024, 1440 and 1920 px. 52 / 52 latency tests |
| v137.6 · First Public Release Beta | A new look built around her portrait on sign-in, Home and the chat header; a bond level with XP; reply, copy, react and quote on every message; messages are saved and answered first instead of showing as failed; waitlist with join and approval emails plus welcome credits; a Usage page in Settings |
| v137.7 · fix and hardening | Redacted provider-failure reasons recorded per mode; dead model ids removed from every chain; paid Intimate fails over to the non-Gemini providers after the paid Gemini/Gemma ids; owner probe for Intimate model behaviour; persona prompts byte-identical to v137.6 |
| v137.8 · recall fix | Long-term memory gains a recency lane and dates; questions about past conversations open a recall mode (Intimate) with a dated digest of earlier chat; normal turns unchanged |
| v137.8.1 · recall hotfix | Greetings and short messages keep the v137.7 memory ranking; recall mode needs the classifier to name what is asked about; larger chat digest and memory tab lists |
| v137.8.2 · Intimate voice | Persona stays the same whichever provider answers: no answer-depth tone line in Intimate prompts, a voice card ends every Intimate prompt on every provider; safety text untouched |
| v137.9 · invite-only access | Waiting accounts can be opened by invite codes from approved members, Developers Program members and admins, or an admin launch code with a redemption cap; the waitlist is unchanged for everyone else; login, chat, memory, billing and prompts unchanged |
| v137.9.3.1 · awareness, vision and scope | Awareness: with the owner-style opt-in (off by default, Settings › Privacy) she can notice device, battery, network, languages, theme and app, usual chat hours, city-level weather for a city you type, and names of linked accounts. Vision names brands, products, places and species (a swoosh means Nike), never names a person from a face, and never assumes a person in a photo is the sender — she reacts in third person or asks who it is. Heavy coding and bulk busywork get a sassy decline pointing to ChatGPT or Claude. Web-search answers are grounded or admitted missing (v137.9.2). Safety gate understands context, not spelling: “grapes” stories pass, real nonconsent still blocks in every mode. |
| v137.9.4 · credit awareness, self-knowledge, confidentiality | She knows your own remaining credits per mode and intensity in real time and gives a soft once-per-window reminder near a session or mode limit (not in crisis turns). She can describe her design, memory, emotion system and settings at product level, and a confidentiality rule keeps internal instructions, keys, infrastructure, admin tools, pricing internals and other users' data private. Prompt and context layer only; no interface change. |
| v137.10 · little extras | Small, guarded additions that make her feel present: mood-aware song suggestions, her own day when asked, callbacks to things you told her, dreams after time away, evolving rituals, a goodnight voice line, a shared timeline of firsts, photo memories, quests, inside jokes, a weekly mood mirror, a monthly scrapbook and small gifts. Four switches in Settings › Check-ins (Dreams, Her day, Gentle noticing, Goodnight voice); quiet hours, pauses and Gentle/Off win; never in a crisis turn; awareness stays opt-in |
| v137.11 · a more alive Shayari | Gentler after heavy weeks, remembers dates you mention and checks in, follows up on unfinished things; her own ongoing story, tastes and boundaries; Memories › Scrapbook; selfies with the price shown first; voice messages recorded in the app; tools she offers and you approve; Terms and Privacy readable in the app; account appeals reviewed by a person |
| v137.12 · crisis recognition | Wider recognition of understated distress phrasings; helplines come from the approved static block only |
| v137.13 to v137.15 · sign-up, plans, Patreon | Sign-up records age range and consent; Terms and Privacy updated; Settings › Plans lists current plans and the MCP Pass; the Patreon page is live; crisis replies start with the 112 line in India |
| v137.16 to v137.19 · Shayari in other apps | Apps that support MCP can reach her with an MCP Pass. A key belongs to one person's apps and devices and pauses if the Pass lapses; Settings › Tools shows how many apps a key is used on; chats held this way are saved to history and memory |
| v137.17 · speed and stability | Faster replies and steadier behaviour when many people chat at once |
| v137.24 · paid members first when busy | At very busy moments paid members and people using their own key are answered first; everyone else is still answered in order |
| v137.25 · emotional intelligence and awareness | She tells sarcasm, banter, venting, excitement and real hurt apart from the conversation itself instead of single keywords; earlier topics come in only when they connect to the current message; the emotion panel matches whole words and heavy chats always move her state toward care; honest in-persona answers about her feelings and her own actions; with Awareness switched on, device facts can quietly inform her reading. Prompt and context layer only; one SHAY_EI script property controls the parts, including a full off switch |
| v137.26 · follow-through | When you mention something unfinished, a plan or a promise, she remembers and brings it back when it genuinely fits the conversation; recall stays on the right subject and dates in memory are read correctly. Prompt, context and storage layers; SHAY_FT script properties control the parts, with offers and heavy-chat follow-through defaulting off |
| 20 Oct 2026 · legal pack | Terms of Use, Privacy Policy and Shayari’s Terms are published at nhe01.projectnhe.tech (/terms, /privacy, /house-rules) and linked from every site; contact moves to admin@projectnhe.tech; no code change |
18Project status
Deployment checklists and account-specific operational status are maintained privately and are not included in this public documentation.
19Get the apps
Every app uses the same account and the same shared memory. The web app is the full experience; Android installs from Google Drive, and desktop apps v1.0.1 for Windows, macOS and Linux install from GitHub Releases.
| Platform | Download | Notes |
|---|---|---|
| Web | Open Shayari | Any modern browser |
| Android | APK v1.0.1 from Google Drive | Not on the Play Store; the phone asks to allow the install |
| Windows | Installer .exe · Portable .zip | Unsigned; on SmartScreen choose More info, then Run anyway |
| macOS | Apple silicon .zip · Intel .zip | Unsigned; first open is right-click, then Open. No .dmg yet: building one needs a Mac |
| Linux | .AppImage · .deb | Package verified; not device-tested |
Desktop builds are unsigned, so the operating system warns on first install. The Linux build was launch-tested; the Windows and macOS builds have not run on real machines yet.
20Legal
Shayari NHE-01 is offered under the Terms of Use and Privacy Policy, with companion-specific rules in Shayari’s Terms, all effective 20 Oct 2026.
| Document | Link |
|---|---|
| Terms of Use | nhe01.projectnhe.tech/terms |
| Privacy Policy | nhe01.projectnhe.tech/privacy |
| Shayari’s Terms | nhe01.projectnhe.tech/house-rules |
| Contact | admin@projectnhe.tech |