Spaces:
Running
Running
Commit History
-
Deploy: real velvet bg + Annoying/Beryl Way labels on comparison banner Running
AIBRUH35b5788
-
Deploy: real green velvet fleur-de-lis photo in Build/Create/Deploy banner
AIBRUH40e6be6 -
Deploy: EasyBanner bold statement + tablet nav fix
AIBRUHdc5f14f -
Deploy: Clique-first site, mobile 2026 pass, Cleo hero, Beryl Suite
AIBRUH485e5cb
-
docs: expand all 4 Runway prompts to full verbose production briefs
AIBRUH +1: Claude Sonnet 4.6Each segment now includes: complete character physical descriptions, exact screen content, camera movement, depth of field, color grade, film look, full audio direction with timing, and mood guidance. Shooting order recommendation added. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>0c22e13 -
fix: nav restructure + MatineeBanner video upgrade
AIBRUH +1: Claude Sonnet 4.6- Nav: The Clique -> /clique-promo (was /#clique anchor) - Nav: removed /clique studio link (only accessible from Clique landing page) - Nav mobile menu: matches desktop changes - MatineeBanner: replaced animated SVG cars with muted matinee-hero.mp4 video Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>df8ac6a -
feat: PinGate security overlay + sovereign agent architecture plan
AIBRUH +1: Claude Sonnet 4.6- PinGate component (PIN 2440): sessionStorage, shake animation, Beryl brand - /privacy, /terms, /api-docs, /contact pages all gated behind PinGate - Footer.tsx: href links replaced with Next.js Link to real pages - docs/CLIQUE_AGENT_ARCHITECTURE.md: full 3000+ word agent stack blueprint - Nu=Qwen2.5-72B, Amanda=Llama-3.1-70B, Jeff=GLM-4, India=Mistral-7B - Plug-and-play HF inference router design - Skill MD system + 20 ABSOLUTE DOMINATION features - 7am-10am implementation sequence for July 1 - HANDOFF.md updated with morning plan and doc pointer Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>c9d99b4 -
fix: resolve TS type errors blocking HF Space build
AIBRUH +1: Claude Sonnet 4.6- ltx/generate/route.ts: cast rawData.output before accessing .data to satisfy TS - ltx-studio/page.tsx: type jobA/jobB as the full union type instead of as-const narrow so status field accepts awaiting_approval and failed assignments Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>95d0540 -
feat(clique-promo): add video hero (banner 1) and Marcus phone scene (banner 2)
AIBRUH +1: Claude Sonnet 4.6- Banner 1: VideoHero — autoplay video player ready for /videos/clique-hero.mp4 Shows polished fallback (gold grid, drop instructions) until video is placed Muted autoplay, loop, playsInline pattern consistent with matinee hero - Banner 2: MarcusPhoneBanner — full-bleed dark section with floating phone mockup Realistic iPhone shell: side buttons, dynamic island pill, status bar, battery Screen: 2x2 agent tile grid (Amanda/India/Jeff/Nu) with live/listening states Amanda tile shows LIVE badge + animated gold ring; others show listening dots Marcus self-view PiP bottom-left; call controls bar at bottom of screen Phone floats and glows on a 4s animation loop Right side copy: headline, 4 feature bullets, pull-quote from Marcus, CTA Mobile responsive: stacks to column on narrow viewports - Former Banner 1 (Cleo hero) demoted to Banner 3 — all subsequent sections shift Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>2579547 -
feat(clique): Clique Chat tab with group and private DM channels
AIBRUH +1: Claude Sonnet 4.6- CliqueChat component: left sidebar with Group channel + individual DMs to each v1 agent - Live preview tab bar added above build-mode project previewer - Tab bar: Live Preview / Clique Chat, gold underline on active, smooth transitions - Messages: CLS mini avatars, grouped runs, user messages right-aligned, agent messages left - Typing indicator with animated dots showing which agent is composing - Input supports group channel or private DM context label - /api/clique/chat route: native fetch GPT-4o, sequences agent responses so agents can react to each other - Agents respond in order using their master system prompts from clique-agent-prompts.ts - resolveResponders() determines who speaks for group messages Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>04bd015 -
feat(clique): wire v1 team roster, agent prompts, handoff protocol
AIBRUH +1: Claude Sonnet 4.6CliqueRoom: v1 team only (india/jeff/nu), new QUICK_ACTIONS and inferAgentsFromText Amanda opener: Hey, I'm Amanda. Tell me what you're building. New agents join as silent-listening; detectAmandaHandoff flips them active resolveResponders wired to user speech transcript for routing AgentTile: silent-listening state, dimmed with Listening badge useAmandaVoice: onAmandaTranscript + onUserTranscript callbacks realtime-token route: uses getAgentPrompt master system prompt Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>3c4c329 -
docs(handoff): cold-boot handoff for account switch — Clique v1 + commercials
AIBRUH +1: Claude Opus 4.8Rewrite the top of HANDOFF.md so a fresh Claude account on a different login can pick up from zero in ten minutes without re-deriving anything. - WHERE TO START: 6-step cold-boot checklist. First stop is lib/clique-agent-prompts.ts (the core deliverable of this session). - CLIQUE v1 team locked in as India/Jeff/Nu/Amanda — every prior stale reference to Eve/Brice removed. Full spec, portraits, meeting protocol (Amanda-first intake, canonical handoff phrase, pre-introduction silence, group-greeting override, close-and-handback), runtime stack (realtime-live2 + Runway + MS Agent Framework + LiveKit). - CLIQUE v1 code file inventory with status flags (SHIPPED / EXISTS-needs- rewiring) so the next session can see at a glance what's done vs. TODO. - REMAINING WIRING: 7 ordered steps. Point CliqueRoom at getV1Team, feed master prompts into Realtime sessions, wire resolveResponders + detectAmandaHandoff, pre-introduction silence rule, Amanda's canonical opener, portrait swap.…ada656a -
docs(commercial): reframe 40s close — first of its kind (video chat with AI agents)
AIBRUH +1: Claude Opus 4.8Remove funding-round line from the close and the on-screen text. The category claim is now the whole point: 'The first of its kind. Video chat — with your AI agents. Not prompts. Not chatbots. People. This is how we do AI now.' Segment 4 retitled THE CATEGORY (was THE BET). On-screen text under the wordmark now reads 'The first of its kind. / Video chat with your AI agents · berylize.com'. Deck paragraph updated to match. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>f6ac84a -
docs(commercial): 40-second Runway funding promo — 4x10s sound-native
AIBRUH +1: Claude Opus 4.8Compact 4-segment script for the Runway build UI (sound-native model, credits-side, not API). Each 10s prompt is copy-paste-ready and includes: in-clip narration lines, background sound design, camera direction, and character reference callouts. Arc: Problem (Marcus + faceless bots) → Solution (Amanda arrives, canonical opener) → Team (India, Jeff, Nu join by name via Amanda's canonical handoff phrase) → Bet ("The first Clique of its kind. Funding round — open.") Marcus is prompt-generated (supporting character). Amanda, India, Jeff, Nu use existing SHIELD portraits as reference stills — they are the four brand faces that must remain identifiable. Transition seams and audio-continuity notes included so the four clips stitch clean end-to-end. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>0c685c6 -
docs(commercial): CLIQUE_COMMERCIAL_V2 — the faceless-agent problem
AIBRUH +1: Claude Opus 4.8Revise the earlier commercial script (CLIQUE_COMMERCIAL.md) to make the villain the *facelessness* of today's AI agents (nameless bots, empty avatars, one-way transcripts) rather than generic "complexity". The resolution is now product-truthful to the v1 meeting protocol we just shipped: Amanda arrives → intake → brings in India / Jeff / Nu by name → four faces on realtime-live listening. New signature turn: Scene 4 ("Amanda Arrives") — the faceless dashboards dissolve and Amanda's face warms into the frame with the canonical opener "Hey — I'm Amanda. Tell me what you're building." Subsequent scenes introduce India, Jeff, Nu one at a time using the exact handoff phrase from clique-agent-prompts.ts. Includes a v1→v2 diff table and reuses existing SHIELD portraits as reference stills (no new character generation needed). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>9e6ccbd -
feat(clique): v1 meeting protocol — Amanda-first intake + handoff phrase
AIBRUH +1: Claude Opus 4.8Every meeting starts with Amanda alone. India/Jeff/Nu are on realtime-live listening from meeting start but silent until Amanda introduces them by name. - INTAKE PROTOCOL added to Amanda's master prompt: greet → listen → mirror goal → decide solo vs. team → execute or introduce by name. - CANONICAL HANDOFF PHRASE: "I'm bringing in <Name> — <Name>, take this." Frontends key off this via detectAmandaHandoff() to flip silent-listening → active. Say the name twice, exactly as written. - SHARED CORE preamble updated: pre-introduction silence rule for India/Jeff/Nu ("Listening." deference if named before Amanda's intro), group-greeting override still stands. - CLOSING PROTOCOL: Amanda summarizes decisions + ownership, hands back cleanly ("That's yours to take from here. Ping us when you need us."). - HANDOFF.md updated with the locked-in meeting protocol. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>ff368d0 -
fix(clique): v1 team is India + Jeff + Nu + Amanda (not Eve/Brice)
AIBRUH +1: Claude Opus 4.8Correct roster to match uploaded portraits — replaced Eve and Brice master prompts with Jeff (Operations/Delivery) and Nu (Innovation/Lateral Thinker), kept India (Growth) and Amanda (Supervisor, MS Agent Framework). Amanda's routing hints updated: India for reach, Jeff for shipping, Nu for the non-obvious angle. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>fecf74a -
feat(clique): v1 reduced 4-member team — master agent prompts
AIBRUH +1: Claude Opus 4.8Switch active focus from The Gym (done) back to Clique. Reduced v1 = 4 members: Amanda (supervisor, Microsoft Agent Framework), Eve, Brice, India — all top-tier software engineers (15+ yrs FANG), named role = lens not fence, any member can own any task end-to-end. - lib/clique-agent-prompts.ts (NEW): full master system prompts for all 4 agents. Shared CORE preamble encodes the conversation protocol: active-listening default, speak-only-when-named, all-four-reply on group greeting. Includes isGroupGreeting() and resolveResponders() routing helpers. - lib/clique-roster.ts: add CLIQUE_V1_TEAM_IDS + getV1Team() (amanda, eve, brice, india). - HANDOFF.md: document Clique v1 pivot, spec, files, and remaining wiring; mark The Gym as frozen/done. No pre-baked loops in Clique — user powers extra members via own API key. Runtime: OpenAI realtime-live2 (voice/computer-use), Runway (alive/listening state), MS Agent Framework (Amanda's orchestration). Co-Authored-By: Claude Opus 4.8 <nore…3e0fca2 -
docs: update HANDOFF for v3 two-state video avatar (idle + talk loop)
AIBRUH +1: Claude Opus 4.8Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>3a5c2ce
-
asset: add eve_idle.mp4 breathing/blinking idle state video
AIBRUH +1: Claude Sonnet 4.6Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>287fbfe -
feat: two-state video system — idle loop + talk loop, no wave greeting
AIBRUH +1: Claude Sonnet 4.6- eve_idle.mp4 (generating now via Wan2.2): breathing, micro-expressions, blinking — plays at all times including on load, no overlay - eve_talking_loop.mp4: lips moving — swaps in only while audio plays, swaps back to idle on audio.onended - Removed wave greeting entirely: no competing videos, no unnatural looping - Eve speaks her greeting through TTS only (no visual state change on open) - Clean two-state machine: IDLE_VIDEO <-> TALK_VIDEO, driven by audio events Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>8d6bc51 -
feat: Eve always alive — no overlay, video plays from first frame
AIBRUH +1: Claude Sonnet 4.6- Overlay and end screen completely removed - Video layer always on: EVE_WAVE_VIDEO on mount, EVE_TALK_VIDEO after first reply so Eve is never a still image — real Wan2.2 motion at all times - Wave greeting video (eve_wave_greeting.mp4, 1.2MB) generated and committed - After audio ends Eve stays on talk loop, not a frozen portrait - Hardcoded name TJ for testing; overlay reinstall brings it back - Cleaned up unused state (phase, nameInput, visemeKey, VISEME_IMG) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>7dfa92f -
feat: Eve opens the conversation on page load, no overlay, addresses TJ
AIBRUH +1: Claude Sonnet 4.6- Skip overlay: phase starts as "session", userName hardcoded to "TJ" - On mount, Eve fires __OPEN__ trigger through the full pipeline (Grok+TTS+visemes) with a wave greeting — no scripted fallback text, live Grok response - Fix: scripted calls now send userText (not "") so route never hits "text required" - route.ts: __OPEN__ gets a dedicated opener system prompt ("wave hello, introduce yourself, ask TJ one question, 2 sentences max") - Confirmed live: "Waving hello! I'm Eve, your warm companion at Beryl AI Labs — what's lighting you up today?" Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>40a63ad -
chore: revert debug state, update HANDOFF doc
AIBRUH +1: Claude Sonnet 4.6- page.tsx: restore phase="overlay", userName="", timeLeft=180 (reverts debug values set during screenshot capture attempts) - HANDOFF.md: full rewrite documenting viseme-driven pipeline, fn_index map, grapheme classifier, HF space statuses, constraints, and next steps Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>9b7a72f -
feat: viseme-driven real-time lip sync for Eve (no pre-baked loop)
AIBRUH +1: Claude Sonnet 4.6Replace the eve_talking_loop.mp4 pre-baked loop video with genuine phoneme/viseme-driven animation synced to TTS word-boundary timestamps: - eve-tts space (fn_index 1): streams audio + WordBoundary events via edge-tts boundary='WordBoundary'. Switched from AvaMultilingualNeural (no WordBoundary support) to AvaNeural (standard neural, same voice). - route.ts: calls fn_index 1, returns audioUrl + visemes array [{word, offsetMs, durationMs}] to the client. - the-gym page: wordToViseme() classifier maps each word to a mouth shape (rest/aa/ou/ee/fv/mid) via grapheme heuristic. requestAnimationFrame loop reads audio.currentTime, finds the active word boundary, swaps the displayed face frame in real time. No loop, no repeat — every word drives a different mouth shape from Eve's actual speaking footage. - public/visemes/: 6 PNG mouth-shape frames extracted from Eve's own Wan2.2 speaking video (closed, wide-open, round, smile, teeth, mid). Co-Authored-By: Claude Sonnet 4.6 …cf901f2 -
Real-time Eve: ~8s response via parallel-fast TTS + pre-baked speaking loop
AIBRUH +1: Claude Sonnet 4.6- route.ts: Grok-3-mini -> AIBRUH/eve-tts sequential, returns in ~8s No LatentSync in hot path (was 90s blocker — moved out entirely) - page.tsx: plays eve-tts audioUrl directly + loops eve_talking_loop.mp4 Video switches: still portrait (idle/thinking) -> speaking loop (audio active) Falls back to browser SpeechSynthesis if audioUrl unavailable - public/eve_talking_loop.mp4: Wan2.2 pre-baked 3s speaking loop (1.6MB) Generated once, reused every conversation turn Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>c80aa46 -
Eve alive: wire proven AIBRUH/eve-tts + AIBRUH/latentsync pipeline
AIBRUH +1: Claude Sonnet 4.6- speak/route.ts: replace Voicebox with AIBRUH/eve-tts (Edge-TTS, cpu-upgrade) - queue/join SSE pattern, en-US-AvaMultilingualNeural voice - returns audio bytes for immediate LatentSync upload (avoids URL expiry) - lipsync: AIBRUH/latentsync A10G — uploads eve_wave.mp4 + audio, fn_index 1 - proven: 66s inference, 807KB lip-synced video output - Grok-3-mini backbone unchanged (always returns reply) - public/eve_answer.mp3: Eve's voice (43KB Edge-TTS) - public/eve_speaking.mp4: PROOF — lip-synced talking video (807KB) - public/frames/eve_speaking_frame: screenshot proof of Eve's mouth in motion Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>9f327e9 -
Add HANDOFF.md — cross-session context for Eve alive pipeline
AIBRUH +1: Claude Sonnet 4.6Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>7f9dfff -
Eve alive pipeline: Grok backbone + HF TTS + LongCat lip-sync + Wan2.2 wave proof
AIBRUH +1: Claude Sonnet 4.6- app/api/hf/speak/route.ts: Grok-3-mini backbone (never throws), AIBRUH/eve-tts Edge-TTS, LatentSync lip-sync - app/api/ltx/generate/route.ts: Wan2.2 14B i2v Lightning, correct ImageData format + int frame_multiplier + steps<=30 - app/api/runway/poll/route.ts: placeholder (Runway removed from Gym) - app/api/save-frame/route.ts: dev helper, writes frames to public/frames/ - app/the-gym/page.tsx: Browser SpeechSynthesis fallback, female voice selection, currentVideo state - app/ltx-studio/: LTX video studio page - public/eve_wave.mp4: PROOF - Wan2.2 generated Eve waving (1.22MB, 624x832, 4.06s) - public/wave_proof.html: dev capture page for filmstrip Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>c66931d
-
feat(clique): wire Amanda live loop into CliqueRoom
AIBRUH +1: Claude Sonnet 4.6- useCLSRunner(amanda) added at room level for intro-phase direct CLSTile - useAmandaVoice onSpeakStart: calls goLive(speak) + sets agentStates amanda=live - useAmandaVoice onSpeakEnd: calls returnToLoop() + sets agentStates amanda=listening - Intro CLSTile: receives liveVideoUrl from amandaRunner + onLiveEnded resets all state - Meeting phase AgentTile already has its own useCLSRunner per agent (committed prev) - Amanda voice layer (WebRTC Realtime) -> CLS router -> Layer C Runway clip: fully connected Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>ac1f472 -
feat(clique): CLS loop router + live Runway switcher fully wired
AIBRUH +1: Claude Sonnet 4.6- CLSTile Layer C: live Runway video element with 200ms crossfade over the always-running CLS loop; gold pulse ring while LIVE is active - useCLSRunner: goLive() checks pre-warm cache (instant) then polls Runway at 1500ms intervals; returnToLoop() clears live state - AgentTile: imports useCLSRunner per agent; triggers goLive(speak) on state==live, returnToLoop on exit; pre-warms speak clip 2s after mount so next switch is instant; passes liveVideoUrl+onLiveEnded down to CLSTile - /api/clique/cls-live: Runway gen4_turbo image_to_video endpoint with speak/nod/react/explain mood prompts - Roster: TJ, Dev, Zara, Simone, Finn added (21 members total) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>7d2802a -
fix(clique): correct gender + Zara bold lip — Zara/Cole/Finn/Rhys v2
AIBRUH +1: Claude Sonnet 4.6Zara: bold red lip, curly hair, correct AF-AM styling Cole/Finn/Rhys: now correctly rendered as males (prev gen used female ref) Male ref: Jeff (LILLY) used for blazer+crest style anchor All 4 re-canonized to LILLY folder Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>40cab4e -
feat(clique): 5 new staff members added — Zara, Simone, Cole, Finn, Rhys
AIBRUH +1: Claude Sonnet 4.6Roster grows from 16 to 21 members. New members: Zara — Brand Strategy (AF-AM woman, 26, natural afro, red lip) Simone — UX Research (AF-AM woman, 27, sleek updo, nude glam) Cole — Cloud Architecture (white male, 23, wavy blonde) Finn — Machine Learning (white male, 22, dark textured quiff) Rhys — Security (white male, 24, curtain hair, stubble) All portraits: LILLY standard — navy blazer, BOS crest on pocket, waist-up studio framing. Canonized to LILLY folder. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>40c383f -
feat(clique): new portraits for Bri and Naomi — distinct identities
AIBRUH +1: Claude Sonnet 4.6Bri: East Asian woman, early 20s, sleek black straight hair Naomi: Kurdish woman, early 20s, sculptural dark updo Both: LILLY standard — navy blazer, BOS crest, waist-up studio portrait Both canonized to LILLY folder on disk. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>6e20d8d -
feat(clique): replace all staff portraits with LILLY canonical photos
AIBRUH +1: Claude Sonnet 4.613 members updated from LILLY folder (correct waist-up blazer+crest style): Amanda, Eve, Jamarr, Jessica, Jeff, India, Lacara, Terrell, Brice, Kizzy, Shelly, Nu, Maria 3 members regenerated via Runway Gen4 to match LILLY style: Bri, Naomi, Cleo (previous photos were wrong — sofa/no-blazer/wrong-crest) All 16 roster members now show: navy blazer, BOS heraldic crest on pocket, waist-up portrait, clean studio background. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>33f287a -
feat(clique): CLS Loop Router + OpenAI Realtime voice for Amanda
AIBRUH +1: Claude Sonnet 4.6- cls-loop-router: wave/listen/confirm/live state machine, A/B crossfade, 12-18s auto-rotation - CLSTile: dual video crossfade + CSS breathing fallback with shimmer scan - AgentTile: CLSRouterState prop, all agents always live-loop - use-amanda-voice: WebRTC hook, ephemeral token, greeting on connect, isSpeaking state - api/clique/realtime-token: Amanda CSA persona, shimmer voice, VAD config - api/clique/cls-generate: Runway Gen4 Turbo image_to_video for CLS loop generation - CliqueRoom: removed ALL window.speechSynthesis, Amanda speaks via OpenAI Realtime only Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>f2c3447 -
feat: CLS - every agent always animated, never 2D. Amanda speaks. No SVG overlay.
AIBRUH4cf2b61 -
feat: Build vs Chat mode detection + split layout + conversational turn-taking
AIBRUH89ff67f -
feat: Clique V2 - 2-panel intro, dynamic agent join, BOS shield, build narrative doc
AIBRUHc2153a4 -
feat: Clique becomes video conferencing with humans + AI (berylize positioning)
AIBRUH +1: Claude Opus 4.8- Humans and AI agents share one room (our Zoom/Meet/Webex = 'Clique') - lib/clique-participants.ts: Human/Agent participant model, room codes, invite links - HumanTile + InviteModal components; mixed gallery in CliqueRoom - LiveKit token API route (Web Crypto HS256, no native deps) for real humans to join - Header reframed: 'Video Conferencing with AI - Real Time', live participant count, Invite - Landing hero: 'Video Conferencing, With AI' + berylize = the easy button - GUI mockup now shows humans (You/Tyronne) alongside agents - Commercial revised: berylize easy-button beat + 2nd human engineer joins the clique Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>4d153c3 -
docs: agents wear branded blazers from different WFH locations in meeting scenes
AIBRUH +1: Claude Opus 4.8Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>50b75e7 -
docs: revise commercial - no competitor named, theme 'AI was supposed to be easier', no keyboard/chat box, face-to-face with friends
AIBRUH +1: Claude Opus 4.8Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>575e17d -
docs: full Clique commercial production bible (8 scenes, VO, Seedance prompts)
AIBRUH +1: Claude Opus 4.8Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>12e0327 -
feat: royal velvet innovation banner on /clique-promo
AIBRUH +1: Claude Sonnet 4.6Purple velvet + gold fleur-de-lis backdrop with 4 innovation pillars and pull quote. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>19a7ef4 -
feat: full investor promo page at /clique-promo
AIBRUH +1: Claude Sonnet 4.66 banners — Cleo hero, paradigm shift stats, CrewAI/LangChain code vs Clique GUI mockup, QCR science, GRI collective intelligence, final CTA. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>a86d4f6 -
feat: replace Cleo placeholder with photorealistic Runway gen4 portrait
AIBRUH +1: Claude Opus 4.8Navy blazer, gold lion crest badge, pearl earrings — matches Eve/female roster styling. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>a22e27a -
feat: GRI system + Clique promo page + Cleo portrait
AIBRUH +1: Claude Sonnet 4.6- lib/gri.ts: Group Response Intelligence — keyword trigger detection (free, no API), 8-category vault (CELEBRATION/GREETING/AGREEMENT/ENCOURAGEMENT/ SIGN_OFF/SURPRISE/THINKING), Web Speech API fallback, anti-repeat + 30s cooldown - components/clique/GroupListener.tsx: pure logic detector on live transcript - components/clique/GroupResponseBanner.tsx: animated banner + staggered portraits + live speech line display during group response - CliqueRoom.tsx: GRI wired in (GroupListener + GroupResponseBanner) - components/CliquePromo.tsx: full marketing promo section replacing SquadScroller — hero, 9-agent roster preview with hover personas, 6-feature grid, dual CTA - app/page.tsx: SquadScroller replaced with CliquePromo - public/characters/CLEO_SHIELD.png: Cleo portrait (BOS shield style, Pillow-generated) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>cb92c86 -
Merge remote-tracking branch 'hf/main' into hf-deploy
AIBRUHfee10d5 -
feat: BERYL CLIQUE V1 — /clique room + QCR science + mobile camera + access grants
AIBRUH +1: Claude Sonnet 4.6New /clique page with 10-member grid room, QCR personality science, mobile-safe camera via getUserMedia, Access panel (email/LinkedIn/phone), Call Me feature stub, rapport rings on agent tiles, Cleo (Minutes agent) added to roster. Nav Squad renamed to Clique everywhere. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>b1066a3
-
Add BERYL_AGENT_SKILL.md — full agent briefing for berylize.com
AIBRUH +1: Claude Sonnet 4.6Complete skill file covering architecture, deployment pipeline, brand rules, known gotchas, video patterns, nav rules, and standard workflow. Drop this into any Claude session to instantly recreate full project expertise. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>8b16262