GustaveOnline shopping means typing, filtering, scrolling and comparing across tabs. And most "shopping assistants" just swap the search bar for a chat box: type, wait, see three products, type again, wait again. In a store, you just talk, and someone starts pulling things off the rack while you're still talking. Every reaction you give sharpens what they bring next. Meet Gustave: a voice shopping assistant that recreates that natural, iterative experience.
TypeSafe AI
Slop isn't just AI, it can also be human. Unslop will input a website and cut out all the ineffective fluff/slop with context decisions and browserbase lookup centered around jev decision making.
TypeSafe AIBrowserbase
KYC-SentinelKYC Sentinel: adverse-media screening for AML/KYC analysts. Jev judges, code decides, the LLM only writes. Compliance analysts waste hours clearing irrelevant news hits: same-name strangers, victims, passing mentions. KYC Sentinel pulls news for every client in a portfolio. Jev (TypeSafe AI) judges each client–article pair: same person? the perpetrator? what risk? how severe? A pure, unit-tested router then sorts every client into CLEAR / REVIEW / FLAGGED / NO_COVERAGE. • Fails closed: any uncertainty or model error means REVIEW, never CLEAR. • Autonomy Dial: a compliance manager drags strictness and the whole portfolio re-routes instantly from stored Jev probabilities, with zero new model calls. • Thresholds live in code, not prompts. The LLM only writes analyst memos, on demand, for flagged/review clients, citing sources. It never decides. • Full audit log of every decision, plus a live receipts meter. Results on a 26-client portfolio: 37 Jev calls, 0 errors, 0.9s, $0.0011, about 145× cheaper than the same job on a frontier LLM (est. $0.16). Famous-name collisions (Michael Jordan, Michael Cohen) are cleared as "different person" even when the other person's news is damning. Victims and identity-theft targets are cleared as "not the subject". Vague common-name mentions go to REVIEW. Documented fraud cases and a Tulsa accountant who shares Taylor Swift's name are surfaced, while the pop star's news is ignored. Stack: Jev (TypeSafe AI), FastAPI, GDELT, Gemini for memos, vanilla JS. 77 tests. Data note: GDELT rate-limited our network, so several clients use clearly labelled synthetic articles (domain synthetic-demo.local). Everything downstream runs identically.
TypeSafe AI
A live band you conduct with paintings: arrange artworks on a musical staff, and every bar an AI conductor (TypeSafe Jev) decides how the band plays while Google's Lyria RealTime generates the music. Painting Band 🎨🎶 Arrange paintings on a staff. A playhead sweeps across. Every bar, an AI conductor decides how the band plays, and an AI music model plays it live. Nothing is pre-recorded. The music is generated live from what's on the canvas. How it works 1. See: Gemini looks at each painting and writes how it should sound: mood words, sound ideas (e.g. "cascading koto arpeggios"), instruments, and the painting's musical tradition (Japanese, Hindustani, Western…). Upload your own image and it's described in about 2–3 s. 2. Arrange: Drag paintings onto the staff. - Left → right = when a painting plays - Height = register (high or low) - Size = how strongly its mood and sounds lead 3. Conduct: Every bar (2.7 s), TypeSafe Jev answers up to 12 typed questions in parallel in 150–300 ms: - how loud each painting should be, and the mood and energy - drums, bass and the lead instrument - two extra sounds and the transition - which culture leads when traditions mix Jev never plays notes; it only decides. 4. Play: Jev's choices become weighted text prompts plus density, brightness and mute settings for Google Lyria RealTime, which streams AI-generated 48 kHz audio and blends toward each new decision. The music changes when you move, resize, add or remove a painting. Architecture - Deciders never make sound; engines never make decisions. Code sits in between. - Deadline-safe: if Jev is later than 150 ms before the next bar, the band reuses the last bar's choices, so the music never stops. - Always playing: if Lyria stalls, the app switches to Strudel (a browser-based live-coding music engine) mid-song, and you can switch back with one click. - Explainable: the panel shows each bar's questions and Jev's odds for every option, the exact prompts sent to Lyria, what Gemini saw in each painting, and a live log of every model call. Features - Drag, resize and delete paintings; draggable playhead (Home = start) - Silence where there's no painting under the playhead - Upload any image; Gemini describes it (with automatic model fallback when busy) - Cultural awareness: each painting's musical tradition shapes the sound, and Jev picks which tradition leads - Jev vs. Rules toggle (keys J/R) to hear the difference judgement makes - Live stats: Jev latency, missed bars, and cost ($0.00001 per bar) Tech stack - Vite + React + TypeScript - TypeSafe Jev: per-bar decisions (/v1/systemone, typed choice answers with confidence) - Google Gemini: image understanding (structured JSON output) - Google Lyria RealTime: streaming music generation (@google/genai) - Strudel: fallback engine (@strudel/web, General MIDI soundfonts) - API keys stay server-side behind a Vite proxy (except Lyria, which streams from the browser in this local demo) Run it Open and drag a painting onto the staff. Paintings Seven public-domain works from Wikimedia Commons: Hokusai, Monet, Van Gogh, Bruegel, Seurat, Rembrandt and Raja Ravi Varma.
TypeSafe AIGMI
Real-time persuasion training game — talk your way past an AI guard, investor, or friend, and every sentence is instantly scored and reacted to.
TypeSafe AI
HaleStormI built a web app that uses jev plus browserbase to analyze the claims, entities, statements, laws etc that are discussed in published political articles with a recurssive jev + browserbase research engine to investigate claims, analyze related articles, and display all the results in a unified exploratory UI in near real-time
TypeSafe AIBrowserbaseThe AI Collective
keikokuLive triage of building-management alarms with Jev (TypeSafe). The design is in jev-alarm-triage-spec.md; the original static mock-up is alarm-triage-poc.html. This build replaces the mock-up's scripted answers with real Jev calls behind a Python backend.
TypeSafe AI
tiredcommuterCommute Copilot A live, text-message commute decision assistant for San Francisco — built for JEVATHON. Text it where you're headed. It pulls real live transit data from multiple independent public sources, and Jev picks the option that actually gets you there most reliably — with a calibrated confidence score, not just a list of times. The problem Google Maps optimizes information — it shows you routes and ETAs and leaves the judgment call to you. It also has real, specific gaps: ferry options are inconsistently surfaced, and it has no concept of what you're actually trying to do next. Meanwhile, real commuters (the author included) routinely get left behind by buses whose live conditions diverge from the static schedule. Commute Copilot is the decision layer on top of the data Maps already has: given real-time bus positions, a fixed ferry schedule, live bike/scooter availability, and what you actually told it, Jev picks — and explains its confidence — instead of handing you a list. Live - Dashboard: - iMessage: ask in Discord / at the table for the live demo number Architecture | Layer | Source | Why this one | |---|---|---| | Bus/Muni (live) | 511.org Vehicle/Stop Monitoring API | Real GPS + live delay data, free, official — no scraping needed | | Ferry | Golden Gate Ferry fixed schedule | Ferries run a locked schedule; the gap is that Maps under-surfaces this, not that the data is hard to get | | Bike/scooter (live) | GBFS free_bike_status feed (Bay Wheels) | Open, standardized, no-auth format used by most bike-share systems | | Traffic incidents (live) | 511.org Traffic Events API | Real active incidents with coordinates, same token as transit | | Destination geocoding | OpenStreetMap Nominatim | Free, no key, turns "Mill Valley" into real coordinates | | Google Maps comparison | Browserbase + Stagehand | The one thing with no free API — scraping is the only way to get Maps' own live answer, used as an honest comparison baseline, not a data source we depend on | | Decision engine | Jev Choice primitive | Given the live options + your stated goal, picks (and ranks) the best one with a real probability distribution | | Interface | Photon / Spectrum | One agent, delivered over iMessage — no app to open | | Dashboard | Next.js on Vercel | Same data + decision logic, visualized: live map, colored route options, Jev's pick highlighted in green, live vs. Maps side by side | Why Jev specifically, not a general LLM: every decision here is a discrete choice among a small, known set of options (this bus vs. this ferry vs. a scooter), re-evaluated as conditions change — not a search/optimization problem. That's Jev's exact shape, and its cost profile ($0.042/MTok input, output free, 70–500ms) is what makes it viable to re-run this on every message instead of caching a single answer. What's real vs. what's simplified - Real: every data source above is live and independently verifiable — open the same public URLs yourself and the numbers will match what the app just used. - Origin is fixed to the CodeRabbit office (201 Spear St) for this demo — there's no GPS/location-sharing available through iMessage, so the destination comes from what you type and the origin is a known fixed point rather than fabricated. - Route paths on the dashboard are straight-line legs, not turn-by-turn routing — there's no free turn-by-turn API in scope for a 3-hour build. - Ferry ETA on the dashboard's trip planner uses the fixed schedule as a same-day approximation, not a live feed (ferries don't have one — they're not late). Running it locally Needs a .env (agent) / .env.local (dashboard) with PROJECT_ID/PROJECT_SECRET (Photon), FIVE_ELEVEN_TOKEN, TYPESAFE_API_KEY, and BROWSERBASE_API_KEY. What's next - Real origin detection (would need a proper app with device location, not just text) - Calendar/Luma integration so the deadline comes from your actual schedule, not something you type each time - Expand beyond SF: the architecture (live feed → geocode → Jev choice) is not SF-specific, just the specific data sources wired up today are License MIT
TypeSafe AIBrowserbasePhoton+1
A code comments classifier which compares Jev with Codex
CodeRabbitTypeSafe AI
jevflowJevflow keeps your writing in the flow
TypeSafe AIThe AI Collective
Explore the project to see what this builder made.
CodeRabbitCognitionTypeSafe AI+1
FirstMinute The first minute decides the stroke. We make it count. A paramedic describes the patient in plain speech. FirstMinute scores the RACE stroke scale item by item with Jev (TypeSafe System One), asks back only what it is unsure about, checks live hospital status with Browserbase + Stagehand, and after the medic confirms opens a CODE STROKE iMessage group with the stroke team via Photon, with an SBAR handoff written on GMI Cloud. Pulsara and JoinTriage put the paper stroke form on a phone. FirstMinute removes the form. Jev scores. Code decides. The medic confirms. Synthetic data only; decision support, not a medical device. Run it Requires Node 22 (nvm use 22) and Python 3.10+. 1. Backend (FastAPI) — :8000 cd backend && python3 -m venv venv && ./venv/bin/pip install -r requirements.txt cp .env.example .env # add TYPESAFE_API_KEY, GMI_, BROWSERBASE_ when you have them ./venv/bin/uvicorn main:app --port 8000 2. Photon bridge (iMessage) — :8787 cd messaging && npm install && cp .env.example .env # SPECTRUM_PROJECT_ID / SPECTRUM_PROJECT_SECRET npm run build && npm start 3. Frontend — :5173 cd frontend && npm install && npm run dev Open (landing) and (product). The regional hospital status board lives at Every integration runs live when its key is set and simulated otherwise. The console shows which mode each one is in. Demo script (3 minutes) Landing (20 s): the problem in numbers. Console → Play "Clear LVO": the transcript streams in, RACE rows fill live, each Jev decision shows its latency, and the total reads 7/9 · LVO suspected. Play "Missing gaze": the gaze row goes dashed and FirstMinute asks "Are the eyes deviated?". Answer it and the row turns confident. Routing: St. Luke's is excluded because its angio suite is occupied (read from the status board), so the route goes to Mercy General. Open /portal, flip Mercy's Neuro IR off, and watch the route change. Confirm & pre-alert: the CODE STROKE group chat appears with the SBAR. With Photon live, it lands on the stroke team's real phones. Real phone: text the project's iMessage number as the medic. The same flow runs over iMessage, and the console mirrors it. Repo Path What backend/ FastAPI: Jev, routing rules, hospital status scraper + mock portal, GMI SBAR, Photon flow, SSE frontend/ React + Vite + TS + Tailwind + shadcn: landing page and live console messaging/ Photon Spectrum bridge (iMessage) video/ Remotion pitch film → video/out/firstminute-pitch.mp4 docs/SPEC.md Product + API contract + design brief Why Jev Jev returns typed answers with calibrated probabilities in about 100–400 ms. Clinical scales are typed forms, so each RACE item maps onto a Jev score question. All items plus "was this mentioned?" checks go in one parallel request. Low confidence triggers a follow-up question instead of a guess. Date math, glucose thresholds and routing stay in deterministic code, where they belong. -- demo link
CodeRabbitTypeSafe AIPhoton+1
