620 usecases built now with Jev

Mario Jankovic

@mariojankovic

Jev waging war against AI slop on youtube. Love it.

notifyShivam

@notifyShivam

introducing https://t.co/VzfUI1571y 📝 report card is the official grade slip of Doomscroll District School, Fall 2026 semester. teacher reads your public posts and grades six subjects, from A+ (gold star sticker) to F (your parents will be notified). demo 👇

Jobin Ayathil

@AyathilJobin

I observed that some LLM calls in many repos could run 99% cheaper & up to 13× faster. I scanned 1,000+ repos & found so many calls that are really just decisions: route this ticket, flag this spam, score this priority, blah blah.. but all this started with a question from a

Rajdeepsinh Jadeja

@TheRealRajdeep

Built a demonstration of Jev playing 2048. Note: It might not always win. :)

Subhojit Karmakar

@essjaykay755

what if a sentence could change the physics of a room? I built JEV FLUX: type a thought > Jev reads the signal > particles turn it into motion. fracture. drift. implosion. pulse. vortex. electric. Every phrase becomes a different storm

Dan Semenescu

@DansiDanutz

↗

Paste an article or post link. Fake / Real extracts its claims, finds outside evidence, and has Jev judge whether the evidence supports or contradicts each one.

A worked guide to Jev's Score primitive: writing a request, defining rubric levels, reading recorded probabilities and the weighted-score math.

leighefford

github.com

↗

Paste or record a speech and 200 Jev-simulated people react line by line: jokes scored on laughs, sincere lines on warmth. A 13-line speech cost $0.00097.

shima78

github.com

↗

Watch Jev play chess against itself, or play against it. Jev picks every move; FastAPI and python-chess run the board.

Brian Luby

github.com

↗

A fast scanner that reviews code for correctness, security, reliability, compatibility and test gaps, with actionable feedback. Supports the Jev API and local models.

Jev reads a search into intent, make and colour, then scores every car 0–100% on how well it fits.

げま｜個人開発

@gemama0

Jevでノートの自動タグ付けシステムを作った🎉 Obsidian使っている人はぜひ👇

Gregor Zunic

@gregpr07

Breaking: Browser Use + Jev = Ultrafast ⚡ Findings flights took 7s and cost only $0.0039 🤯 > new action space every step > DOM state space > small LLM fallback to type (this video is at 1x speed btw) Built a tiny open source browser agent. try it below ↓

shiftynick

github.com

↗

An agent-ergonomic CLI for fast calibrated judgments from the shell: pick, rate, check, rank, triage and guard, plus CI and agent hooks.

Adnan

@_itzadnan_

Another Jev use case - Dreaming! I tested two different Dreaming pipelines: A purely LLM-based pipeline using Gemini. A hybrid pipeline using Jev for classifying and maintaining knowledge graph. Check it Out - https://t.co/24x0rqZGLy Repo -

Arto Bendiken

@bendiken

The latest @ASIMOV_Platform release lands a built-in `--jev=NOUL` output filter, enabling agentic harnesses such as Hermes to offload simple natural language postprocessing decisions to Jev, a System One model Look ma, here just casually turning my LinkedIn network into JSON-LD

Reinhard Zach

@mrza_ch

I put Jev behind the wheel. A small vision model in your browser describes the road. Jev, TypeSafe’s fast, cheap classifier, decides what to do. Does it stop for a child? A dog? A teddy bear? Drop them on the road and find out: https://t.co/ccWsmPEZaF

Błażej Kustra

@blazejkustra_

Best CI use case for @typesafeai's Jev: Enforce the rules a linter can't every repo has rules that only live in review comments and onboarding docs softlint puts them in a json file and checks every pull request against them, flagging the exact line any language, ~$0.001 per

A video letting Astra plan and Jev act inside Minecraft, with an outcome the creator didn't expect.

typakon4

github.com

↗

An open-source decision layer that recommends a capability from a host-approved set and records the outcome for replay. The host keeps control of permissions.

Avinash Jetwani

@jetwaniavinash

↗

After every Claude Code message, Jev decides in ~0.3 s whether it holds a decision, rule or bug worth keeping, and jevmem saves it as one line in JEVMEM.md.

Nelson P.Klark

@nelsonpklark

Inspired by @heystefan_: name a dish or a cocktail, and its ingredients rise out of a pile of stickers. ⚡ Jev judges every search in half a second 🎨 ~1,000 illustrations by FLUX.1 [dev], run locally through ComfyUI 🧠 Claude Opus 5.5 built it all and redrew the illustrations

Semantic-aware linting with System One models: rules you can state in a sentence, checked against your code by Jev.

Sends a detected bot's last 48 request paths to Jev, which picks what it's after (prices, articles…) and how it crawls (pagination, IDs…), or unknown.

Maitree Mervana Parekh

@maitreemervana

built a virtual closet & outfit generator from raw closet videos. classification + semantic search thanks to jev 🥰. clueless closet dreams finally coming to life

Kyle

@kylemclaren

This is one of the best use cases I have found for @typesafeai Jev so far, instantly find anything in a PDF using natural language. Try it out: https://t.co/mByvIRcoQp

Michele Lacorte

github.com

↗

Replays real compressor telemetry through an emulated Modbus device, spots anomalies in plain code, then asks Jev which fault from the manual explains them.

An AI Magic 8 Ball. Ask the ball a question and Jev tilts the odds of the answer.

tomerglick57

github.com

↗

A self-hosted proxy that trains a local model on Jev's answers. It served 72% of Banking77 locally at 15 ms, with a 2% audit and a bound on disagreement.

Andrey Popov

github.com

↗

Write Playwright steps like "add the most expensive item to the cart". Jev finds the right buttons and fields, fills forms and checks the result.

Alex Forman

@alex_forman1

↗

Typo tolerance, typeahead, barcodes and facet counts in plain Postgres SQL, plus an optional Jev step that asks one question per top-10 result.

Harsha Varma

@harsha_varma02

↗

A speedcubing agent built on Jev and Laya ModernBERT-421M, with real-time 3D state, temporal memory and calibrated move probabilities instead of a solver.

Captain-Sangam

github.com

↗

Keeps your desktop visible and your Mac awake while a tiny fox blocks keyboard, mouse and trackpad input. Jev drives the character's reactions.

Zahle Khan

@zahlekhan

Introducing jev board, short for jevin keyboard. Fast, reliable models unlock much subtler experiences for building ambient intelligence into interfaces. A small exploration at the edges of GenUI. With done @typesafeai and @CompleteSkeptic

Combines rubric science and LLM-as-a-judge research to grade outputs with AI judges: LLMs, decision models like Jev, or both.

Johnny Makhoul

@johnnymakhl

Stop letting LLMs or Jev write raw SQL against production data or even evaluate rows. I built a CLI that routes questions through a semantic layer (Cube/dbt) with confidence checks so it only runs safe, verified queries. Quick demo running on: https://t.co/ACoN1ld7MM

An experiment replaying market history to test Jev on sequential investment decisions.

Dhanush N

@Dhanush_Nehru

npm install is the scariest command in your terminal. One typo → lookalike package → malicious postinstall → secrets gone. jev-sec-audit flags it in milliseconds using Jev, a System 1 model built for fast decisions, not chat. One step in GitHub Actions. Open source.

Jaz

github.com

↗

A Claude Code and MCP hook where Jev answers seven yes/no risk questions per tool call to allow, ask or deny. Usage and benchmark numbers are in the repo.

Mu99Ti

github.com

↗

Jev triages streaming logs into page, digest or resolve, cutting alert noise and paging humans only for high-confidence incidents. About $1–3 for 1M events a month.