The newest builds with Jev

Newest first, 1–32 of 1072. All 1072 in curated order

• 

  TypeSafe AI

  @typesafeai

  we announced Jev 1.14 on 10.14 at 1:14pm PT 🔥 a new and improved model, along with experimental features for our dreamers: • images • a new box type • longer context surprise, Jev was already able to see you! 👁️ BUT our bar for production-grade intelligence is quite high, so builders beware, these are preview features. enter the ~*~ danger zone ~*~ at your own risk. 🚨

  

  X·Documents and OCR

  Pick

  Jev 1.14: images, a Box type and longer context

  Long context, opt-in

  262k tokens

  Price, per M input tokens

  $0.042

• 

  Malay

  @MalayVasa

  text-to-screenshot just say what you want and the crosshair goes and gets it. built with jev 1.14 from @typesafeai

  

  X·UI

  Text-to-screenshot

• 

  Shann³

  @shannholmberg

  how to add a decision model to your AI workflow 1,000 yes/no decisions can cost around: ~$10 on GPT-6 Astra ~$4 on Claude Opus 5.5 ~$0.04 on JEV use language models for planning, writing and coding, and decision models for decisions a decision model can: > check your agent’s output before it ships > approve a draft or request revisions > route a task to the right agent or tool > classify leads, tickets or comments > score fit, quality or priority > check whether content follows your brand rules > pick an option from a shortlist > decide whether to continue, stop or request a review at a much faster speed as well than any regular LLM here’s how to add one 1. find the decisions in your workflow look for repeated steps that need a choice, classification or score start with one decision you can compare against examples you’ve already reviewed 2. define the question and allowed answers give the model the information and references it needs for a content workflow, that could include your draft, voice DNA file, anti slop rules and approved examples ask it to return a choice such as approve, revise or human review 3. connect the answer to an action your software uses that answer to decide what happens next approved drafts move to your review queue, revision requests return to the writing agent, and uncertain cases go to you 4. test before letting it act compare its answers with your reviewed examples if it returns confidence scores, check whether those scores match how often it gets the decision right start with actions you can easily reverse 5. put simple checks first use code for fixed rules, such as required fields and character limits then use the decision model for checks that need context, before starting more expensive work 6. track quality and cost measure cost per completed task, incorrect decisions and how often another model or a person needs to review use the failures to improve your questions, references and allowed answers

  

  X·Benchmarks and evals

  How to add a decision model to your AI workflow

  1,000 decisions, Jev

  ~$0.04

  1,000 decisions, Claude Opus 5.5

  ~$4

  1,000 decisions, GPT-6 Astra

  ~$10

• Sponsored

  Your card here

  One card in the feed, every twelve, on every page of it. $100 a week, cancel any week.

• 

  Our guide·madewithjev.com

  What is Jev?

  Our explainer: what a System One model is, the three question types, what it costs, what it cannot do, and the builds that show it working.

• 

  Todd Dailey

  @twid

  Tried @typesafeai’s jev 1.14 preview on my doorbell cam’s alert-to-Discord pipeline. My old setup: Gemma 4 26B describes the frame, then DeepSeek V4.1 Flash writes the caption. It caught only 14 of 23 people in recent motion events and missed the mail carrier. Asking jev “is a person in this frame?” across 4 frames of each event got all 23 in a test, with zero false alarms, in about 200 ms. (!) The new jev Box API then crops to the person, so Gemma can describe them far more reliably (21/23, up from 16). Concept to live in less than an hour. This replaces a LOT of AI calls and bounding box tools. The jev call costs about $0.00008 per event. (!) Things are changing so fast. 🚀🚀🚀

  

  X·Robotics and devices

  Pick

  A doorbell camera on Jev 1.14

  People found, Jev

  23 of 23

  People found, old pipeline

  14 of 23

  Answer time

  about 200 ms

  Cost per event

  about $0.00008

• 

  Akshay 🚀

  @akshay_pachaar

  i just put Jev inside an open agent harness. (150x cheaper decision-making than LLM) agents burn a lot of tokens on decisions that are really just picking one option from a short list, like matching a client request to the right GitHub issue. so i built a weekly client follow-up agent that does exactly that. i tested it on 40 requests, and it was as accurate as letting Opus make every match, at 150x lower decision cost. here's the tech stack i used: → TrueForge as the agent harness → Jev for the matching decisions → Daytona as the sandbox for code execution Jev is a decision model from TypeSafe AI. it takes the options from your app and returns a structured choice with a calibrated confidence score, without generating any text. that confidence decides what gets a second look. low-confidence matches go back to Opus for review, and in my test, that review caught 5 wrong matches that would otherwise have gone through. TrueForge is TrueFoundry's harness, and it keeps context small. it loads tool definitions only when needed, writes large tool outputs to files, and lets the agent process data in scripts instead of the conversation. on DevRev's Enterprise Bench, it solved about as many tasks as Claude Managed Agents on roughly a third of the tokens. it also keeps credentials outside the sandbox and holds every write for approval. if you want to try this out, TrueForge is fully open source (MIT-licensed) and runs on your own machine with a single command. TrueForge GitHub: https://github.com/truefoundry/trueforge (don't forget to star 🌟) to help you reproduce my work and understand all the integration details, i wrote a detailed article. it's quoted below.

  

  X·Agents and browsers

  Jev inside an open agent harness

  Requests tested

  40

  Decision cost

  150x lower than Opus

  Wrong matches caught in review

  5

• 

  kyle_AI

  @kylefu07571

  A model release with a literal "danger zone." Jev 1.14 can locate a signature on a scanned form. API: jev-1.14.0 + TypeSafe-Danger-Zone-Images: true Prototype only: a valid box doesn't prove the target exists. typesafe.ai/blog/jev-1-14

  X·Documents and OCR

  Finding a signature on a scanned form

• Our guide·madewithjev.com

  Every Jev guide, in one place

  Every guide on this site in one page, grouped by the question it answers: what Jev is, what a decision costs, how to put it inside an agent, and what it is already being used for across the 855 builds catalogued here.

• 

  Vishal Pandey

  @_vMyth

  Runs agent evals and guardrails as 1 request to a Jev decision model, not an LLM judge. Cheap enough to score every trace. Change 2 defaults: the quick-start sends your traces to a hosted API, and a gate lets calls through if it's down. github.com/openlayer-ai/j…

  

  GitHub·Benchmarks and evals

  jevals

  Stars

  105

  Checks per request

  8

  Cost per trace

  $0.00006

  Answer time

  0.33 s

• 

  Dart Guy

  @odinachidavid

  I built JevChess ♞: realistic 3D chess in your browser vs Jev, @typesafeai's decision model. Beginner, Pro or Legendary. Works on your phone. Free, no sign-up. Play: jevchess.odinachi.space Open source, contributions welcome 👇 github.com/Odinachi/jevch…

  

  Live site·Games and real time

  JevChess

• 

  AJ Asver

  @_aj

  Every day this week, we're launching a new feature @GrepdotAI to help you automate the work that's slowing down your business. 𝗗𝗮𝘆 𝟮: 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻 𝗼𝘂𝘁𝗽𝘂𝘁𝘀 𝗽𝗼𝘄𝗲𝗿𝗲𝗱 𝗯𝘆 𝗝𝗲𝘃 Customers often ask why our agents don't attach confidence levels to their recommendations. My answer has been that LLM confidence levels don't mean much. The model writes a number after the answer, predicting what a confident-sounding score looks like, with a bias toward making humans happy. RLHF pushes models overconfident. Decision models like Jev by @typesafeai change that. You declare the options up front. Jev returns a probability for each one in a single pass, plus a confidence score derived from how concentrated that distribution is. TypeSafe trained it with RLCD, which rewards calibration instead of rater approval, so decisions at 0.9 should be right about 90% of the time. In Grep, you can now build agents that use frontier models for the research and diligence, then hand their findings to Jev to make the final decision against your criteria. You set the threshold: above it the agent acts, below it a human reviews.

  

  X·Agents and browsers

  Decision outputs in Grep

• 

  Ours·shippile.com

  Describe the problem. Jev finds the startup.

• 

  Our guide·madewithjev.com

  What is Jev Engineering?

  Our guide to the term: split an agent into an LLM that writes, Jev that decides and code that acts, with the rules the builds on this site have in common.

• 

  GitHub·SDKs and integrations

  jevgate

  Gate a shell command on a yes/no answer from Jev. Smarter cron.

  GBGordon Brander

  8
• 

  GitHub·Agents and browsers

  brojev

  A Jev browser agent for Claude Code. One Go binary, no Playwright.

  Bbarockok

  4
• 

  GitHub·Context and memory

  pi-skimmer

  Jev keeps the relevant chunks of text and JSON for the Pi coding agent.

  Jjon-devlapaz

  2
• 

  Our guide·madewithjev.com

  Jev use cases

  What people actually use Jev for, from 855 catalogued builds: 100,000 posts scored in 20.4 seconds, 500 emails triaged for 3.5 cents, a flight search in about 7 seconds.

• 

  GitHub·Agents and browsers

  jev-testing: CAPTCHA detection with SeleniumBase

  Jev reads a page’s HTML and names the CAPTCHA on it.

  MMMichael Mintz

  2
• 

  GitHub·Benchmarks and evals

  ProbabilityBench

  Tests Jev and other decision models against exact probabilities.

  ILIshida Lab

  4
• 

  Kyle Wild

  @dorkitude

  Jev isn't tricked by ordering, and the others are. Tested OpenAI Decisions, Clef-flash, Microsoft-Decision-1, and SubQ Snap. dorkitude.com/writing/order-…

  

  Article·Benchmarks and evals

  Jev is not tricked by option order

• Our guide·madewithjev.com

  Sift: sort your Gmail on your own Mac

  Our own: a Mac app that sorts, labels and marks your Gmail with a System One model running on your machine, so nothing is uploaded and nothing is installed in your browser. In build now, and the first 50 on the list pay $5.

• 

  GitHub·Open source

  Jeva

  A System One model built from first principles, with open weights.

  QLQi Li, Xinchao Wang

  76
• 

  Standard Thinking

  @standardthinkin

  Introducing Standard One SH: open-weight decision models. One pass. A probability per option. No text generation. Decision Index 0.3 public index: - 3B 51.5, highest under 4B vs the Oct 12 board; - 8B 57.4 Self-scored with the official kit. Open weights on @huggingface 🧵 1/6

  

  X·Open source

  Standard One SH

  Decision Index 0.3, 3B

  51.5

  Decision Index 0.3, 8B

  57.4

• 

  Eduardo

  @eduardo_builds

  I built Smart Find: Ctrl+F, but for questions. Ask any web page a question and it jumps you to the passages that answer it. Powered by Jev, each search takes under a second and costs less than a cent. Open source Chrome extension github.com/eduardoalba00/…

  

  GitHub·Search

  Smart Find

  Time per search

  0.4 to 0.9 seconds

  Cost per search

  $0.0005 to $0.007

• 

  Our guide·madewithjev.com

  Is Jev open source?

  No: TypeSafe serves Jev from its API and has not published the weights. These are the open models that answer typed questions locally — Julia 1 at 144.3M, Laya at 421M, von under 15 ms.

• 

  Satya Nadella

  @satyanadella

  Introducing Microsoft-Decision-1, our new model for fast decision-making. It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality. We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.

  

  Article·Routing and model choice

  Microsoft-Decision-1

  Benchmarks in the comparison

  36

  Against GPT-6 Sol

  35x quicker

• $0.15Clef-omni, per M input tokens · about 130 ms text-only decision, median · $0.038 clef-flash, per m input tokens

  Article·Open source

  Clef-omni, a faster Clef and a cheaper Clef-flash

  Cloudflare's open-weight decision model now takes audio and video.

  CCloudflare

• 

  doofz

  @reversedoofz

  WAIT. An open-source decision model with 322M parameters that beats Jev on some benchmarks... Runs locally on a PHONE... And now has a FREE API?! Meet THX-01. Weights: huggingface.co/doofz/THX-01 API (Free): api.hal-x.ai/docs/thx-01 pip install thx01

  

  Live site·Open source

  THX-01

  Parameters

  322M

• Our guide·madewithjev.com

  The Jev Build Report

  Our own count: every public Jev build in week one, with the median published cost per decision, the median decision time, and the stars and languages of every repository created since launch. Free to cite, with the rows as JSON.

• 

  Rhythm Garg

  @rhythmrg

  You can now train your own decision model in our platform AC2! Jev-like models, custom fit for your use case :) We implement decision models through a language-model backbone with a small learned output layer called a decision head. The backbone processes the input, question, and answer choices, and the head produces scores which are softmaxed to produce a probability distribution over answer choices. Our software interface makes it easy to add a variable-sized decision head to frontier open-weight models. Choose any open source model, and train it as a decision model using Brier loss or cross-entropy loss. Training updates both the decision head and the language backbone. We tried it on 50k sampled training datapoints from the Civil Comments dataset, starting from Perplexity’s pplx-decider-v1-27b, and F1 for detecting toxic comments increased from 0.482 to 0.677 on 20k sampled eval datapoints. The training job took less than an hour on four B300 GPUs. Reach out to get started with your own classification task: https://docs.appliedcompute.com/platform/training/decisions

  X·Open source

  Train your own decision model on AC2

  F1 before

  0.482

  F1 after

  0.677

• 

  Natzir

  @natzir9

  I tested Google's new decision model for the browser, MediaPipe Decision Maker (Chrome's own Decisions API has no engine yet). On its own it gets 75%: below Gemini Nano (88%), OpenAI's Decisions API (83%) and Jev (92%). Psss... it sends usage data back to Google 👀

  X·Benchmarks and evals

  Google's MediaPipe Decision Maker, tested in the browser

  MediaPipe Decision Maker

  75%

  Gemini Nano

  88%

  OpenAI Decisions API

  83%

  Jev

  92%

• 

  GitHub·Benchmarks and evals

  BeelineBench

  How well do decision models plan across a multi-step problem?

  Kkyle-pena-nlp

  37
• 

  Our guide·madewithjev.com

  How to use Jev

  Your first Jev call, line by line: the state, the questions, the typed answer and what to do with the confidence score. Then the SDKs, the gateways and 58 video walkthroughs.