AI for decisions.

Ultra-fast browser agent

Zurich to London on Google Flights in 7.1 seconds, including model calls, generated text, browser work and loading waits. Swapping to a decision model took median task time from 9.450s to 7.092s and median browser protocol calls from 1,092 to 101.

One natural-language goal, on the real web, at 1x speed. Maker-reported: three repeats of one task on one browser profile.

• 7.09 smedian task, down from 9.45 s
• 101browser calls, down from 1,092

browser-use · ★ 23,396 · MIT · Jev

• browser
• agent

Figures from the project's own README and docs/performance.md. The maintainers note this is three repeats of one task on one browser profile, not a general benchmark.

Source: GitHub → Source: Measurements →

One trade decision per block

Attempts one trade decision per Monad block on the Kuru MON-USDC market, and holds when the model misses the block deadline.

Jarrod Watts · ★ 3,050 · MIT · Jev

• trading
• real-time

Racing game steered by d1

A pixel-art racer where d1 picks left, centre or right on every tick, with a mode that races it against Jev. Liquid AI's own example, in their cookbook repo, so the star count is for the whole repo.

Liquid AI · ★ 2,623 · no licence · d1

• game
• demo

Computer use at $0.0002 a step

OCRs the screen, then classifies the next action. The claimed per-step cost is the maintainer's own figure, not independently measured.

awlevin · ★ 1,251 · MIT · Jev

• computer-use
• cost

Staged code review

A staged review workflow with a local dashboard: each stage is a bounded judgement rather than a written critique.

Dev Agrawal · ★ 686 · MIT · Jev

• code-review
• workflow

Mario, played from emulator state

An agent that plays Super Mario Bros. by classifying the next action from structured emulator state rather than generating a plan.

fhshaik · ★ 456 · no licence · Jev

• game
• control

Session recaps sorted by Solar Decide

A local agent workflow tool written in C. Its recap command sends each session transcript to Solar Decide, which labels every statement as a goal, decision, constraint, done or noise before a chat model writes the summary.

Sidiora Labs · ★ 433 · MIT · Solar Decide

• agent
• tooling

Page clutter removal

A browser extension that decides, element by element, what on a page is clutter, with reusable template rules.

Kitze · ★ 382 · MIT · Jev

• browser
• extension

Camera-input drone in simulation

A drone experiment in MuJoCo with a small judgement model in the control loop, on camera input. The maintainer calls the harder tunnel run a partial result.

Roman Slack · ★ 282 · MIT · Jev

• robotics
• control

fastbrowse: a browser agent where Jev picks each action

An LLM plans, reads and writes; Jev picks each action from the controls indexed on the page, and code stops irreversible clicks without authorization. On 46 tasks run three times each against the hosted Browser Use agent, it passed 99.2% of runs to 96.3% and cost $0.0296 a run to $0.3180, 10.7x less, but was slower: 18.9 s a task to 15.3 s (published campaign release-0.7.1).

agent-labs-dev · ★ 155 · MIT · Jev

• browser
• agent

Live meter over video

Scores every sentence of a video and renders the running result as an overlay.

ChetasLua · ★ 108 · MIT · Jev

• video
• scoring

Paper-trading command center

A paper-trading research app where Jev makes the decisions, wrapped in an animated 3D command center with model pets and a ten-timeframe research panel. Every trade is simulated; there is no real order path.

mars-tw · ★ 63 · MIT · Jev

• trading
• research

Visual inspection workbench with Laya

A local inspection workbench: OpenCV measures the image, hard rules decide anything numeric, and a Laya decision model cross-checks the result. Built for fruit picking, weed and pest monitoring, and steel pipe and textile checks. Version 3.0 also trains your own Laya-format decision models.

uu889 · ★ 58 · MIT · Laya

• inspection
• vision

Full-duplex voice agent

A browser voice agent where the TYGER decision model is the ears: it transcribes you and decides when you've finished, when you've cut in, and when to say "mm-hm", while an LLM writes the replies.

NineNineSix · ★ 53 · Apache-2.0 · TYGER

• voice
• agent

Frame-by-frame video QA

QA for Remotion videos: code measures every frame, the Sage decision model answers yes/no questions about each one, and only the frames it flags go on to the slower critics.

Levanto Labs · ★ 47 · MIT · Sage

• video
• qa

Commit classification

Classifies git diffs and messages into bug fixes, security fixes with CWEs, and change types.

Devansh Batham · ★ 39 · no licence · Jev

• classification
• security

laya-guard: review shell commands before they run

Checks coding-agent tool calls with rules and a local multilingual Laya fine-tune, returning allow, review or block. VENDOR-REPORTED, base to fine-tune: the model alone held 32 then 39 of 43 attacks and allowed 25 then 44 of 50 everyday commands. Six end-to-end verdicts improved and two worsened, missing a preset no-regression criterion. Accuracy on 162 held-out training rows rose from 0.611 to 0.852. The author inspected the benchmark and evaluation sets between training runs, so they are less independent than a fresh test.

scs0209 · ★ 35 · MIT · Laya

• guardrails
• shell
• local

Source: Fine-tune and evaluation →

Vercel form router: send submissions to the right team

Routes lead, contact and issue forms with Jev through Vercel AI Gateway and the AI SDK. It accepts Jev's destination when confidence is at least 95%; otherwise, or if Jev fails, openai/gpt-6-luna-fast evaluates the submission independently. The result shows the destination, deciding model, timings and an email preview, with optional delivery.

vercel-labs · ★ 15 · MIT · Jev

• forms
• routing

Decision models vs prediction markets

A live site where OpenAI Decisions, Jev and Cloudflare's Clef put a probability on live questions after reading recent news, never the odds. Their probabilities are compared against Polymarket and Kalshi prices.

yorkeccak · ★ 12 · MIT · Decisions API, Jev, Clef

• forecasting
• benchmark

Nouli: multi-turn sessions for decision models

Decision models forget everything after each answer; Nouli keeps a session. Type facts as you learn them and start a line with ? to ask a new question; earlier facts and answers stay in the history. A Rust CLI and library that can chain sessions into decision graphs, with Jev through its TypeSafe adapter or other providers.

nouli-ai · ★ 12 · MIT · Jev

• cli
• rust

Guardrails for coding agents' bash commands

A small decision model scores every bash command against your GUARDRAILS.md in about 100 ms (maker's figure), before an opencode, pi or Claude Code agent runs it. Commands scoring above the threshold for data loss, secret leaks or rule breaks are blocked; the README warns it can still let risky ones through.

Berget AI · ★ 11 · MIT · berget/bev (System One-compatible)

• security
• agent

Jev as a second pair of eyes for Claude Code

A Claude Code plugin that asks Jev short typed questions while Claude works: how big is this request, is this command destructive, was the work really done. It suggests an effort level per request, and in enforce mode a confident check can block a "done!" when the work looks incomplete.

Civalski · ★ 4 · MIT · Jev

• coding
• agent

Decision functions inside DuckDB

A native DuckDB extension that adds seven Jev-style SQL functions backed by a local Laya model: DuckDB handles geometry and distance, Laya reads the text fields. It uses no hosted model or API keys.

mraad · ★ 3 · Apache-2.0 · Laya

• sql
• spatial

Nimble and Laya play Slay the Spire

Runs Bespoke Nimble-9B and three Laya checkpoints as players over the same 200 seeds of a headless Slay the Spire simulator, zero-shot and fine-tuned. The results are the authors' own.

MindrLabs · ★ 2 · MIT · Nimble, Laya

• game
• benchmark

Jev DevTools

A drop-in React inspector that turns an app's Jev requests into interactive diagrams of the context, each question and the returned answers. Marked experimental.

diegoag64 · ★ 2 · MIT · Jev

• developer tools
• react

GitHub issues filtered in plain words

A local web page and CLI that reads a repo's GitHub issues and lets you filter them by typing a criterion, such as people blocked from upgrading. Each criterion is asked of a decision model through your TypeSafe key or a gateway; add another to narrow the list.

BerriAI · ★ 2 · MIT · Jev

• tooling
• web

Unorphan: loose files filed into their projects

A local app you point at a messy folder like Downloads: it works out which of your projects each loose file belongs to, reading the README or CLAUDE.md in your code folders, and files it into a matching folder under your chosen output location. Nothing moves until you press Move, and one click puts it all back.

sushrutkhandelwal · ★ 2 · no licence · Jev

• desktop
• files

Jev and Kev compared on the same questions

Benchmark code and a 362-question test set that sends each item to Jev and to Kev 4B, and reports accuracy, calibration, latency and cost.

Opper · ★ 1 · Apache-2.0 · Kev, Jev

• benchmark
• evaluation

Span-01 as a language filter

Tests Span-01 Lite as a second check on whether narration text is in the right language, after a regex pass, against a general chat model. The author notes the 23-case test set is small.

sunnydachs · ★ 1 · MIT · Span-01

• evaluation
• guardrail

On-device email triage

Classifies Apple Mail messages as for you, to review or junk with a Laya model running on your own computer, and shows a report of what it would do. Mail never goes to an external AI service, and it never deletes anything.

patrikcze · ★ 1 · Apache-2.0 · Laya

• email
• local

LinkedIn feed filter

A Chrome extension that hides LinkedIn posts that don't match your stated interests, using Kev 0.6B running in the browser on WebGPU. Post text never leaves the browser.

GuitarWag · ★ 1 · MIT · Kev

• browser
• extension

PathJev: decisions on pathology slides

A decision model for histopathology: given a tissue image, a question and candidate answers chosen at run time, including 'none of these', it returns a probability for each in one forward pass. Built on MedGemma-1.5-4B with LoRA adapters and a decision head, with code to rebuild every number in the authors' preprint.

Cristian Tommasino and Antonio M. Rinaldi · ★ 1 · Apache-2.0 (code); weights for non-commercial research only (MedGemma HAI-DEF terms) · PathJev-P (own, MedGemma-1.5-4B base)

• medicine
• vision

MedJev: zero-shot medical decisions

Runs an open System One model locally on Apple silicon against ten medical benchmarks, from USMLE-style questions to emergency-department admission and 30-day readmission, and compares it with zero-shot LLMs and supervised baselines.

Simonlee711 · ★ 1 · MIT (code); model weights CC BY-NC 4.0 · OpenJev Flash 9B

• medicine
• benchmark
• local

Reasoning effort set per message

A DeepSeek Harness plugin where Jev, via OpenRouter, judges each message as simple, standard, complex or escalated and raises or lowers only the reasoning effort of the model you picked. If Jev fails, it switches itself off.

prgrmrwy · ★ 1 · MIT · Jev

• routing
• coding

Ants that draw your picture

Each ant is a Jev agent that sees the cells around it and its neighbours' headings and decides which way to move and whether to settle. A thousand small decisions turn a random scatter into a word or an uploaded picture; the maker puts a word at about fifteen seconds and seven cents.

scalefreegan · ★ 1 · MIT · Jev

• art
• swarm

X spam blocker

A Chrome extension that hides spam and noise in X posts and replies by combining Jev's probabilities for rules you write in plain language with local signals, and decides locally what to hide. Everything hidden can be restored in place, and if the API fails, posts are shown.

bit-cook · ★ 1 · MIT · Jev

• browser
• extension

UI tests written in plain English

Write test steps as plain-English Gherkin and Jev picks the element, action and check for each one from options Decisium reads off the page; code, not the model, decides whether a step passed. Resolved steps are recorded so CI can replay them with no model calls.

andletenkov · ★ 1 · MIT · Jev

• testing
• playwright

Noullama, a desktop runtime for local decision models

A desktop app that finds and downloads decision-model GGUFs from Hugging Face, runs them on llama.cpp, and serves a local API with choice, yes/no and score questions, plus a playground for trying presets.

parasite6 · ★ 1 · GPL-3.0 · Local GGUF models

• local
• tooling

RealStop: catch work handed back by a coding agent

A Claude Code Stop hook with a local fine-tune of DecisionTune 1.0 that can block a turn ending that hands work back to the user. VENDOR-REPORTED on 864 test turn ends: the moderate setting caught 67.5% (195 of 289) of hand-backs at 15.8% false interventions, against 56.7% and 14.6% for phrase rules. That test split guided development. Both members were correct in only 16% (37 of 229) of synthetic pairs; the model did not beat phrase rules there. Warm model latency was a median 27 ms on an M5 Pro. The hook cannot verify claimed task completion.

decision-tune · ★ 1 · Apache-2.0 · DecisionTune 1.0 (RealStop fine-tune)

• coding
• guardrails
• local

Source: Model and evaluation →

Offline browser agent on Nimble

A macOS app whose browser agent makes every choice, such as which element to click, as one classification by Nimble-9B running locally in Ollama. Low-confidence calls go to the person.

jinyoung · ★ 0 · Apache-2.0 · Nimble

• browser
• agent

Local intent router with a model cascade

Routes support messages through regex, then a small classifier, then decision models, then an LLM as a last resort, all running locally. Laya answers the guardrail and department questions, and Tev1 is the default for the next tier.

Indranil Chandra · ★ 0 · MIT · Laya, Tev1

• routing
• local

Pacman played by Tev1 in Ollama

A one-file browser Pacman where the open directions at each step become the options in a single question to a local Tev1 model through Ollama's decision endpoint.

bidouilles · ★ 0 · no licence · Tev1

• game
• ollama

Intent router on OpenAI's Decisions API

A proof of concept that classifies incoming requests with the Decisions API preview and hands them to worker agents. Its README warns that the preview's request format is not yet published.

anujgupta9860 · ★ 0 · no licence · Decisions API

• routing
• agent

Sentence to typed query plan

A TypeScript library where Jev picks the table, columns, filter, order and limit from what the schema offers, so it can choose a column but never write a query. Drizzle, Prisma or a SQL builder turns the plan into a real, parameterised query.

saembit · ★ 0 · MIT · Jev

• sql
• typescript

Robot boxing: Jev against GPT and Claude

A 3D boxing game where Jev, GPT-4o-mini and Claude Haiku pick each move from the same state and legal actions, and a seeded rules engine resolves the hits. The maker calls the 56-bout results a pilot, not a ranking.

Marcyvan1777 · ★ 0 · no licence · Jev

• game
• comparison

Pet shop catalogue with evidence

Tags each pet product's species, life stage and allergens from the store's own text, asking Jev or Laya one typed question per value: supported, contradicted, unknown or conflicting, with the source sentence attached. Merchants can approve, correct and lock tags, or let a validated policy accept them automatically. A hackathon entry for AIBoomi Startup Weekend Kochi, 23-24 Oct.

Jerom Palimattom Tom (Rexin Dynamics) · ★ 0 · MIT · Jev, Laya

• e-commerce
• shopify

Daily arXiv digest screened by Jev

A GitHub Actions job where Jev scores each new paper from your chosen arXiv categories against each of your research interests, code ranks them and keeps the top few, and only those go to DeepSeek for a summary emailed to you. The default follows humanoid robotics papers.

Monkeypox966 · ★ 0 · MIT · Jev

• research
• email

Politicians by Jev

Ask a question and Jev, via Vercel AI Gateway, gives each of 100 well-known American politicians a yes/no probability; the faces above the threshold float up out of a physics pile.

n8peace · ★ 0 · MIT (code); portraits under their own licences · Jev

• fun
• web

Live interview checklist

A macOS app that transcribes both sides of a call on your Mac with Whisper while Jev ticks off each of your questions once it has been answered, notes which question you just asked, and flags surprising answers for a follow-up. The maker puts Jev's cost at about 1 to 2 US cents for a 45-minute interview.

Darlison Holdings · ★ 0 · MIT · Jev

• meetings
• mcp
• local

Voice tutor grounded in a textbook

Answers a seven-year-old's spoken questions from one scanned Grade 2 textbook chapter. Jev decides whether each new question can be answered from the chapter and, with the optional verifier on, whether the drafted answer's claims are supported by the retrieved passages; common questions are matched to cached answers. On the maker's 14-question test, the decisions API cut average answer time from 4.1 to 1.7 seconds and the cost of each gate call about 25 times, against the chat wrapper.

balajibankapur · ★ 0 · MIT · Jev

• education
• voice

Job description to occupation code

Paste a job ad and watch Jev walk Singapore's 2024 occupation classification level by level, keeping the three best paths at each step, to a five-digit code, drawn as an animated pixel-art crowd. Six requests, about 1.4 seconds, per the README.

blurboy1985 · ★ 0 · no licence · Jev

• classification
• visualisation

Talk to your Mac in one sentence

Speak several instructions in one run-on sentence and Jev picks each action from a menu of skills, and any app from those installed on your Mac, while you are still talking. Anything outside the menu goes to Claude for a proposed shell command, which waits for your approval unless you turn on trust mode.

manikv723-jpg · ★ 0 · no licence · Jev

• voice
• macos

Thunderbird email tagging that learns

A Thunderbird extension that tags your email with decision models served by Ollama's /v1/systemone endpoint, such as Tev1 0.8B, Tev1 4B or Nimble, and keeps learning from the tags you add by hand.

sarath · ★ 0 · MIT · Tev1, Nimble

• email
• local

One MCP server for any System One model

An MCP server that gives an AI assistant yes/no, choice and score tools backed by whichever decision model you configure: any /v1/systemone endpoint such as Jev or Clef, or Laya running on Apple silicon. Its tools never name a model family.

dmonteroh · ★ 0 · MIT · Laya, Jev-Style-0.8B (any /v1/systemone endpoint)

• mcp
• local

A village run on Jev

A pixel-art village in the browser where Jev, via OpenRouter, chooses what each adult does for the next two hours, while fixed rules handle urgent needs, night-time sleep and children. The maker built it to test whether Jev's choices stay sensible and reflect each villager's personality.

Dasge97 · ★ 0 · MIT (code); CC0 1.0 (graphics and sounds) · Jev

• simulation
• game

Build or not: a verdict on your side project

Describe a side project and get BUILD, MAYBE or DON'T BUILD with the reasons: Jev rates pain, reach and feasibility out of five and judges whether the GitHub and Hacker News results it finds already do the job. A run costs well under a cent.

blakestone-x · ★ 0 · MIT · Jev

• cli
• ideas

PII discovery in plain SQL

A DuckDB function that asks Jev typed questions about each database column: is it personal data, which kind, and whether GDPR, CCPA-CPRA, HIPAA, LGPD, PIPEDA or DPDP apply. Whether to keep, mask, hash or drop it is decided by code, not the model, and a failed call sends the column to review. Also runs in the browser.

senthilsweb · ★ 0 · Apache-2.0 · Jev

• data
• duckdb
• compliance

Search evaluation with Jev as judge

Grades search results with Jev on a four-level scale, checked first against Amazon's human-graded shopping queries, and stores runs, results and judgments in DuckDB with the metrics computed in SQL. The author recommends checking it against at least 300 of your own labelled pairs before trusting it on another domain.

rickcrawford · ★ 0 · MIT · Jev

• search
• evaluation

decisions, an R package and web app

A Hugging Face app built on the R package decisions: upload a set of images or texts, ask Jev one question about each, and get every answer with its probabilities plus the R code to repeat the run. Visitors need no key or account; runs are checked against estimated session and daily budgets.

fmegahed · ★ 0 · MIT · Jev

• r
• images

Android notification triage

An Android app that can use Jev to sort notifications into five classes, from action required to hide, alongside local safety rules and corrections it learns from you. It starts in observation mode and never cancels notifications there; Jev is opt-in with your own key.

KoheiTakada · ★ 0 · MIT · Jev

• android
• notifications

West Philippine Sea Watch

A public monitor of the West Philippine Sea with live ship positions, Sentinel-1 radar passes and Global Fishing Watch events. Jev answers four questions about each item from 13 news feeds, and two of them, whether it serves a Philippine reader and whether it carries PRC state framing, decide whether it is shown or held back. Live at wps.gdgt.link.

gianviterbo (Gadget Pilipinas) · ★ 0 · Proprietary (contact Gadget Pilipinas for reuse) · Jev

• news
• maps
• monitoring

Tetris Arena

Jev, SAP-RPT-1, LLMs and a 15-line heuristic play Tetris on the same pieces and candidate moves, with live cost tracking. In the maker's 50-piece race Jev and the heuristic both cleared 19 lines and the others 18, a tie within noise; the difference was speed and cost.

arndth · ★ 0 · MIT · Jev

• game
• comparison

Decision models as tool routers, measured

Calls Jev, OpenAI's Decisions API, Upstage Solar Decide and local Ollama models through one interface and logs version, latency, tokens and cost. On picking the right one of 12 tools for 40 Korean and English requests, the maker measured Jev 1.13 at 40 of 40 and OpenAI Decisions at 0.90, against 0.85 for a generative model choosing directly.

Daewooki · ★ 0 · MIT · Jev, Decisions API, Solar Decide, Nimble

• agent
• benchmark

Terms of service checker

A Chrome extension that splits the terms of service on the page into clauses and has Jev check each for eight kinds of one-sided term, from selling your data to forced arbitration, marking only clauses that go well beyond what major services do and showing each next to the original text. The maker says it is not legal advice.

shohei81 · ★ 0 · MIT · Jev

• browser
• extension
• legal

CI failure triage

Jev reads each failed test and decides the cause: environment or timeout, flaky assertion, genuine regression or API contract mismatch. Code re-runs the build only when every failure would be fixed by re-running (three attempts in all by default), gives flaky tests a low-priority ticket as well, and files tickets for real failures with the test's owner.

tejred213 · ★ 0 · no licence · Jev

• ci
• devops

decide, a CLI and MCP server for Jev

A Go command-line tool and MCP server that gives coding agents and shell scripts Jev's yes/no, choice, score and multi-question calls, with offline request previews and batch runs.

koltyakov · ★ 0 · MIT · Jev

• cli
• mcp

Site search that goes to one page

Visitors type what they need in their own words and Jev, via OpenRouter, picks the one page on the site that fits, choosing only from your list of pages. With no key or a slow reply it falls back to word matching.

Mou1z · ★ 0 · MIT · Jev

• search
• web

Restaurant order matching

Matches messy restaurant orders such as "2 cs portobellos, 5# limes" to exact catalogue items with Jev and flags uncertain lines for a person to check. The maker reports 96% exact matches on held-out test orders.

prefill-vanishing-point · ★ 0 · no licence · Jev

• food
• ordering

Mail server filter that files into folders

Sorts incoming mail for the maddy mail server into IMAP folders: Jev answers questions such as whether a message is spam or phishing, and rules in a config file turn the answers into a folder. It also learns from where you have filed mail before.

lesderid · ★ 0 · MIT · Jev

• email
• self-hosted

Which fixes clear most Intune noncompliance

Reads Intune compliance data from Microsoft Graph, groups failing devices by the setting that fails, and ranks fixes by how many devices each makes fully compliant. For custom settings its rules don't cover, Jev can optionally pick the remediation path. You can try a live demo with a sample tenant.

dallascrilley · ★ 0 · MIT · Jev

• it admin
• microsoft

Classified ads filter

A browser extension that asks Jev about every ad on the Bazoš classifieds site against criteria you write in plain language, and collapses the ones that don't match. Other marketplaces and auction sites are planned.

Aladincz · ★ 0 · MIT · Jev

• browser
• extension
• shopping

Ask Jev to flip a coin

A small command-line tool that asks Jev to flip a coin N times and reports the share of heads.

royvandewater · ★ 0 · no licence · Jev

• test
• cli

Hacker News curator on Jev

Polls new Hacker News stories every two minutes, runs each unprocessed one through decision trees of Jev questions you define, and sends the stories that match any tree to a Telegram chat or channel.

uint4096 · ★ 0 · GPL-3.0 · Jev

• feed
• telegram

Agent questions answered by Jev

An opencode plugin for autonomous runs: when the agent stops to ask the human a question, Jev (or an LLM, if you set one; the default tries Jev first) picks from the offered options. Below a configurable confidence (0.6 by default) it gathers context in a side session and decides again; below 0.35 the human answers after all.

jflowers · ★ 0 · Apache-2.0 · Jev

• agent
• coding

Jev picks which tools an agent loads

A Pi extension that keeps most tool and skill descriptions out of the first request and loads them on demand. In its optional Jev mode, Jev decides before each prompt which ones the request needs.

dantetekanem · ★ 0 · MIT · Jev

• agent
• cost

What changes Jev's election forecasts

An open research essay on three competitive 2026 US Senate races: compare stored Jev forecasts across different sets of evidence and different orderings of candidates and sources, with the exact requests and saved responses to inspect. The author calls it an experiment, not a calibrated forecast.

prashaantr · ★ 0 · MIT · Jev

• research
• forecasting

A decision queue in front of agent tools

A Claude Code plugin that checks an agent's tool calls before they run, using hosted Jev when you configure a key and offline rules otherwise. In enforce mode it refuses a call with a reason; advisory mode only reports the verdict.

iamvazghen · ★ 0 · MIT · Jev

• agent
• guardrails

Jev for marketing ops

A free guide, a Claude skill and four editable recipes for typed marketing-ops decisions: route this lead, tag this asset, is this reply interested. Jev makes the call; an LLM still writes the copy.

brent-phillips · ★ 0 · MIT · Jev

• guide
• marketing

Fold low-value posts on X

A Chrome extension: describe what you don't want to see in plain words, and eligible posts on your X timeline get a probability per rule. By default, anything over your threshold folds into a one-line bar you can open again.

Nixz0824 · ★ 0 · MIT · Jev, Clef-omni

• extension
• feed

Support tickets routed by Laya

A small ticket router: with the Laya backend selected, each support ticket goes to Laya, the open Jev-style model, with three questions (which team, how urgent, is it spam). The default backend is a keyword stub, with a slot left for Jev.

ikeremerdem · ★ 0 · no licence · Laya

• support
• local

Stock signals with sources, from Parallel

A small demo with a live site: type a US or Indian stock and two Parallel Decisions calls, through Parallel's free MCP endpoint, assess its technicals and trading activity from the live web and return probabilities and sources.

hckmstrrahul · ★ 0 · no licence · Parallel Decisions API

• web
• trading

Decision models forecasting Polymarket

Keeps the 50 busiest Polymarket questions forecast by several models, including Jev, Perplexity's Decider and an OpenAI model, all given filtered web search results but never the price. When markets resolve, each is scored on a leaderboard by Brier score, log loss and accuracy.

aaron-zhlg · ★ 0 · no licence · Jev, Decider

• forecasting
• benchmark

Jev Workspace: a mission, some links, a verdict on each

Give Jev a mission and some links: it gathers every item, judges each one live with counters and a running API bill on screen, and ends with a results page you can sort, spot-check and export. Runs on your own machine with your own keys.

freakngenius · ★ 0 · MIT · Jev

• local
• research

Ask questions about any document, locally

A script that asks true/false and multiple-choice questions about an image, PDF, Word file, slide deck, spreadsheet or text, using a decision model on local Ollama. Validated with d1:3b and Clef-Flash; d1:3b is the default.

nikspence · ★ 0 · MIT · d1

• local
• documents

A 3D disk map that asks Jev what's safe to clear

A Windows disk-space map that draws your drive as a 3D city and asks Jev which folders look safe to delete; those get a neon outline and land in a Reclaimable list, biggest first.

NoxLoveYa · ★ 0 · GPL-3.0-or-later · Jev

• desktop
• windows

A library's guide: Jev and Claude sort your email

A step-by-step guide for people who don't write code: set up Jev with Claude Code and build a read-only assistant that ranks the last two weeks of Gmail into piles like Reply needed, Waiting on them and Possible phishing.

byui-library · ★ 0 · MIT · Jev

• guide
• email

A moderation queue that learns a new harm in minutes

Simulates a moderation queue hit by a wave of privacy-invading posts the existing router did not prioritise: Claude reads 20 of those posts and 20 ordinary ones and drafts one yes/no question, and a fine-tuned version of the open decision model Laya asks it of every new post so the matches jump to the urgent queue.

Enayat-Hassani · ★ 0 · MIT · Laya

• moderation
• simulation

Drex inside DuckDB and other SQL systems

Nace's DuckDB extension asks typed questions about rows from SQL and returns probabilities as column values, for routing support tickets, classifying documents or scoring data you already query. Nace also publishes MIT-licensed connectors for Snowflake, PostgreSQL, ClickHouse and Apache Spark, including Databricks SQL. Text and JSON calls default to drex-v2.0; images need an image-capable model such as drex-max.

Nace AI · ★ 0 · MIT · Drex 2.0, Drex Max

• sql
• database

Source: Snowflake → Source: PostgreSQL → Source: ClickHouse → Source: Apache Spark and Databricks SQL →

Cameo: put yourself in any video

A ComfyUI workflow that adds you to an existing video. Liquid's d1-2B judges every shot (framing, whether there's room for one more person, where everyone stands) and casts the best ones, then image and video models put you in beside the people already there.

kristopolous · ★ 0 · MIT · d1

• video
• comfyui

Kariyer decision bench: Turkish job ads

Written at Kariyer.net R&D to pull seniority, department and work type out of job ads. On 600 real ads with 7 questions each (4,200 decisions), Jev 1.13.0 scored 71.5% against 64.6% for the open tau-4b and 65.7% for a prompted 4B LLM. tau-4b was better calibrated (ECE 0.093 against 0.156), and it scored 95.7% on its own training data, which is why the author warns against benchmarking a model on the set it shipped with.

kubrakrcn · ★ 0 · Apache-2.0 · Jev, tau-4b

• benchmark
• turkish

Narrative audit: earnings calls against the numbers

A harness that checks claims from earnings-call transcripts and footnotes against tables in DuckDB, on 64 synthetic cases. Perplexity's pplx-decider-flash-v1.2 scored 85.94% at about 1.4 s a case; a rule baseline scored 68.75% but caught only 2 of 9 Q&A deflections, which the decider caught 9 of 9. A chat model led on accuracy at 90.62%, with confidences stacked at 0.99 to 1.00. OpenRouter's chat endpoint rejected the decider with HTTP 400, so it runs through the separate /api/alpha/decisions endpoint.

adityavsb · ★ 0 · MIT · Decider

• benchmark
• finance

layagrep: train Laya to search code

jevgrep finds code by asking Jev thousands of yes/no questions. layagrep records those questions on SWE-bench tasks and fine-tunes the open Laya to answer them locally, with no API key and no code leaving the machine. A smoke run on 400 held-out questions lifted file-navigation AUC from 0.79 to 0.94 (Jev 0.97), but declaration relevance stayed at 0.58 (Jev 1.00).

gak4u · ★ 0 · Apache-2.0 · Laya, Jev

• code-search
• fine-tuning

decision-cli: local LLMs as decision models on a Mac

Reads the probabilities of the answer tokens from one forward pass of an ordinary local LLM, with no fine-tuning, and serves them through a CLI, batch mode and a Jev-like API on Apple Silicon. On the 231 public JevBench questions, gemma-4-26b-a4b scored 84.8% at about 170 ms a question and ling-3.0-tiny 69.7% at about 45 ms; most of the misses are on the hard set.

cafe3310 · ★ 0 · Apache-2.0 · Local MLX models

• cli
• mlx
• local

desktop-agent: Windows apps run in the background

Lets any agent operate Windows desktop apps without taking over the screen. A local 0.33B decision model, S1-Fast, reads the app's accessibility element table and does the sure steps. Uncertain steps go back to the agent or to a fine-tuned OneJev-4B, and irreversible ones stop until a person confirms them. It reports 68.4% macro step success on five public held-out test sets and 40 of 40 on its own development tasks.

elidot007 · ★ 0 · Apache-2.0 · S1-Fast (own 0.33B), OneJev-4B

• desktop
• agent
• windows

Decision model kernels: a faster llama.cpp on one GPU

A lab notebook for speeding up one decision model, H2O Lightning 4B, served through llama.cpp on an RTX 3060 Ti. Each request takes 2.13 to 2.45 times its roofline floor. The first measured change, a llama.cpp pull request, cut latency by 1.94% with bit-for-bit identical answers; the bigger gains in its list of 15 targets are labelled predictions.

WyrmKeep · ★ 0 · MIT · H2O-Lightning-4B

• inference
• llama.cpp
• cuda

JEV Damocles: when a group-chat bot should speak

An AstrBot plugin that decides whether a bot in a group chat should reply. It merges bursts of messages, separates conversation threads, then asks Jev four questions, batched into one request when the backend supports it (was the bot addressed, does it follow, should it reply, how urgent). For messages without a direct mention, quote-reply or poke, it uses a high and a low reply threshold alongside other checks, and scores in between can be reassessed later; those direct interactions can skip the gate. The README suggests a 3 to 7 day dry run first.

ch7flyer · ★ 0 · MIT · Jev

• chat
• bot
• astrbot

jev-router: Jev sets Claude Code's reasoning effort

A Claude Code plugin that asks Jev one choice question per message, low, medium or high effort, and applies the answer when Jev is at least 60% sure. It changes effort, never the model, so the prompt cache survives. Subagents are never routed.

pyxl-dev · ★ 0 · MIT · Jev

• claude-code
• plugin
• routing

JevRouter: Jev picks the next step, a policy decides

An agent runtime where an LLM reads the task, one Jev call answers four typed questions (next action, risk, whether to confirm, whether to reason further) and a local policy engine decides what may run. On 53 versioned test cases it hit the expected action 92.5% of the time against 96.2% for an LLM baseline, at about 1.0 s against 4.0 s, and asked for confirmation on 16 of the 17 cases that needed it.

HangChi · ★ 0 · MIT · Jev

• agent
• runtime
• policy

skill-tester: grading agent skills with Jev

An eval harness for agent skills: headless agent runs, code checks, Jev judge packs and blind human review; the generic pack asks one yes/no question per skill rule. Graded with the writing pack, the reference skill's v2 run matched its original benchmark's report within 2 points on every layer and in total.

milesroxas · ★ 0 · MIT · Jev

• evals
• agent-skills

dsh-cu-d1: Liquid's d1-2B drives a browser and a Mac

Uses Liquid's open d1-2B as a local System 1 for DeepSeek Harness Browser Use and macOS Computer Use, with approvals and routing. Downscaling wide screenshots before the model reads them cut one decision from 879 ms to 310 ms on a 2508-pixel window, and six consecutive trials all chose a click action. d1-2B itself is under the LFM Open License, not MIT.

Alyosha28 · ★ 0 · MIT · d1

• computer-use
• browser
• local

Agastya: walking a document's outline to find answers

Retrieval that walks a document's table of contents, asking Jev one yes/no question per section, then ranks the sections it kept with EmbeddingGemma. On all 6,005 test queries of the public SearchTome release it returned 89.1% of gold sections at 3.6 sections per query, against 84.5% at 3 for EmbeddingGemma alone; its top-1 and top-3 recall equal the embedding model's. Jev alone, ranking flat, scored 54.2 top-1. It needs no training and runs on one 8GB consumer GPU, and failed upgrades are published too.

cars3 · ★ 0 · MIT · Jev

• retrieval
• search

Jev picks the move for a robot arm

A course project where Jev chooses the transfer strategy for a CRANE+ arm in a Gazebo simulation, MoveIt 2 plans the path and ROS 2 controllers run it. In three episodes on authenticated Jev decisions with no fallback, Jev picked the home transfer at 0.94 to 0.96 confidence and all three placed the cube, 2.70 to 7.48 mm off target. These are scripted-teacher episodes; the README's separate learned-policy (ACT) tests are not reported as grasp success.

uhiron55 · ★ 0 · Apache-2.0 · Jev

• robotics
• ros2

jev-droid: Android automation with two models

Drives an Android emulator from plain language: DeepSeek V4.1 Flash decides the next step, and Jev triages each screen (loading, error, permission prompt) and guards actions before they run. The three-step demo in the README, Settings to Network to Wi-Fi, cost $0.00019 and took 21 seconds; every step saves its screen, decision, tokens and cost.

frederico-kluser · ★ 0 · MIT · Jev

• android
• agent

topic-gate: reset the chat when the topic changes

Asks Jev one question per message, 300 to 600 input tokens, to tell whether the conversation is on the same topic, a subtopic or a new one, and recommends a session reset only when a new topic wins clearly (p of at least 0.65 and 0.25 ahead), so you stop paying to resend a dead transcript. Checked against live Jev on related, unrelated and short messages.

tauseefau · ★ 0 · MIT · Jev

• context
• agent

Laya Notes: notes that tag themselves

A desktop notes app for Mac, Windows and Linux that keeps plain Markdown files and runs the open Laya model on your own computer. Each tag is a yes/no question, like "Is this note about a trip?"; Laya answers all of them for a note in one pass and keeps the tags it is confident about. Notes stay on the computer; the only network request is a one-time download of about 1.6 GB of model files.

itsdula · ★ 0 · MIT · Laya

• notes
• desktop
• local

pi-omarchy-cu: Linux desktop control for the Pi agent

Lets the Pi coding agent drive real Linux desktop apps on Omarchy (Hyprland Wayland) by reading the accessibility tree and asking Jev for the target element and the operation. It offers 11 Wayland-safe element operations. Jev-driven actions abstain below 0.55 confidence and need confirmation below 0.70, or 0.90 for destructive ones; direct operations on a known element run without Jev.

Paul-Yuchao-Dong · ★ 0 · MIT · Jev

• computer-use
• linux
• agent

Decision Wall: 200 questions about one text

Asks Jev 200 yes/no questions about one text in a single call and shows the answers as a heatmap. The keyless hosted demo replays recorded answers. VENDOR-REPORTED: about 185 ms for one question, 200 ms for 50, and 150 to 300 ms for 200; seven parallel calls returned 1,400 answers in 282 ms, against 1,092 ms back to back. The author measured Jev 1.14 from a US home connection and has not measured calibration.

charles-forsyth · ★ 0 · MIT · Jev

• classification
• heatmap

Jev-Router: choose a model after applying hard constraints

An OpenAI-compatible router that filters models by hard constraints before Jev judges which one fits. VENDOR-REPORTED, on its own 30 prompts: tier accuracy was 100% against 53.3% for a heuristic, task-type accuracy 83.3% against 46.7%, and hard prompts sent to a weak model 0 against 14. Estimated savings against always using the strongest model, from token counts and configured prices rather than running the chosen models, were 35.6% against 68.7%; the heuristic's estimate was higher because it under-routed. Decision latency was 295 ms at p50 and 409 ms at p95.

AIAnytime · ★ 0 · MIT · Jev

• routing
• agent

Laya and ZCode: local checks and context selection

Runs multilingual Laya through a local Go/ONNX service, with a ZCode plugin for risk checks, context selection and 13 MCP tools. VENDOR-REPORTED on an RTX 3060, three runs per variant: total input fell from 359,085 to 239,544 tokens (33.3%) and requests from 16 to 9, but non-cached input rose 21.8%. Laya ranking alone cut total input 9.3% and non-cached input about 2.8%, within the observed range; the author has not established a fresh-token or cost saving. The /decide endpoint took about 26 ms at p50.

Ydjin1984 · ★ 0 · MIT · Laya

• coding
• context
• local

Source: Benchmark and caveats →

PR wall: separate judgments about each pull request

Puts open pull requests on a wall and asks Jev eight typed questions about each diff and its tests, using quarkusio/quarkus by default. It keeps the answers separate and never combines them into a score. Right/Wrong feedback records corrections and groups accuracy by confidence as you label answers; no accuracy figures are published yet. Its questions and Quarkus context are adapted from brunobat/quarkus-pr-wall.

House-elves · ★ 0 · Apache-2.0 · Jev

• code-review
• calibration

openclaw-d1-local: local decisions for OpenClaw

Supplies OpenClaw with local typed decisions from LiquidAI/d1-Omni-2B-MLX-8bit on Apple Silicon. It has a native decision provider and a bridge for OpenClaw's TypeSafe integration. The repository name contains Kev, but the runner loads d1-Omni. VENDOR-REPORTED on an M4 Mac mini: about 200 ms per warm batch and about 3 GB of resident RAM.

heff0 · ★ 0 · MIT · d1

• agent
• local
• apple-silicon

inspect-drex: score agent outputs against a rubric

A scorer for the UK AI Security Institute's Inspect framework that asks Drex whether an output meets your criteria and keeps the probabilities, so you can change pass thresholds after the run. It defaults to drex-max, whose target changes with flagship releases; pin a model for repeatable runs. Drex Max accepts images, while drex-v2.0 accepts text and JSON.

nace-ai · ★ 0 · MIT · Drex 2.0, Drex Max

• evaluation
• agent

OwnYourTimeline: filter the X Home feed

Filters the For you and Following feeds in Chrome or Edge using a plain-language instruction and Jev. It sends one bulk TypeSafe request per timeline response, splitting to stay within input budgets, and removes posts scoring at least 0.90 before X renders them. Errors and timeouts leave posts visible; it checks at most 80 posts per response. The built extension has Chromium tests with X and TypeSafe responses stubbed. No filtering-accuracy figures are published.

Raghav Sharma · ★ 0 · MIT · Jev

• feed-filtering
• browser-extension

Jev router for GitHub Copilot

Jev sizes a Copilot message as tiny, everyday, large or hardest and sends it to a helper agent pinned to a model. Defaults are Haiku 5.5, Sonnet 5.5 and Opus 5.5, with the hardest helper configured to request high effort. Recorded helper runs used medium effort. The author records live runs of the hook in Copilot CLI 1.0.105 and VS Code 1.144, plus the CLI wrapper. The MCP fallback is tested offline only. Its 54 offline tests passed when checked on 03 Nov 2026; it publishes no savings benchmark.

Sascha Corti (TechPreacher) · ★ 0 · MIT · Jev

• model-routing
• coding-assistant

Source: Live CLI wrapper run → Source: Live VS Code run →