directorysource-backed
Jev Use Case Tracker
A browsable collection of Jev use cases, repositories, opinions and updates, grouped for exploration.
THE JEV ECOSYSTEM, INDEXED
What shipped.
What it proves.
Projects, demos, integrations and claims around Jev. Every entry keeps its source and evidence label attached.
395entries indexed
106author demos
Latest field notes
replicasource-backed
Qwen3.5 0.8B decision model: a local Jev alternative
An independent 0.8B Qwen3.5 model for typed decisions, published with weights and a comparison against Jev.
integrationsource-backed
cmd-mod-jev-nudge: decide when an agent should continue
A Command Code mod asks Jev whether a gentle nudge would help an agent continue useful work within the user's existing request.
demosource-backed
jev-voice-games: voice-driven Godot mini-games
Two voice-controlled Godot games use local speech recognition for clear commands and Jev with game state for ambiguous ones.
productsource-backed
ASO Workbench: Jev-assisted keyword analysis
An open-source Mac tool for App Store Optimization with keyword analysis and listing workflows that the author connects to Jev.
productsource-backed
Jev Voice: typed decisions for Mac voice control
A macOS menu-bar voice controller with on-device speech recognition and Jev decisions for commands and UI actions.
productsource-backed
jev-chat-jarvis-mac: WeChat reply assistant
A macOS overlay that reads WeChat on screen, runs an optional TypeSafe Jev or local decision model, and prepares reply suggestions for manual sending.
productsource-backed
jev-chat-jarvis: Android reply assistant
An Android chat assistant that uses Jev or a compatible decision endpoint to judge message intent and risk, then offers drafts from a separate generative model.
integrationsource-backed
jev-linkedin-slop-filter: label LinkedIn posts
A Chrome extension that applies BAIT, CORP and BRAG labels to LinkedIn posts using Jev, with a local server for the API key and heuristics to reduce calls.
integrationsource-backed
gmail-jev: label Gmail threads with Jev
Classifies Gmail threads into workflow labels with Jev and can optionally remove them from the inbox. The tool does not send mail.
demosource-backed
jevdemo: Choice, Score and Noul in Python
A small Python and HTTP example of support-request routing with Choice, frustration scoring with Score, and urgency evaluation with Noul.
integrationsource-backed
ZeroNSFWBot: optional Jev text moderation for Telegram
A Telegram moderation bot that uses Jev for optional text, bio, advertising and language judgments. Image moderation runs through a separate local detector.
integrationsource-backed
Jev decisions in BigQuery through Cloud Run
A Cloud Run remote function lets BigQuery call Jev to classify support tickets and expose the resulting judgments to SQL queries.
demosource-backed
jev-ui-map: typed actions for browser tasks
Maps visible UI states to bounded action options so Jev can select the next browser step. The repository includes a food-ordering demonstration with action limits in code.
benchmarksource-backed
rerank-bench-jev: Jev versus Qwen3 Reranker
An inspectable comparison of Jev Noul and Qwen3-Reranker-0.6B on retrieval ranking tasks, with the harness and raw model responses published.
integrationsource-backed
qc-use: Jev-assisted UI tests from plain-language steps
Turns plain-language critical-path tests into bounded UI actions chosen by Jev. The runner checks a fresh screenshot after each action and records a step-by-step result.
integrationsource-backed
intent-classification: a scope guard in front of agent workflows
A modular gateway: define each agent's scope and confidence threshold, plug it in before the workflow — one reusable guard, many scopes.
integrationsource-backed
jgrep: ask questions of logs, files and pages from the shell
A Rust CLI that pipes logs, files or any text through Jev: natural-language question in, structured semantic decision out.
demosource-backed
jev_robot: a moving-target pick-and-place in MuJoCo
Jev-inspired sim with a local 2B model driving a PiPER robot in MuJoCo: the cube is relocated three times per run and the robot detects, interrupts and recovers.
integrationsource-backed
laravel-jev: Jev::is / Jev::choose inside Laravel
Runtime `if (Jev::is($body, 'spam'))` and `Jev::choose($msg, [...])` for Laravel, with `Jev::fake()` for offline tests and `Rule::jev()` for form validation.
replicasource-backed
Multimodal Jev prototype: option probabilities plus bounding boxes
Answers image questions with option probabilities and bounding boxes; trained on CUB-200-2011 with a Qwen2.5-VL backbone.
demosource-backed
Polymarket 5-minute BTC Up/Down agent on Jev
A Polymarket trading agent with a TUI where Jev is the decision layer for the 5-minute BTC Up/Down market.
replicasource-backed
openjev.cpp: a llama.cpp fork for Jev-like inference
A llama.cpp fork serving Jev-like models as an inference server.
demosource-backed
Jev Desktop: open-source computer use, ~10x faster than native
Desktop computer-use agent released as open source and slated to become part of the author's internal verification workflow.
integrationsource-backed
pi-jev-router: automatic model routing for Pi via Vercel AI Gateway
Open-source Pi extension that lets Jev route each turn to a model through Vercel AI Gateway; the author pairs it with Astra adaptive thinking.
demosource-backed
MineLog: Astra plans, Jev decides, one Minecraft body
The harness behind minelog.xyz: GPT-6 Astra plans, Jev makes the moment-to-moment decisions for a single Minecraft agent.
integrationsource-backed
switchboard: a cache-aware decision router for Claude Code and Codex
Model-agnostic router that takes prompt cache into account when Jev picks the model per turn; other System One models planned.
demosource-backed
jev-rubiks: the code solves, Jev coaches your hand solve
An interactive 3D Rubik's cube: turn it by hand, Jev watches each move, stays quiet while you progress, warns on a break and steps in with the next algorithm.
demosource-backed
jevyoumean: semantic 'Did you mean?' for any CLI
Wraps commands and uses Jev to match mistyped subcommands by intent, not edit distance: `git record` → `git commit`, `npm add` → `npm install`.
replicasource-backed
LogJev: Jev-style choices from any model's first-token logprobs
Adapts first-token logprobs from any OpenAI-compatible endpoint (cloud or local) into bounded Jev-style choices and scores; text, image or audio in when the backend exposes logprobs. Node + Python, with agent skills and a 2048 demo.
productsource-backed
Feed Lens: your labels on X, Threads and Weibo
An open-source Chrome extension (store review pending) that labels posts on X, Threads and Weibo with rules you define, powered by your own TypeSafe account.
directorysource-backed
jev-lab: 59 open-source projects around one question
Fifty-nine small open-source projects exploring what changes when AI returns a typed decision instead of a paragraph — agent safety, RAG, research, games, public data — mapped in one repository.
demosource-backed
doom-ai-overlord: Doom on a 421M local decision model
Doom played by the Laya System-1 model via ViZDoom: one forward pass per decision, fully local, live model probabilities on screen; the model advises, deterministic rails enforce.
integrationsource-backed
duckdb-jev (prasanthj): native, batched, cached
A native DuckDB extension for Jev classification, scoring and semantic predicates from SQL: vectorized input, batching, bounded concurrency, dedup and cross-query TTL/LRU caching. Distinct from colliber/duckdb-jev.
integrationsource-backed
Treg + Jev: three workflows, $8K/month saved
Treg ('OpenRouter for agent tools') with Jev on the decision step across fraud detection and signup screening, buying-signal triage and viral-content monitoring.
integrationsource-backed
JEV DataOps: screen and evaluate training data
A workflow for uploading, screening, training and evaluating datasets, with Jev API calls used for the screening stage.
replicasource-backed
necro: an abandoned Qwen3.5-0.8B LoRA replica, with the retrospective
LoRA fine-tuning experiments for Jev-like typed judgments on Qwen3.5-0.8B, published with datasets, adapters, evaluations and a full write-up of why it was abandoned.
integrationsource-backed
typesafe-go: a zero-dependency Go SDK
Go SDK for the TypeSafe API: typed questions in, structured answers out, no dependencies.
integrationsource-backed
jevcache: skip the LLM call when Jev says same intent
An OpenAI-compatible local cache proxy (`npx @kushalicious/jevcache`): agents that re-ask the same thing get the cached answer when Jev judges the intent identical.
demosource-backed
jev-shell-history: fish-style zsh suggestions ranked by Jev
Picks the most likely command from the last 100 unique history entries and ghosts it after the cursor, fish-style, using Jev to rank by intent.
roundupcommentary
Twenty Jev projects to copy (Chinese list)
A Chinese list of twenty projects for people who just got an API key: jev-ultrafast, fast-jev-compaction, json-render, typesafe-mcp, jev-mcp, SemDecide, the Codex router, winnow, jev-review, blink, Agent Desktop, typesafe-mario, jev-drone, OneVOneJev, jev-trader, prism-liquidity-agent, neo4jev, jev-curate, Canny and killmyidea.
demosource-backed
xo-jev: Jev plays tic-tac-toe
A browser tic-tac-toe game where Jev chooses the O move from the currently free cells.
replicasource-backed
jevmlx: parallel constrained decisions for any MLX model
Jev-style parallel constrained decisions for any MLX model on Apple Silicon: typed, schema-valid JSON in one forward pass.
replicasource-backed
litjev: /v1/systemone on top of a local Qwen via vLLM
Turns any off-the-shelf LLM into a Jev-like decision layer and serves the same /v1/systemone API locally — no API key needed.
integrationsource-backed
is-malicious: scan a repo before you run it
A codebase scanner that checks third-party repositories and CI scripts for malicious behaviour before execution, with Jev as the judge.
integrationsource-backed
jev-guard: auto mode for every coding agent
Risk-scores every tool call (rm, curl, bash…) with session context into deny / ask / allow, flags prompt injection in tool results and checks skills and plugins; works with Claude Code, Codex and others.
integrationsource-backed
opencode-jev-orchestrator: cheap sticky model, Jev escalates hard turns
Keeps OpenCode on one cheap model for a warm cache and lets Jev decide which turns are hard enough to spawn stronger subagents.
integrationsource-backed
pi-typesafe-jev: Jev as five native Pi tools
A Pi extension exposing TypeSafe judgments as five tools (choice / bool / score and friends) so the model makes narrow semantic calls while your code keeps thresholds and weights.
No matching signal
Try a broader search or .