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.
GitHubAgents & browsers
GitHub
310 builds · page 1 of 8
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.
GitHubAgents & browsers
Playwright + Jev: tests in plain language
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.
GitHubAgents & browsers
toolgate: a tool-call firewall for agents
Omi
Sponsored
Gentle daily affirmations on your Home Screen and Lock Screen.
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.
GitHubTools & apps
Jevstiller: distill Jev calls into a local model
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.
GitHubContent & growth
Laugh Track: rehearse a speech for 200 Jev listeners
A fast scanner that reviews code for correctness, security, reliability, compatibility and test gaps, with actionable feedback. Supports the Jev API and local models.
GitHubTriage & routing
momus: staged Rust code and security review
Typo tolerance, typeahead, barcodes and facet counts in plain Postgres SQL, plus an optional Jev step that asks one question per top-10 result.
GitHubTools & apps
Algolia-style Postgres search with a Jev reranker
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.
GitHubAgents & browsers
Jev Layer: bounded decisions for agent harnesses
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.
GitHubGames & real time
System 1 Speedcuber: a Rubik's cube agent
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.
GitHubTriage & routing
Jevops: SRE log triage with Jev
Replays real compressor telemetry through an emulated Modbus device, spots anomalies in plain code, then asks Jev which fault from the manual explains them.
GitHubRobotics & devices
Machine fault diagnosis with Jev
Keeps your desktop visible and your Mac awake while a tiny fox blocks keyboard, mouse and trackpad input. Jev drives the character's reactions.
GitHubTools & apps
bonk: a fox guards your Mac's keyboard
An agent-ergonomic CLI for fast calibrated judgments from the shell: pick, rate, check, rank, triage and guard, plus CI and agent hooks.
GitHubTools & apps
jev-axi: a Jev CLI for agents and humans
Watch Jev play chess against itself, or play against it. Jev picks every move; FastAPI and python-chess run the board.
GitHubGames & real time
Play chess against Jev
Azdaja gives Claude Code, Codex and OpenCode a persistent Python workspace to break tasks down and reuse results. Jev adds optional judgments for ranking and classifying.
GitHubAgents & browsers
Azdaja: Jev inside an open-source RLM layer
aeogeolabs
Sponsored
Get recommended in ChatGPT, Perplexity and Google AI Overviews.
A preregistered evaluation publishes request code, raw responses, and outcomes across 21 experiments on Jev decision behavior.
GitHubResearch & data
PriorBench: test Jev batching, confidence, and failure modes
A frozen Jev Choice setup classifies 3,080 banking support messages using category definitions and retrieved labeled training examples.
GitHubResearch & data
Jev on BANKING77: 77-way support-intent classification
Jev combines include/exclude choices with atomic eligibility checks to screen research abstracts against a published systematic-review dataset.
GitHubResearch & data
Jev abstract screening: compare eligibility decisions with human labels
A research CLI uses Jev to rank repository folders, files, and declarations, then returns relevant paths and verbatim source excerpts.
GitHubAgents & browsers
Jevgrep: find relevant code for coding agents
Jev selects battles, destinations, team changes, and menu actions from game state while an emulator harness handles movement and button presses.
GitHubGames & real time
Jev plays Pokémon Red through a legal-action harness
Jev judges transfer risk and behavioral patterns; Java rules decide whether the case passes, freezes, or goes to an analyst.
GitHubTrading & markets
Jev Guard: triage exchange deposits and withdrawals
Jev chooses installed command recipes and closed input values; ordinary code builds a visible execution plan and enforces confirmation rules.
GitHubRobotics & devices
Evoke: route a sentence to installed programs
Jev connects memories, routes retrieval across graph views, scores candidate evidence, and decides when the answer model has enough context.
GitHubResearch & data
Jev-Mem: typed decisions for agent memory and retrieval
A browser extension asks Jev narrow questions about writing patterns, then combines their probabilities to filter social feeds.
GitHubContent & growth
Slop Filter: score and collapse low-quality social posts
An opt-in Jev reranker scores candidate memories from a local SQLite store before selected evidence reaches a coding agent.
GitHubResearch & data
Hippo Memory: rerank recalled memories with Jev
Define and test a typed Jev judgment in a local UI, then call the same immutable version from a backend or coding agent.
GitHubTools & apps
Jev Workbench: versioned judgment functions over HTTP and MCP
An offline linter catches malformed decision setups; an optional Jev pass checks semantic problems that structural rules cannot detect.
GitHubTools & apps
Wellposed: lint Jev questions before trusting the answer
Sitequiet
Sponsored
Uptime monitoring, status pages and client reports for agencies.
An MCP server and decision library use Jev to judge whether evidence supports a claim, rank candidates, and classify proposed agent actions.
GitHubTools & apps
Jevwire: verify claims against cited evidence
A local Codex router asks Jev to choose the next model and reasoning effort while forwarding the complete conversation to that model.
GitHubTriage & routing
Jev Codex Router: model and reasoning selection per call
Jev selects search sources and time ranges, then scores result relevance in a multi-engine search app with editable filters.
GitHubTriage & routing
Jev Search: choose sources and rank web results
Claude supplies a goal and text; Jev selects the browser element, action, value, and completion state while Playwright executes the step.
GitHubAgents & browsers
Jev Browser: an LLM plans, Jev executes browser steps
A reproducible security evaluation uses Jev probabilities to detect prompt injection and vulnerable code on public labeled datasets.
GitHubResearch & data
Jev security bench: injection and vulnerable-code detection
Spliit Cloud can use Jev Choice to suggest categories for shared expenses after checking its local dictionary and group history. Users review uncertain suggestions.
GitHubTools & apps
Spliit Cloud expense categorization with Jev
GitHubTools & apps
tierjev: tier lists ranked by Jev
Magento 2 module asks Jev typed questions about orders, customers, products, reviews, and abandoned carts, then stores answers and confidence in the admin.
GitHubTools & apps
Jev decisions for Magento 2
MinusPodJev is a FastAPI proxy that makes TypeSafe Jev available to MinusPod as an OpenAI-compatible ad-detection model.
GitHubTools & apps
MinusPodJev: podcast ad detection with Jev
Oko uses Jev to rank code for agents. Its author reports 0.48 vs BM25's 0.21 for needed code within 8k tokens, and faster Claude Code sessions across nine tasks.
GitHubTools & apps
Oko: code search for coding agents
Experiment in forecasting Hong Kong stock direction: it builds a past-only state from market data, asks for an up, flat or down call, and renders a standalone report.
GitHubTrading & markets
jev_stock
Crypto terminal that reads up to 1,000 posts about a ticker alongside market and funding data and turns them into a buy, sell, hold, or take-profit call.
GitHubTrading & markets
Jev X Sentiment Analysis
Omi
Sponsored
Gentle daily affirmations on your Home Screen and Lock Screen.
GitHubTools & apps