Jev Reranker
Filter and rerank retrieval candidates using typed Jev relevance judgments.
Runs on demand
Added
Explore what's possible
Jev AI Projects & Use Cases
Explore Jev projects, including those that run in realtime or nearly.
NewJev Gmail Classifier
Classify Gmail messages with custom labels, confidence gates and a metadata-first Jev decision.
Runs on demand
Added
Open Intelligent UI
Jev chooses text, tables or interactive visuals before a chat model creates the answer.
Runs on demand
Added
NewEkko Studio
Optional Jev checks filter and rerank memory cards for an agent workspace.
Runs on demand
Added
NewZerikai Memory
Jev checks codebase questions and retrieved passages before memory evidence is used.
Runs on demand
Added
NewInvalidate
Checks new events against stored facts and records whether memories remain valid.
Runs on demand
Added
Slop Filter
A browser extension combines Jev writing-style judgments with local rules to flag likely AI prose.
Runs on demand
Added
Jev for Chrome
A browser extension uses typed decisions to choose actions from the current page.
Cadence not verified
Added
Jev Codebase Search
Screens and ranks source files by a plain-language implementation goal.
Runs on demand
Added
NewApple RAG MCP
Jev ranks Apple documentation and WWDC transcript matches after hybrid retrieval.
Runs on demand
Added
JEV Shield
Jev scores prompt injection and proposed shell commands before coding-agent hooks allow them.
Runs on demand
Added
Video unavailable. Open the source below.
NewJevbox
Permission-aware document-tree retrieval with Jev branch routing and passage scoring.
Cadence not verified
Added
CreativeJeved
New
NewAutoRAG Jev Decisions
An optional Jev tool gives a local document agent typed classification, routing, and scoring decisions while the caller keeps thresholds and execution policy.
Cadence not verified
Added
DuckDB Jev
The DuckDB extension passes each ticket row's body text and constant criteria to jev_ask.
Cadence not verified
Added
Tasksource Jev Audit
Tasksource publishes rows with state, question, kind, options, and target.
Cadence not verified
Added
Pi Jev Guide
For a semantic tool-action check, the plugin sends a redacted state containing the current task, applicable rules, and proposed action.
Runs on demand
Added
Is Jeven
Each isEven(number) call sends the number as state and asks a Choice question keyed category with true and false criteria.
Runs on demand
Added
NewRoboDiag Harness
Jev classifies the operator’s text into query, diagnosis, action, or chat.
Runs on demand
Added
NewJev as Robot Policy
The controller first asks Jev to select a manipulation intent from the task and observed geometry facts.
Cadence not verified
Added
Laya vs Jev T-Rex
For each T-Rex game decision, a deterministic physics planner creates a text state and labels jump, duck, and run as safe or unsafe under the model’s answer timing.
Cadence not verified
Added
NewJev WeChat Reply Assistant
For a message and optional recent context, Jev receives two questions in one request: intent Choice and direct-reply-risk Score.
Runs on demand
Added
NewSharp X Timeline Filter
When the TypeSafe classifier is selected, Sharp sends a Noul question asking whether to hide each eligible X post under the reader’s plain-language filter instruction.
Runs on demand
Added
NewWeFlow CLI
For each article, the client sends a state containing the title and up to 4,000 characters of body.
Cadence not verified
Added
Stratum
The query analyzer sends the user's log query and known service names to Jev.
Runs on demand
Added
NewJev Chat
For each new message, Jev sees the latest message, recent conversation, available recent results, and any pending question or confirmation.
Runs on demand
Added
Video unavailable. Open the source below.
NewPlaywright Recast
The demo sends measured browser state, the goal, and recent action history to a typed Choice question for the next browser action.
Cadence not verified
Added
Jev Gateway
Jev reads the assistant instructions and recent conversation turns, then answers a typed tool Choice and a Noul question about whether a tool call is needed.
Runs on demand
Added
Experimentspijev
New
pijev
pijev sends the same ticket state with several typed Choice questions that vary only the order of the same support-team criteria.
Runs on demand
Added
Jev Calibrate
A CLI for testing authored Jev questions against labeled examples, selecting thresholds, measuring calibration, and checking changes against held-out data.
Cadence not verified
Added
Jev Arena
A benchmark harness that compares Jev and DeepSeek on comment-labeling tasks and records per-item outcomes, usage, cost, and latency.
Cadence not verified
Added
SREGym
An SRE agent evaluation framework with optional Jev decision support for reviewing diagnostic plans and submitted evidence.
Cadence not verified
Added
NewQuantStudio
A research and trading workbench with a Jev-powered futures monitoring and proposal-evaluation path connected to a simulated contest account.
Cadence not verified
Added
NewSuperTerminal
A terminal app whose command palette combines local fuzzy matching with optional Jev ranking of commands, tabs, and sessions for plain-language searches.
Runs on demand
Added
NewJev WebMCP Extension
A Chrome side panel that maps a user request to page-provided WebMCP tools and their typed arguments using Jev.
Runs on demand
Added
NewSiftRank
A ranking tool that uses pairwise model comparisons across batches and repeated trials to find the strongest items in a large collection.
Cadence not verified
Added
Ulka
A browser-agent extension that combines language-model planning with Jev-selected browser actions and an evidence-checked execution runtime.
Cadence not verified
Added
Computer-Use Cache
A local OpenAI-compatible proxy that caches repeat model requests and can use Jev to judge safe semantic reuse after exact cache misses.
Runs on demand
Added
arc-cua
A computer-use action layer that lets an agent hand bounded desktop subtasks to a fast decision model for execution.
Cadence not verified
Added
Jevvy
A coding-agent permissions plugin that uses Jev to review unresolved shell approval requests.
Runs on demand
Added
NewObsidian LLM Hub
An Obsidian plugin for multi-provider chat, workflows, and local vault search, with optional Jev filtering for retrieved results.
Runs on demand
Added
NewFeather Wand
A JMeter plugin that adds AI chat and Agent Mode, with optional Jev routing to select a focused tool pack for a request.
Cadence not verified
Added
Video unavailable. Open the source below.
NewVexJoy Agent
An agent workspace that routes plain-English requests to specialist agents, skills, and workflows, including an optional Jev-powered route.
Runs on demand
Added
NewTocket
A command-line toolkit for agent handoffs, workspace context, and developer workflows, with optional Jev decisions for routing and checks.
Runs on demand
Added
NewCodexQA Jev Browser
A browser automation skill that uses page-observed controls and Jev choices to carry out and verify user goals.
Cadence not verified
Added
JevIntent
An FkWeChat plugin that classifies a selected message's intent, emotion, urgency, and suggested reply posture.
Runs on demand
Added
jevcore
A Jev decision layer for DeepSeek Harness and other MCP hosts, with explicit controls for provider use and data egress.
Runs on demand
Added
Daily Paper Skills
A research reading workflow that uses Jev to rank candidate papers by relevance before an agent writes commentary and notes.
Cadence not verified
Added
NewTreg Jev Memory
An opt-in Claude Code mod in Treg remembers lasting project preferences from answered prompts using Jev.
Runs on demand
Added
Quivr V2
Quivr V2 combines durable stream ingestion with natural-language article alerts judged by an optional Jev classifier.
Runs on demand
Added
Newjevsd-pg
A PostgreSQL extension and workspace provide natural-language SQL planning, semantic operators, reusable evidence, and reviewed query execution using Jev judgments.
Runs on demand
Added
NewRikkaHub SillyTavern Android
An Android chat client optionally uses Jev to screen memories for relevance and expose a judge tool to its main model.
Runs on demand
Added
NewSmartMoney-Cub
A financial decision harness compares deterministic rules with optional Jev typed judgments over fixed evidence cases.
Runs on demand
Added
NewJev Chat Assistant
An Android conversation assistant reads the visible chat, asks Jev for structured judgments, drafts reply candidates with a text model, then uses Jev to rank them for the person to review.
Runs on demand
Added
NewOmniStudio
An agent platform exposes typed Jev decisions through a UI, an agent tool, and a System One-compatible API, with local and hosted backends.
Runs on demand
Added
Perch
Perch scans code and dependency graphs with configurable System One models, including Jev, to assess issues and rank findings.
Runs on demand
Added
Summarize
A transcript summarizer can optionally use Jev to prefilter relevant passages before the existing summary model runs.
Runs on demand
Added
NewDocJev
A local document workflow uses Jev to classify document pages and identify document boundaries, with review for uncertain results.
Runs on demand
Added
Video unavailable. Open the source below.
NewLLM Debugger
A VS Code debugging extension uses Jev to route each debugging step, with a language model available as a baseline or for other tasks.
Cadence not verified
Added
Horosa Skill
A local astrology skill offers an optional TypeSafe Jev decision layer for narrow routing and interpretation judgments.
Runs on demand
Added
NewJev Browser Skill
A Playwright-based browser skill lets an agent run a bounded web task while Jev selects page actions.
Cadence not verified
Added
MetaCog
A model-agnostic metacognition loop that generates candidate reasoning paths and uses a System One judge such as Jev to select or score them.
Cadence not verified
Added
CNKI Skills
Research workflow skills for CNKI that include an opt-in Jev extension for title and abstract screening proposals.
Runs on demand
Added
Skilled Agent Harness: Spec Driven Loops
A collection of agent skills and tooling that includes a CLI classifier with Jev and Pi classifier transports.
Runs on demand
Added
Albatross
An agent runtime can ask Jev to answer narrow error-classification questions before using the main model.
Runs on demand
Added
Video unavailable. Open the source below.
NewAstra
An agent runtime optionally uses Jev to select relevant memories and detect explicit dismissal of saved lessons.
Runs on demand
Added
Save Token Jev Clean
A token-saving context compactor that uses Jev Noul judgments to choose which tool calls and results to retain.
Runs on demand
Added
Glowbom OSS
Open source project with an optional OpenCode tool that lets an agent ask Jev for a structured choice.
Runs on demand
Added
Astra-Ares
A Codex hook that asks Jev to choose GPT-6 reasoning effort and how many generations to keep that choice.
Cadence not verified
Added
Laya Ultrafast
A local Apple Silicon browser agent port of jev-ultrafast that uses Laya typed decisions by default and retains hosted Jev as an optional mode.
Cadence not verified
Added
Jev Design Test
The project turns a single probabilistic request into a varied exploration grid by combining independent slot distributions, enforcing incompatibility rules, and selecting diverse combinations.
Runs on demand
Added
NewJev Explained Playground
The examples make the boundary between classification and action concrete: Jev supplies typed probabilities, while ordinary application code applies thresholds, confidence checks, and human-review branches.
Runs on demand
Added
NewDetroit AI Player
The adapter lets a typed classifier choose among a game's existing actions while enforcing that the answer is one of the offered options and has the highest reported probability.
Cadence not verified
Added
Hafiza OS
The integration narrows model judgment to candidate selection over source-checked records, with privacy checks, input and question budgets, caching, deadlines, and a local fallback around the call.
Runs on demand
Added
Pi Codemode
It makes typed probabilistic classification an optional primitive inside a sandboxed tool-calling agent.
Runs on demand
Added
NewJev X Sentiment Analysis
It combines market microstructure with stratified social evidence in one structured decision request, with separate typed outputs for recommendation, sentiment, squeeze risk and news impact.
Runs on demand
Added
NewClaude Code Trace
It evaluates agent behavior with a fixed set of interpretable metrics plus action-window questions, while minimizing or explicitly confirming session data before sending.
Runs on demand
Added
Hookmeter Jev
Typed judgments are combined with explicit product rules: a cautious Noul threshold protects legitimate bold copy, while score/archetype weights adapt to text length.
Runs on demand
Added
Webctl
The state keeps the search intent beside each candidate result, while the same judgment API supports individual calls and batched per-result decisions to limit round trips.
Runs on demand
Added
ErisLint
Rules are declared as typed choices over compiler-like Rust contexts, so teams can tailor checks while dry-run exposes the exact planned state and request before the API call.
Cadence not verified
Added
CaptainCore
It adds a typed review layer to deterministic malware signatures: the model sees the exact matched text and surrounding source, while the existing scanner remains the source of detections.
Cadence not verified
Added
Anna Agent
The decision input is constrained to task-relevant candidate fields, candidate IDs are remapped before sending, and abstention is an explicit option when the evidence does not distinguish a suitable assignee.
Runs on demand
Added
NewBeamWeaver
The example shows both direct multi-type classification and Jev as a router classifier, with an explicit minimum-confidence setting before dispatching to a selected model.
Runs on demand
Added
AI Backends
It packages Jev evaluation behind a provider interface and exposes inspectable typed-request examples, so an API caller can switch among TypeSafe and other evaluation providers while keeping the same state-and-questions contract.
Runs on demand
Added
OpenAI Scala Client: TypeSafe
It makes a structured decision model usable through an existing chat-completion API by translating schema fields into typed decisions, while retaining Jev probabilities and confidence in the original response metadata.
Runs on demand
Added
Video unavailable. Open the source below.
NewJevmem
The same typed-decision model supports a complete project-memory loop: classify and filter completed turns, retrieve memories for the next prompt, and evaluate relevant safety rules before tool use.
Runs on demand
Added
NewRedAmon
A security recon framework applies bounded Jev decisions to page classification and scan planning.
Cadence not verified
Added
Social Monitor
A multi-source news monitor assesses reader value using a structured Jev rubric.
Cadence not verified
Added
NewJev SEO Python Audit
A crawler combines deterministic technical checks with typed semantic judgments for actionable SEO reports.
Runs on demand
Added
Shapeshift Jev UI
An input field turns natural language into structured interface cards through parallel typed decisions.
Runs on demand
Added
Ghosthands Jev Fast Lane
An optional browser-control fast lane uses Jev to choose operations and UI targets.
Cadence not verified
Added
DeepResearch Jev Report Evaluation
A research agent evaluates report relevance, evidence and citations with a strict Jev decision adapter.
Runs on demand
Added
Jimothy Jev Distillation
A distillation CLI uses hosted Jev teacher judgments to label data for a smaller local classifier.
Runs on demand
Added
LandPPT Jev Layout Selection
A presentation builder uses Jev to score slide-to-layout fit while deterministic assignment enforces layout constraints.
Runs on demand
Added
NewSub2API TypeSafe Gateway
An API gateway forwards native Jev System One requests with account isolation, usage billing and bounded account failover.
Runs on demand
Added
NewDeepSeek Harness Jev Plugin
A community plugin adds typed Jev decisions to DeepSeek Harness skill selection, file ranking, supervision and tool-output handling.
Cadence not verified
Added
NewOh My Claude Code: Jev Judgments
A Claude Code orchestration plugin compares typed Jev judgments with existing heuristics through opt-in shadow calls.
Cadence not verified
Added
Road Decider: Jev Mode
A racing demo compares Jev and d1 lane choices on the same road.
Runs in realtime
Added
NewOpenMuse Generative UI
A Jev adapter chooses presentation controls and scores candidate fit for a mobile assistant.
Runs on demand
Added
NewOpenMausBot Auto Routing
Jev chooses responders for unmentioned messages in an Auto-mode bot room.
Runs on demand
Added
NewJev Social Research Agent
A social research example routes user questions to evidence collection before generating an answer.
Runs on demand
Added
Jev DOOM Agent
A live Jev controller chooses movement, view, fire, and interaction controls for DOOM.
Cadence not verified
Added
New
Jev Voice for Mac
A macOS voice and text controller that selects live UI actions with Jev.
Runs on demand
Added
Jev Design Dashboard
A logistics dashboard whose design system Jev selects from a one-sentence style brief.
Runs on demand
Added
NewJevgrep
A code search CLI that asks Jev typed relevance and scope questions about candidate source blocks.
Runs on demand
Added
RAG-Fusion Jev Evaluation
Tests Jev as a typed relevance judge and query router inside a RAG-Fusion retrieval experiment.
Runs on demand
Added
NewLangWatch Instant Evals
Runs typed Jev judgments over selected traces and spans in a user-triggered Instant Eval job.
Runs on demand
Added
Laravel AI SDK
Laravel AI SDK classification gateway with a TypeSafe provider that sends typed Boolean, Choice, and Score questions to Jev.
Runs on demand
Added
New
NewJev robot control
Recorded xArm7 MuJoCo pick-and-place trial comparing Jev with two language-model controllers under the same Cartesian action interface.
Runs in realtime
Added
doc-router
PDF page router that uses Jev to identify pages needing OCR, extracts text pages locally, and merges the results in order.
Cadence not verified
Added
Jev for Apple Foundation Models
Swift bridge that turns Apple Foundation Models @Generable schemas into Jev typed questions and reconstructs typed results.
Runs on demand
Added
Agent toolingfx
New
fx
Native Zig coding agent with an optional Jev-backed automatic permission reviewer for pending tool actions.
Runs on demand
Added
jgrep
Semantic code search and diff linting that asks Jev whether source chunks match a behavior described in plain language.
Cadence not verified
Added
Jev Chat Jarvis for macOS
macOS chat overlay that judges incoming-message intent and reply risk, then ranks suggested replies.
Runs on demand
Added
jev-code
Agent tool and CLI that batches typed Jev classifications, checks, scores and rankings for coding tasks.
Runs on demand
Added
NewCelesto Jev PR Review Lab
Runnable PR-review lab that compares Jev and an LLM on candidate code-review findings.
Runs on demand
Added
NewOh My Pi
Coding-agent fork with a native TypeSafe Jev judgment provider used for bounded agent decisions.
Runs on demand
Added
LiteLLM
LLM gateway whose optional Jev complexity classifier routes each incoming request to a configured model tier.
Runs on demand
Added
NewBilingual Book Maker
EPUB translation tool that can ask Jev which markup groups contain text worth translating.
Runs on demand
Added
NewPro Workflow
Coding-agent workflow with optional Jev hints for correction detection and command risk.
Runs on demand
Added
Flick
Local MCP computer-use agent that lets Jev choose browser and macOS actions from observed controls.
Runs on demand
Added
GPT Researcher
Research agent that scores scraped passages with Jev before drafting cited reports.
Runs on demand
Added
Jev Model Router
A Claude Code module that uses Jev to route model tier, reasoning effort, and risky-action judgment for agent tasks.
Runs on demand
Added
Clash Jev
A research Clash Royale bot that uses computer vision and Jev to choose gameplay actions on a real Android device.
Cadence not verified
Added
NewJeview
A local proxy and live visualizer for Jev decisions and their conditional follow-ups.
Runs on demand
Added
NewGoutoujunshi Jev Chat
A Mac WeChat reading and reply-drafting companion with optional Jev strategy selection.
Runs on demand
Added
Jev Kit
A set of Jev-powered tools for Claude Code, including guarded tool calls, document classification, search, browser control, and review.
Cadence not verified
Added
DeepDoc
Researches a local document collection with Jev-backed evidence selection and coverage checks.
Cadence not verified
Added
New
NewJev-Mem
Uses fast decisions to organize memory and guide retrieval for long-running agents.
Cadence not verified
Added
NewJev Curate
Sifts synthetic and pretraining datasets with typed Jev decisions.
Cadence not verified
Added
New
NewOpenCodex
A provider proxy for coding agents with optional Jev model and effort routing.
Cadence not verified
Added
Math To Manim
Builds animated math explanations and uses Jev to evaluate teaching and visual checkpoints.
Cadence not verified
Added
NewAgentConnect
A collaborative workspace that routes team conversations and review work to AI agents.
Runs on demand
Added
Agent Chaperone
An MCP proxy and hooks adapter screen agent tool calls and returned content with probability-based Jev judgments.
Runs on demand
Added
NewGrok Bot Jev Router
A small Grok Bot router uses Jev to decide whether to reuse work, stop retries, limit research, or ask for approval.
Runs on demand
Added
Video unavailable. Open the source below.
NewMario Never Dies
Jev chooses Mario’s moves from structured game state; after death, four VM branches try different recoveries.
Cadence not verified
Added
MoonBit Jev Playground
A MoonBit playground puts Jev's typed decisions into games, command-line experiments, browser actions, and agent safety checks.
Cadence not verified
Added
Video unavailable. Open the source below.
NewJev Browser by Ying-Kai Liao
A browser agent lets an LLM set the goal while Jev chooses page actions and checks progress in a Playwright loop.
Cadence not verified
Added
Pi Jev by Theo Oliveira
A Pi coding-agent extension uses Jev to discover relevant tools and skills, make typed judgments, and optionally guard tool calls and compaction.
Runs on demand
Added
YC Indexor
Search 6,241 Y Combinator companies by meaning, logo, visible text or tags, then have Jev score the shortlist.
Runs on demand
Added
SemDecide
A Unix CLI that turns Jev judgments into predicates, routes, scores, filtered streams and stable exit codes.
Runs on demand
Added
NewJev Plays StarCraft
Jev completed the Strongarm mission in original StarCraft shareware using structured state and mouse-and-keyboard actions.
Runs every few seconds
Added
Pi Jev Auto Mode
A fail-closed permission gate for Pi that asks Jev to judge tool calls left undecided by hard rules.
Cadence not verified
Added
NewBest Agent Skills
Daily rankings of agent skills across registries, with Jev judging social relevance, listing quality and category.
Cadence not verified
Added
NewSkylos Jev Review
An opt-in Jev review of ambiguous dead-code findings in the Skylos scanner, with uncertain results left visible.
Runs on demand
Added
NewJev Chat Jarvis
A phone conversation copilot that reads visible chat and offers suggested replies while the user stays in control.
Runs on demand
Added
NewJevHarness
LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.
Cadence not verified
Added
jev-dataops
An open-source JEV-powered workbench for streaming data selection, quality evaluation, automatic LoRA training and held-out model evaluation.
Cadence not verified
Added
Newminecraft-agent
Astra planner and JEV controller for Minecraft, with native recording, tested routes, and run verification.
Runs on demand
Added
Newjev-dsh-decision
Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。
Runs on demand
Added
Newembodied-jev
EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs.
Cadence not verified
Added
jevgrep
Jev-powered semantic code search for coding agents — find behavior across repositories via CLI or MCP, with exact source excerpts and line numbers.
Runs on demand
Added
Newjegrep
Semantic grep CLI where Jev judges which files and exact line ranges match a natural-language code query.
Runs in realtime
Added
jev-recall
Retrieve by relevance, not resemblance: filter an AI assistant's memories with TypeSafe's Jev.
Runs on demand
Added
jev-libero
Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.
Cadence not verified
Added
Video unavailable. Open the source below.
NewJev Align
An open-source CLI helps developers tune Jev criteria using good and bad examples.
Cadence not verified
Added
jevmail
Open-source AI email triage for Gmail. Sorts your inbox into Needs reply, Updates, Promos, Sales and Spam with Jev, TypeSafe AI's decision model, via Vercel AI Gateway. Read-only, runs locally, 1,000 emails in about a minute for 3 cents.
Runs occasionally
Added
jev-skill-suggester
用 TypeSafe Jev 推荐已安装 Skill / Bounded installed-skill recommendations with TypeSafe Jev. Python CLI, Codex skill, bilingual docs and live examples.
Runs on demand
Added
Newjev-use
Say it, and your Mac does it. A computer-use harness on Jev that reads the screen through Accessibility. Fast, no vision model
Runs on demand
Added
jev-semgrep
Grep by meaning, across languages. TypeSafe Jev scores every line against a meaning; combine meanings with AND/OR/NOT. 意味で探す grep。日本語で英語を、英語で日本語を検索できる.
Runs in realtime
Added
Creativelive-jev
New
jev-voice
Talk to your Mac. Local + one Jev (TypeSafe) call per command + macOS automation.
Runs in realtime
Added
NewHermes Jev Skills
A Jev toolkit for agent model routing, memory filtering, compaction, skill selection, triage, and bounded computer/browser decisions.
Cadence not verified
Added
Video unavailable. Open the source below.
NewAbide coding-agent rules
best coding agent use case for Jev: enforcing rules a linter can't coding agents tend to break rules and some rules can't be codified Jev can now score every turn against such rules and tell the agent what to fix asap open-source:
Runs on demand
Added
CreativeJevinci
New
Newjev-recruiter
A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.
Cadence not verified
Added
Jev Social
A local browser-grounded research agent lets Jev choose bounded operations across Instagram, TikTok, and LinkedIn.
Runs occasionally
Added
Jev CU
A Codex computer-use skill that asks Jev to choose actions from accessible on-screen controls.
Cadence not verified
Added
Video unavailable. Open the source below.
NewJev Reviewer
Introducing Jev Reviewer, a tool designed for systematic reviewers to quickly find and extract the information from research articles. App: GitHub:
Runs on demand
Added
Video unavailable. Open the source below.
NewJev Tax Document Classifier
A creator demonstrates a Jev tax-document classifier. Reported accuracy, speed and costs apply to the creator’s corpus and are not independently validated.
Cadence not verified
Added
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
New
NewWindTunnel: Jev + WebMCP
An open benchmark pairs Jev tool selection with Mercury-generated arguments.
Cadence not verified
Added
Jev SEO
A Rust CLI and MCP server uses Jev to route and score zero-cost SEO and generative-search research tasks.
Cadence not verified
Added
is-malicious
Scans a codebase for covert, deceptive, or data-stealing behavior with Jev, then reports suspicious files and line ranges before the user runs it.
Runs on demand
Added
NewVideo unavailable. Open the source below.
New
jev-rules
Jev picks which of your rules apply to each prompt, so Claude only sees the ones that matter.
Runs on demand
Added
NewJev CLI
A command-line toolkit exposes Jev verification, classification, extraction, ranking, routing, compaction, and custom typed decisions for scripts, CI, and agent workflows.
Runs on demand
Added
jev-shell-history
Fish-style zsh history autosuggestions ranked by Jev (TypeSafe).
Runs on demand
Added
hono-jev-router
Route HTTP requests by meaning. A semantic router for Hono powered by Jev.
Runs on demand
Added
Video unavailable. Open the source below.
NewJevcal confidence-threshold calibration
Everyone picks Jev confidence thresholds by vibes. 0.95? 0.5? I built jevcal. Give it your data and say "I need 99% accuracy". You get the exact threshold, how much Jev can handle, and how much still needs an LLM. Open source, one command.…
Runs on demand
Added
Newjev-browser-use
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
Cadence not verified
Added
Video unavailable. Open the source below.
NewTouchpress mobile end-to-end testing
my mobile e2e testing library powered by @agent_device and AI sdk now supports Jev from @typesafeai Same test, same loop: Jev: 29s, $0.003 Haiku 4.5: 37s, $0.07
Runs on demand
Added
jev-pruner
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
Runs on demand
Added
NewJevbridge
ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.
Runs on demand
Added
Jev Sift
Classify first. Read selectively. A portable agent plugin and MCP tool for batch text classification.
Runs on demand
Added
Newyoshi
Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into
Runs on demand
Added
NewYouTube sponsor skipper
Detect youtube sponsor segment with live audio and transcript powered by Jev
Runs on demand
Added
Sniff Test
A prose linter that combines local countable rules with Jev-powered judgment rules for writing checks.
Runs on demand
Added
Video unavailable. Open the source below.
NewVideo unavailable. Open the source below.
NewFast Jev Compaction
A Claude Code plugin experiments with pruning context instead of summarizing it.
Runs on demand
Added
Newpg-jev
Filter, rank and classify PostgreSQL rows using natural-language conditions.
Runs in realtime
Added
NewCompact Adviser
"Work appears completed or recorded. Run /compact to save tokens."
Runs on demand
Added
NewJev-Trades
Trading bot with the all new TypeSafe AI's first system one model named as Jev.
Runs on demand
Added
NewJev Search
A web-search application uses Jev to choose sources, time ranges and search terms, then rank returned links and snippets.
Runs on demand
Added
typesafe-adblock
🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.
Runs on demand
Added
skillbox
Self-hosted, versioned skills library for AI agents. MCP, scoped clients, and optional Jev recommendations.
Runs on demand
Added
jev-code (rhighs)
Interactive TypeScript coding CLI with typed routing, decision programs, and validated formal trees driven by Jev.
Cadence not verified
Added
NewVideo unavailable. Open the source below.
NewJev Model Router CLI
A CLI recommends an agent or model from a task and the user's available AI subscriptions.
Runs on demand
Added
NewPixel Art from Jev
A classifier produces small pixel-art images through repeated color choices.
Cadence not verified
Added
fastbrowse
A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.
Runs on demand
Added
pg_typesafe
A PostgreSQL extension exposes Jev categorical classification inside SQL.
Cadence not verified
Added
Jev as a Judge
An evaluation harness comparing Jev with LLM judges on the same recorded agent runs.
Runs on demand
Added
NewVideo unavailable. Open the source below.
NewJev Voice Browser
A voice-browser demo combines speech input and Jev-selected actions in a rapid interaction loop.
Runs on demand
Added
Unclutter
A browser extension removes ads, cookie banners and other page clutter with reusable Jev rules.
Runs on demand
Added
Foreman
An experimental supervisor uses Jev to assess and steer a coding agent.
Cadence not verified
Added
JevMeter
A video tool scores each spoken sentence and renders an annotated 16:9 edit.
Cadence not verified
Added
Kill My Idea
A web app asks Jev a set of parallel questions to decide whether a startup idea should be killed, fixed, or shipped.
Runs on demand
Added
Jev for Home Assistant
Turn questions about household state into sensors and automation inputs.
Runs occasionally
Added
Video unavailable. Open the source below.
NewMobile Jev
An Android agent navigates apps with a live studio and execution trace.
Cadence not verified
Added
Jev Music Playground
A music playground that turns a chosen style into sheet music, playback and MIDI.
Cadence not verified
Added
NewJevGPT
An experiment that makes a non-generative decision model assemble a chat reply one word at a time.
Cadence not verified
Added
Commit Miner
A command-line tool classifies Git commits by change type, bug fixes and security relevance.
Cadence not verified
Added
Video unavailable. Open the source below.
NewSkillRanker
A Rust CLI ranks installed agent skills against live session context with Jev, then applies abstention and local feedback around the typed result.
Runs on demand
Added
Jev Moderation Bot
A Discord bot uses Jev to filter spam and scam links and escalate repeat offenses.
Runs on demand
Added
Video unavailable. Open the source below.
NewJev Review
An MCP tool supplies repeated software-quality measurements to coding agents.
Runs on demand
Added
Jev Evaluation Agent
A personal-assistant agent uses Jev to select one tool from a 100-tool catalog before each model step.
Cadence not verified
Added
NewInstinct UI Selector
Natural-language requests select and configure real UI components.
Runs on demand
Added
Video unavailable. Open the source below.
NewJev Ultrafast
A browser agent selects actions from the current DOM and demonstrates flight search.
Runs in realtime
Added
Games1v1 Jev
New
Video unavailable. Open the source below.
NewJev Trader
A trading experiment connects rapid decisions to an on-chain order book.
Runs in realtime
Added
TypeSafe Plays Minecraft
A Minecraft bot gathers materials and builds a supplied Canadian flag blueprint.
Runs in realtime
Added
Jev Review Workflow
A staged code-review workflow follows Jev signals through focused checks and a local dashboard.
Cadence not verified
Added
NewJev Router
A local router chooses a model tier for each Claude Code or Codex turn.
Runs on demand
Added
TypeSafe Computer Use
A macOS computer-use loop uses OCR and Jev to choose bounded actions.
Cadence not verified
Added
Blink
A codebase-search tool uses ensembles of Jev-guided filesystem walkers.
Cadence not verified
Added
Pi Jev
A Pi extension gates tool calls, judges command output and exposes typed Jev questions.
Runs on demand
Added
Video unavailable. Open the source below.
New
NewPi Warden
A Pi extension watches tool calls and agent progress for safety and completion problems.
Runs on demand
Added
Winnow
A Claude Code hook that filters large tool results before they enter the agent's context.
Runs on demand
Added
Newpi-typesafe
Pi extension with a Jev evaluation tool, terminal playground, and typed API for other extensions.
Runs on demand
Added
Loki Jev Companion
The Loki agent offers Jev as an optional typed-decision companion and session model router.
Runs on demand
Added
NewSupercov
Code quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.
Runs on demand
Added
Memorax Code
An agent memory plugin that can ask Jev whether a new request needs a memory search.
Runs on demand
Added
Newduet-agent Jev Routing
duet-agent uses a Jev-backed routing table to select models for agent work.
Cadence not verified
Added
NewHippo Memory
A local memory system for AI agents with an optional Jev reranker for recalled notes.
Runs on demand
Added
Decapod
A repository governance kernel can attach optional Jev trajectory observations to its assurance loop while retaining deterministic policy, interlocks and proof rules.
Runs on demand
Added
NewPi Interactive Shell
An interactive terminal extension that can use Jev to select useful output from captured command logs.
Runs on demand
Added
OpenWork Jev Verification
OpenWork uses Jev as a typed verification judge for agent-produced work in its evaluation testkit.
Runs on demand
Added
NewSmithers Jev Workflows
Smithers uses Jev checks and scores across repository and workflow automation.
Runs every few seconds
Added
NewQuantDinger
An open-source quantitative research platform that documents Jev-powered pre-trade decisions alongside market data, backtesting and execution tools.
Cadence not verified
Added
NewSurf CLI
A Chrome control CLI with an optional Jev-driven semantic action loop.
Cadence not verified
Added
Vercel AI CLI
A terminal tool exposes typed Boolean, Choice and Score evaluations with Jev as the default evaluation model.
Runs on demand
Added
NeuroLink Jev Decisions
NeuroLink exposes typed Jev decisions for routing, compaction, tool use, and retrieval planning.
Runs on demand
Added
OpenAgents Coder
A terminal coding agent uses Jev for typed turn, risk and progress judgments before its generative planning and tool loop.
Cadence not verified
Added
Formanator Jev Claims
Formanator can use Jev to select benefit and reimbursement categories for claims.
Runs on demand
Added
No projects matches these filters.