LangChain · TypeSafe
langchain-ai
An optional JEV classifier integration for Python LangChain workflows.
What JEV decides
Submits binary, categorical, and ordered-score questions and returns typed answers with probabilities.
Open Source Gallery · JEV
See how real open-source projects use JEV for choice, scoring, and typed decisions. Compare integration points and decision spots, then reuse the same shape in your own agent flow.
System One
jev-1.14Curated by decision pattern
langchain-ai
An optional JEV classifier integration for Python LangChain workflows.
What JEV decides
Submits binary, categorical, and ordered-score questions and returns typed answers with probabilities.
virattt
An educational hedge-fund prototype with an optional JEV adapter for structured strategy judgments.
What JEV decides
Converts strategy questions into System One requests and normalizes typed answers for the fund workflow.
BerriAI
LiteLLM can use JEV inside its complexity-based model router.
What JEV decides
Maps a request to a configured complexity class that drives backend model routing.
Wei-Shaw
A subscription-to-API gateway with a native TypeSafe client for content moderation.
What JEV decides
Batches Noul questions, validates every probability, and returns moderation scores to local risk-control policy.
volcengine
OpenViking can use JEV as a calibrated reranker for agent memory and context retrieval.
What JEV decides
Asks one Noul relevance question per document and falls back to vector scores when evaluation fails.
can1357
A coding agent with an optional TypeSafe judgment provider for bounded workflow decisions.
What JEV decides
Sends agent state and typed questions to JEV and parses structured answers.
davila7
A Claude Code mod that classifies subagent model and reasoning-effort needs.
What JEV decides
Jev classifies the task; local policy maps the result to model and effort settings.
ComposioHQ
A TypeSafe provider that uses JEV to choose among tools and bounded argument options.
What JEV decides
Turns tool conditions into structured questions and passes answers to local invocation logic.
vercel
The AI SDK TypeSafe provider exposes JEV through the shared evaluate interface.
What JEV decides
Maps choice, score, and yes/no questions to System One and parses typed results.
trycua
A computer-use example pairing Cua Driver observation and execution with bounded JEV choices.
What JEV decides
Reads DOM or visual-region descriptions and returns one supplied candidate action ID.
vectorize-io
An agent-memory system with a TypeSafe reranker that can prune irrelevant recall candidates.
What JEV decides
Uses calibrated relevance decisions to score and optionally prune retrieved memories under bounded retry policy.
different-ai
An open-source cowork-style agent workspace that can run JEV-backed reviews inside CI and skill workflows.
What JEV decides
Scores or gates test-coverage and review findings before merging agent-produced changes.
pydantic
A TypeSafe model integration that maps supported structured outputs to JEV questions.
What JEV decides
Converts output fields into typed questions and maps JEV answers back to the result model.
elizaOS
An optional TypeSafe HTTP adapter in the Eliza agent operating system.
What JEV decides
Sends state and questions only when explicitly called and validates typed answers.
browser-use
A browser agent that uses JEV to choose an action and matching DOM element, calling a text model only when input text is needed.
What JEV decides
Chooses the next browser action and target element from the current page state.
langchain-ai
A TypeSafeClassifier integration for JavaScript LangChain workflows.
What JEV decides
Invokes JEV with predefined questions and parses choice, noul, score, and probability fields.
vercel-labs
A JEV UI-composition experiment that selects from predefined components and properties.
What JEV decides
Evaluates component configurations before local code assembles the UI specification.
NandhaKishorM
Multilingual non-autoregressive System 1 decision engine: typed choice/score/noul in one forward pass, with a router across checkpoints.
What JEV decides
Answers typed questions over text or structured state without generating free-form text to parse.
OpenByteInc
An open-source trading OS with a JEV decision gate before selected live entries.
What JEV decides
Checks evidence quality, signal consistency, exposure, and budget before an order reaches the exchange.
openchamber
An optional automatic model router that classifies a message before model selection.
What JEV decides
Selects a task category; local mappings determine the model and reasoning configuration.
0xPlaygrounds
An experimental Rust crate for expressing JEV questions and answers with Rust types.
What JEV decides
Sends application state and questions and parses Choice, Score, or Noul answers.
maximhq
Bifrost exposes TypeSafe as a native provider through its shared decision operation.
What JEV decides
Maps Bifrost decision requests to System One while preserving aliases, usage, errors, and typed answers.
kunchenguid
An agent crew dispatcher that can match task briefs to rules with JEV.
What JEV decides
Matches the task brief to candidate rules before local policy resolves the execution profile.
tbphp
A self-hosted AI gateway with a first-class JEV channel and native Decisions routes.
What JEV decides
Registers the fixed TypeSafe endpoint and routes decision creation, model listing, and probes through the native protocol.
GreptimeTeam
GreptimeDB adds an experimental SQL predicate backed by JEV judgments.
What JEV decides
Evaluates each non-null row as a Noul question and compares its probability with a caller-supplied threshold.
tamaratran
Compacts Claude Code tool history while keeping retained text verbatim.
What JEV decides
Scores which calls remain useful; local code keeps, truncates, or drops them.
oomol-lab
Open Connector exposes TypeSafe evaluation through its provider runtime.
What JEV decides
Validates Noul, Choice, and Score questions and responses before returning them to connector workflows.
vercel
Vercel’s open agent framework for packaging skills, evals, and tool-using workflows.
What JEV decides
Structures agent runs so later steps can apply typed judgments before acting.
Kiln-AI
Kiln maps compatible JSON schemas to JEV questions for structured single-turn tasks.
What JEV decides
Converts enums, booleans, bounded integers, and probabilities into typed questions, then reconstructs schema-valid output.
agentgateway
A JEV webhook guardrail example for inspecting model requests and responses.
What JEV decides
Scores jailbreaks, harmful content, and secret disclosure before gateway policy accepts a request.
latitude-dev
An optional JEV preclassifier for selecting which conversation checks should run.
What JEV decides
Judges which checks apply before thresholds and rate limits allow them into the evaluation queue.
jaredpalmer
A tiny trainable Jev-like decision model based on Qwen2.5-0.5B.
What JEV decides
Exposes a TypeSafe-compatible API for bounded local choices and scores.
jev-chat
An Android conversation copilot that reads visible chat context and proposes replies without auto-sending.
What JEV decides
Uses JEV to judge conversation state and bounded reply choices while the user retains the send action.
TheoLeeCJ
An independent open-model implementation of the semantic-if interface pattern.
What JEV decides
Reads option probabilities directly from open models without a generated answer sentence.
vercel-labs
A Zig coding agent with an optional TypeSafe Jev permission reviewer for pending tool actions.
What JEV decides
Posts pending actions to System One as Choice questions and maps allow/deny probabilities into the agent permission gate.
ax-llm
A TypeSafe integration for boolean, finite-class, and native JEV signatures.
What JEV decides
Maps supported signatures to typed JEV questions or sends native System One requests.
http4k
A typed Kotlin client and fake implementation for the TypeSafe System One API.
What JEV decides
Builds model, state, and typed question maps and posts them to the native System One endpoint.
theagentrouter
Agent Router provides a native TypeSafe System One translator in its Envoy-based gateway.
What JEV decides
Passes typed requests through with optional model overrides while retaining usage, errors, and resolved model identity.
jarrodwatts
A market-making experiment that can request one JEV trade decision per Monad block.
What JEV decides
Turns order-book state into a bounded buy, sell, or hold decision before local execution policy.
TianyuCodings
A 0.6B open replica of the JEV interface with parallel decisions and a training pipeline.
What JEV decides
Scores runtime-defined candidates in one pass and exposes complete probability distributions.
typesafe-ai
Official agent skills for building against TypeSafe’s System One / JEV API.
What JEV decides
Guides agents to frame Noul, Choice, and Score questions against System One.
theopenco
LLMGateway implements a native System One route with typed schemas and provider mappings.
What JEV decides
Validates Noul, Choice, and Score requests, resolves aliases to priced models, and routes them through decision-capable providers.
bespokelabsai
An open toolkit for local typed decisions, data curation, and evaluation.
What JEV decides
Explores open local classifiers for bounded judgments and comparable evaluations.
Pluviobyte
An agent-skill collection containing a JEV gate for bounded office-document checks.
What JEV decides
Turns configured document-review conditions into typed judgments before the workflow proceeds.
lahfir
An optional JEV skill that chooses native desktop controls and actions from accessibility data.
What JEV decides
Selects a target and action and estimates presence and risk before local policy executes.
mizorewww
A local Laya typed-decision runtime for Apple Silicon and Core ML.
What JEV decides
Returns choice probabilities from a local open-weight model.
yibie
A large community directory of public JEV projects, integrations, and discussions.
What JEV decides
Organizes the ecosystem into browsable implementation and discussion groups.
elvisun
An open-source PR workflow that screens a live news feed for timely brand opportunities.
What JEV decides
Jev scores hundreds of headlines; the agent only expands the short list into PR actions.
vellum-ai
An optional JEV provider that submits conversation state and explicit questions.
What JEV decides
Bundles state and questions for System One and returns structured answers to the assistant.
vinnylarouge
An independent starter model that scores a changing list of text or visual options in one pass.
What JEV decides
Returns one probability per option without reproducing JEV’s undisclosed model or training.
laravel
Laravel AI includes a native TypeSafe classification provider backed by JEV.
What JEV decides
Maps Laravel classification requests to the System One gateway and a configured JEV model.
asymptote-labs
Cross-harness agent memory that can ask Jev to score bounded, redacted session projections before promoting lessons.
What JEV decides
Sends Noul rubric questions to TypeSafe System One and stores calibrated probabilities with human review gates.
CelestoAI
A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.
What JEV decides
Judges whether a finding was introduced by the change, is supported and merits a fix.
awlevin
Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.
What JEV decides
Selects the next step from deterministically extracted controls and actions before desktop execution.
nokia-applied-research
An open framework that adapts language models to typed decision endpoints.
What JEV decides
Reads closed-form answers from a model and calibrates choice probabilities.
bastani-inc
An optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.
What JEV decides
Sends predefined questions to Jev and decodes answers for callers; regular models still generate code.
vercel-labs
A terminal generator CLI that ships with an agent skill for creating content from the command line.
What JEV decides
Chooses generation steps and skill instructions before local CLI execution.
Anil-matcha
An evidence-backed playbook of JEV use cases, patterns, prompts, and starter code.
What JEV decides
Helps builders pick which typed decision pattern fits a product workflow.
kitfunso
A local-first agent-memory library with an opt-in JEV reranker for recalled memories.
What JEV decides
Scores each recalled memory against the query in one batched Noul request and falls back locally on failure.
githubnext
A local Jev-compatible server with benchmarks across small local models.
What JEV decides
Keeps the Jev request shape while swapping the hosted model for a local classifier.
samuelfaj
A coding-agent runtime with JEV lanes for routing, compaction, memory, and tool-result handling.
What JEV decides
Chooses among bounded runtime policies before local code performs context and tool operations.
uezo
An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.
What JEV decides
Assesses utterance completeness and whether the user is likely to continue speaking.
kentcdodds
Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.
What JEV decides
Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.
v-modal
A curated directory focused on tools built for JEV and TypeSafe System One.
What JEV decides
Surfaces practical tools by integration shape and use case.
milind-soni
A local macOS computer-use companion driven by Jev or Gemini Live.
What JEV decides
Jev chooses pointer actions from locally parsed screen targets.
incoai
A local Apple Silicon inference engine oriented around decision-style models.
What JEV decides
Runs local inference so apps can obtain typed judgments without a remote JEV hop.
AgentiLoop
An optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.
What JEV decides
Adds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.
jev-chat
A Windows reply assistant that reads chat screenshots with local OCR.
What JEV decides
Judges conversation intent and emotion before showing reply drafts.
kerpopule
JEV-powered routing, memory, compaction, skill selection, and computer/browser use for Hermes agents.
What JEV decides
Chooses models, skills, or next computer actions from bounded JEV questions.
heyjunpenn
A multilingual, community-maintained catalogue of open-source JEV projects.
What JEV decides
Indexes implementations and integrations while retaining repository-level provenance for discovery.
Sac-Y
Computer-use helpers that call JEV to decide the next UI action.
What JEV decides
Picks a bounded next action from observed UI state before local execution.
agentjido
A TypeSafe provider for calling Jev through ReqLLM’s evaluate interface in Elixir.
What JEV decides
Sends state and questions, normalizes answers and retains the raw provider response.
devagrawal09
Reviews a Git diff or a codebase in stages and displays review leads in a local dashboard.
What JEV decides
Judges risk, files, evidence regions, mechanisms and severity before rule-based reviewer routing.
BennyKok
An omg.dev mobile testing script can use Jev to read the accessibility tree and choose the next interaction.
What JEV decides
Chooses controls and checks completion or blockage before the test runner operates the UI.
rmalde
A Minecraft agent where a planner sets objectives and JEV selects legal game actions.
What JEV decides
Chooses one available action from observed game state and planner objectives.
thruwire
An independent supervisor loop that reads worker diffs, logs and tests, asks Jev Nouls about stuck / off-track / verify, then applies a Python policy.
What JEV decides
AsyncTypeSafeClient.system_one with default jev-latest sends Noul questions for supervision.
kydlikebtc
A source-linked catalogue and MCP search tool organized by decision pattern.
What JEV decides
Indexes examples by the bounded judgment they implement; it does not call Jev for catalogue search.
wfzyx
An open, local System One decision model with a JEV-compatible interface.
What JEV decides
Scores bounded typed choices locally without autoregressive text generation.
featherless-ai
Adapter turning open LLM endpoints into Jev-compatible classification services without training a separate classifier head.
What JEV decides
Extracts log-probabilities of candidate tokens from model vocabulary logits, formatting them into standard Jev responses.
AbdelStark
A curated list of official and community resources for TypeSafe, System One, and JEV.
What JEV decides
Surfaces which projects and docs are worth opening when building with System One.
AbdelStark
A source-backed field guide to TypeSafe JEV projects, SDKs, demos, and evaluations.
What JEV decides
Organizes ecosystem resources by how they implement or apply typed, confidence-aware decisions.
wuyoscar
A collection of agent skills and workflows with a standard-library JEV decision client.
What JEV decides
Runs typed decisions through TypeSafe or OpenRouter and applies confidence-aware review rules.
notque
An optional Jev routing path that matches VexJoy requests to specialist Agents, skills and workflows.
What JEV decides
After deterministic routing guards, Jev judges the remaining candidates and required workflow components.
smithersai
An agentic TypeScript workflow framework with a first-class JEV classify path.
What JEV decides
Classifies workflow steps or review verdicts through a dedicated JEV relay.
jev-chat
A macOS overlay that reads visible chats and suggests replies.
What JEV decides
Judges message intent and risk before ranking drafted responses.
superagents-lab
Searches the web with Jev choosing sources and time ranges, then ranking returned links.
What JEV decides
Judges search intent, source and time settings, and relevance of individual results.
mrmps
A zero-shot classification service with JEV as its primary typed-decision backend.
What JEV decides
Classifies labels and dimensions, with explicit fallback and observability around JEV calls.
kyotofin
Classifies extracted tax-document pages against a fixed IRS form catalogue.
What JEV decides
Returns form type, page type, and confidence while ingestion stays deterministic.
logicrw
A source-backed JEV ecosystem radar with plain-language discovery and GitHub sync.
What JEV decides
Curates which open-source JEV integrations are worth browsing by decision pattern.
wy-coliney
A Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.
What JEV decides
Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.
dabit3
Small Jev experiments including intent search and agent-assist flows.
What JEV decides
Uses fast intent judgments after retrieval instead of asking a large model to inspect everything.
droidrun
Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.
What JEV decides
Chooses apps, controls and next actions from phone state; Mobilerun executes them.
fhshaik
An experimental NES Mario controller that gives Jev structured emulator RAM and telemetry instead of screenshots.
What JEV decides
Reads motion, enemies, terrain and recent controls, then selects a predefined legal action.
cobanov
A source-backed list of projects built with JEV / TypeSafe System One.
What JEV decides
Highlights repositories that demonstrate concrete typed-decision integration points.
gargpratyush
A Claude Code and CLI proxy that asks Jev to score task complexity and pick a model from the account’s available set.
What JEV decides
Scores task, reasoning, and tool complexity, then chooses among the exact models the account can run; failures keep the current model.
Rizzo-AI-Academy
An independent local decision model exposing a TypeSafe-compatible System One interface.
What JEV decides
Translates Noul, Choice, and Score wire questions into local model requests without claiming JEV model parity.
WrongStack
An optional Jev dispatch classifier for choosing among WrongStack specialist Agents.
What JEV decides
Jev evaluates the task against eligible specialists; local dispatch rules use the result.
cognesy
A TypeSafe Decision driver within Instructor PHP’s Polyglot module.
What JEV decides
Converts application state and typed questions into Jev requests and maps responses to PHP decision objects.
razorback16
An independent System One decision server compatible with Jev’s API, running an open DiffusionGemma model.
What JEV decides
Accepts Jev-style state and Noul, Choice, and Score questions, producing probabilities with a local model.
Mapika
One-pass typed decisions with calibrated probabilities, fine-tuned from Qwen3.5-2B.
What JEV decides
Returns local System One–style answers for Choice, Score, and yes/no style prompts.
TianyuCodings
A framework for creating and evaluating task-specific Jev decision harnesses.
What JEV decides
Turns observations into typed questions and combines answers into actions.
realZachi
Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.
What JEV decides
Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.
AnotiaWang
A curated list of JEV applications, libraries, and System One resources.
What JEV decides
Groups ecosystem resources so builders can compare implementation patterns.
receptron
A Node.js and TypeScript runtime for the open Laya JEV-compatible decision model.
What JEV decides
Runs the ONNX model locally and returns typed decision probabilities without a hosted JEV call.
jkudish
Eight MCP tools for evidence checks, content screening, search, reranking, classification, comparison and extraction.
What JEV decides
Uses typed questions to assess evidence support, content risk and candidate relevance.
shhivv
A Swift client stack that calls JEV while driving local computer-use style helpers.
What JEV decides
Requests typed judgments from JEV before applying local automation actions.
jerryjliu
A document classifier and splitter with a dedicated JEV engine.
What JEV decides
Classifies documents and split boundaries from bounded schemas, with cache and alternate-engine support.
yonatangross
OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.
What JEV decides
Classifies the first task prompt and branch state by work type; local policy accepts the result or falls back.
sutro-sh
A CLI for calibrating Jev classifiers from human examples with GEPA.
What JEV decides
Optimizes the decision prompt against examples instead of relying on a generic criterion.
ekzhang
A JEV-compatible API endpoint built on open models with a prefill-only serving path.
What JEV decides
Serves System One–style probability answers from open models instead of hosted JEV.
Heman10x-NGU
A calibrated ~151M non-autoregressive local decision engine aiming at JEV-style typed answers.
What JEV decides
Produces local Noul/Choice/Score-style probabilities without calling hosted JEV.
typesafe-ai
A drop-in TypeSafeClient replacement that backs System One calls with ordinary LLM APIs.
What JEV decides
Maps Noul, Choice, and Score questions onto LLM providers and normalizes probabilities.
itsmostafa
An MCP server that lets Claude Code, Claude Desktop, Codex and Pi ask Jev typed questions.
What JEV decides
Submits state and Choice, Score or Noul questions and returns structured answers with probabilities.
monotykamary
Pi’s programmable runtime includes an optional Jev loop for observing state, making decisions and running bounded actions.
What JEV decides
Programmed questions feed Jev judgments into local action logic under runtime budgets.
cequence-io
A dedicated TypeSafe module in a Scala client that supports multiple AI providers.
What JEV decides
Sends shared state and typed questions to Jev and parses structured answers.
moritzkremb
Controls a Playwright browser by sending incremental speech transcripts to Jev.
What JEV decides
Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.
FerryCorleone
A local chat-analysis app using Jev for emotion, intent, and reply checks.
What JEV decides
Scores message intent and the quality of a proposed reply from a conversation.
hr98w
An educational JEV-like visual inference experiment on Apple Silicon with shared context scoring.
What JEV decides
Scores visual or textual candidates in one forward pass and returns calibrated probabilities.
jkudish
Drives a browser from a task and URL, returning the final page, screenshot and action trace.
What JEV decides
Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.
monteduro
A startup-idea checker that asks Jev bounded scoring questions.
What JEV decides
Scores idea criteria and applies a local rule to classify the outcome.
0xNatoshi
Uses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.
What JEV decides
Classifies task difficulty and reasoning needs before local policy selects a model configuration.
rokbenko
A robot orchestration CLI with an optional System One stepper that chooses among permitted discrete robot calls.
What JEV decides
Routes Choice and Noul questions through the TypeSafe System One client while the executor keeps safety gates.
kitze
A self-hosted, versioned Agent skills library with optional Jev recommendations.
What JEV decides
Jev scores task relevance among skills the client is allowed to access.
typesafe-ai
The JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.
What JEV decides
systemOne submits state and named questions and infers answer types from the questions.
logan-markewich
A self-hosted Jev-compatible service powered by GliFormer.
What JEV decides
Preserves the decision API while running the classifier locally.
ipenywis
A local open-weight port of Jev Ultrafast for Apple Silicon browsers.
What JEV decides
Uses Laya to choose bounded browser actions from page state.
usenotra
A product that turns work artifacts into publishable content with agent skill hooks.
What JEV decides
Uses skill-guided steps to decide what to extract and how to package content.
coldteadotai
A coding-agent rule layer for constraints that ordinary linters cannot express.
What JEV decides
Scores each agent turn against semantic rules and returns targeted corrections.
noperator
A command-line ranking tool that uses JEV to find relevant items in large collections.
What JEV decides
Scores candidates in batches and applies convergence rules before returning the highest-value subset.
OmniJev
A gallery of System One papers, open reproductions, and independent evaluations.
What JEV decides
Connects model implementations with research and evaluation evidence.
NiazMorshed2007
A local MCP code-quality reviewer returning structured scores to coding Agents.
What JEV decides
Jev scores correctness, complexity, tests and security; code ranks areas to improve.
typesafe-ai
Official TypeSafe Python SDK with synchronous and asynchronous clients for Jev System One, plus question and answer types.
What JEV decides
system_one sends context and choice, score or yes/no questions to the API, then parses answers by question name.
kitze
A browser extension using Jev to identify ads, promotions, and subscription popups and save reusable hiding rules.
What JEV decides
Evaluates candidate page elements before the extension applies local hiding rules.
fatwang2
A source-backed JEV directory plus a reusable JEV-only GitHub review workflow.
What JEV decides
Runs JEV over pull-request signals to produce review judgments in CI.
FBddcz
An embodied-agent evaluation stack comparing JEV with local and general-model decision policies.
What JEV decides
Offers legal actions as bounded choices, validates returned probabilities, and keeps execution under local policy.
Knuckles92
A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.
What JEV decides
Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.
vercel-labs
Vercel's AI SDK for Python with an experimental evaluate path that asks typed questions through typesafe-ai/jev.
What JEV decides
Batches Choice, Score, and Boolean questions against shared state via the AI Gateway evaluation protocol.
kunchenguid
A coding-agent skill/plugin that advises when to compact context to save tokens.
What JEV decides
Judges whether the session looks complete enough to compact safely.
vinilana
A gateway for inserting Jev decisions into Claude Code and Codex tool flows.
What JEV decides
Delegates bounded tool-choice judgments while the coding agent owns the broader task.
QuentinCody
Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.
What JEV decides
Assesses inputs such as test names, documentation claims and supporting evidence.
mmastrac
A DGX Spark container recipe for running DiffusionGemma NVFP4 structured decisions.
What JEV decides
Packages local diffusion decision serving so apps can query typed outcomes on-box.
BillionsBobby
A lightweight JEV router for models, tools, and subagents.
What JEV decides
Chooses a model, tool, or subagent from caller-supplied candidates.
lakeday-org
Semantic code linting that asks JEV / System One whether findings should fire.
What JEV decides
Scores lint candidates against project rules before reporting issues.
standardagents
A browser driving simulator where Jev chooses among locally generated paths and speeds.
What JEV decides
Jev reads road and traffic state and selects motion; geometry, collision prediction and braking remain local.
Michaelliv
A TypeSafe plugin exposing Jev decisions as callable actions in Runline Agent JavaScript.
What JEV decides
evaluate, choice, score and noul actions submit questions and retain answers and usage.
AgriciDaniel
A live SEO audit that combines crawl evidence with narrow Jev judgments.
What JEV decides
Evaluates semantic page checks after deterministic crawling and parsing.
hellogumbo
The source catalogue behind awesomejev.com, covering repos, integrations, demos, and research.
What JEV decides
Indexes the wider ecosystem while separating repositories, sites, and articles.
CTNicholas
A visual multiplayer builder for workflows that call Jev and text models.
What JEV decides
Runs configured Jev questions inside a user-defined workflow graph.
Yinsongxu
An adapter that turns local language models into JEV-compatible structured decision engines.
What JEV decides
Uses prefill-only binary inference to produce Choice, Score, and Noul probabilities.
tamaratran
A Claude Code plugin that trims long Bash output with TypeSafe JEV before the model sees it.
What JEV decides
Decides which output slices stay useful versus safe to drop under a token budget.
y0usaf
A Pi extension that flags tool risks before execution and checks output for secrets and failure types.
What JEV decides
Jev scores destructive actions, scope and output risks; configuration chooses warnings or confirmation.
Juspay
NeuroLink ships a TypeSafe provider and classifier-routing support for JEV.
What JEV decides
Validates typed decision requests, calls JEV directly or through a gateway, and normalizes answers for routing.
DevMortimer
Adds checks for project rules, out-of-scope actions, repeated failures, and completion claims to Pi Agents.
What JEV decides
Uses Jev to judge rule violations, irreversible actions, and task drift, feeding results back to the Agent.
wquguru
A reading-practice app that combines streaming ASR with per-word JEV judgments.
What JEV decides
Judges word matches, error classes, and sentence similarity from aligned text.
RomanSlack
A MuJoCo drone experiment deriving scene features from camera buffers for Jev tactical advice.
What JEV decides
Uses range sectors, obstacle heights and target state to choose maneuvers and assess risk or target loss.
hackclub
A Jev forwarding endpoint in the Hack Club AI proxy, using its authentication, limits and usage logging.
What JEV decides
Forwards authorized structured requests to TypeSafe and returns answers with usage accounting.
valentynkit
A TypeSafe JEV resource list centered on typed, confidence-aware decisions.
What JEV decides
Maps resources to Choice, Score, Noul, and integration patterns.
uehaj
Meaning-based grep with multilingual AND, OR, NOT, and probability thresholds.
What JEV decides
Scores whether each line satisfies a proposition, then applies grep controls locally.
shhivv
A fast computer-use action layer with a TypeSafe policy implementation.
What JEV decides
Selects the next allowed UI action from observed state while the local harness owns execution.
dbreunig
An agent skill for writing and improving programs that call JEV / System One.
What JEV decides
Advises how to frame state and questions so JEV returns usable typed answers.
ThinkFlowLab
An agent framework with interchangeable Jev, Laya, and Cua-S1 decision backends.
What JEV decides
Uses a selected decision backend to choose an action from task observations.
Promethe-us
A source-backed bilingual collection of JEV resources, projects, research, and operational updates.
What JEV decides
Separates official facts, author-reported experiments, and leads that still need verification.
kshetrajna12
A small open decision model that recreates the JEV/System One interface on Qwen.
What JEV decides
Returns calibrated probabilities for state plus typed questions.
danieljvdm
An Effect Agent TypeSafe decision provider for typed question sets and optional model selection.
What JEV decides
Jev answers probability, choice and score questions for application transitions or model selection.
allebee
An independent open-weight model for choice, score, and yes/no decisions.
What JEV decides
Answers bounded typed questions from local model weights.
ldbumble
An optional Jev judgment module in Taskuary for checking user-defined conditions on task state.
What JEV decides
Turns conditions into yes/no probability questions and returns local-threshold verdicts plus probabilities.
Devin-AXIS
A structured JEV decision plugin for DeepSeek Harness and compatible coding-agent hosts.
What JEV decides
Packages bounded questions as a service and returns typed results to the host harness.
walidboulanouar
A source-linked catalogue of shipped JEV demos, repositories, reported metrics, and model limits.
What JEV decides
Keeps shipped examples separate from unbuilt ideas and links each entry back to its original evidence.
Dicklesworthstone
A Rust CLI that ranks agent skills against live session context with JEV.
What JEV decides
Ranks candidate skills and abstains when confidence is below policy.
kraayenjon
A curated guide to JEV use cases, projects, SDKs, tools, and learning resources.
What JEV decides
Explains typed Choice, Score, and Noul patterns and links them to public ecosystem implementations.
devagrawal09
Bounded JEV workflows for coding agents with a dedicated adapter.
What JEV decides
Turns review and coding checkpoints into typed JEV judgments.
aowang-ai
A live Hyperliquid trading agent with JEV as a bounded decision layer.
What JEV decides
Chooses among configured trading actions from market and position state.
Heman10x-NGU
An independent ModernBERT-based typed-decision model with calibration experiments.
What JEV decides
Produces bounded choice and score answers from an open model.
supercorp-ai
A code-quality and coverage tool that uses JEV for bounded quality checks.
What JEV decides
Scores whether generated tests and coverage changes meet configured quality criteria.
vinilana
Agent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.
What JEV decides
Employs Jev for two-stage discrete pruning over tool catalogs, narrowing extensive tool lists down to relevant candidates in milliseconds.
mrnugget
Fish-style Zsh history suggestion tool ranked by Jev, ordering candidate commands from local history based on context.
What JEV decides
Packages current command input and historical candidates into a Jev request, ranking the most plausible command for inline suggestion.
openqa-cn
A browser skill that indexes page controls for bounded Jev navigation.
What JEV decides
Selects a visible control and action, then checks the resulting page state.
daseinlabs
An open JEV-style implementation with custom fine-tuning support.
What JEV decides
Runs bounded decision questions on a locally trainable model.
virajbhartiya
A side-by-side game harness comparing local Laya with hosted Jev.
What JEV decides
Each model chooses a bounded action from the same game state.
SiliconLabAI
An open-source JEV-compatible implementation for typed decision requests.
What JEV decides
Accepts bounded question schemas and returns structured answers through a compatible interface.
jexp
A Neo4j graph navigator that uses JEV to classify the next relationship.
What JEV decides
Chooses the next graph relationship from the current node and query goal.
timrogers
A CLI and MCP client for benefit claims with optional JEV receipt classification.
What JEV decides
Selects the benefit and receipt category, falling back when confidence is low.
agent-labs-dev
A browser agent that indexes page controls and lets Jev pick the next action while an LLM plans and reads.
What JEV decides
Issues Choice and Noul questions over candidate DOM actions and verifies answer claims against quoted page text.
GhalebDweikat
A recoverable context filter for Claude Code tool outputs.
What JEV decides
Judges whether each output block is needed for the current task before passing it on.
mmastrac
A DiffusionGemma server exposing a Jev-style structured decision endpoint.
What JEV decides
Maps typed questions to bounded answers through a local model server.
savka777
A macOS computer-use harness that drives Accessibility controls without a vision model.
What JEV decides
Chooses a visible accessibility element and the next allowed action.
w3cj
A tool-using chat interface where JEV chooses only from code-supplied reply and tool options.
What JEV decides
Selects tools, arguments, and reply fragments from bounded pools.
kyle-pena-nlp
An experiment that assembles chat text from repeated typed Jev choices.
What JEV decides
Chooses the next character or stop option from a fixed alphabet.
trungdq88
YouTube extension detecting sponsored segments from live audio and transcripts using Jev, skipping promotional blocks automatically.
What JEV decides
Inspects transcript segments with Jev to identify sponsor reads while browser code handles playback timeline skipping.
pithings
A small TypeScript client for asking Jev multiple typed questions about the same data.
What JEV decides
Combines yes/no, Choice and Score questions and maps responses to typed values.
rokcso
An X/Twitter filtering extension using local rules by default, with optional Jev checks for unmatched replies.
What JEV decides
When experimental AI is enabled, Jev evaluates replies missed by rules and local thresholds decide whether to hide them.
ellipsis-dev
A codebase finder that sends Jev-guided walkers through file and folder names.
What JEV decides
Scores likely paths and allocates walkers toward relevant files.
AkashPriyadarshii
A Rust pipeline that uses Jev to screen candidate dataset rows.
What JEV decides
Judges record quality against configured criteria before retaining it.
nassim-arifette
A semantic code-search tool that scores repository fragments with Jev.
What JEV decides
Judges which eligible code excerpts match a developer's question.
can1357
Semantic grep for live code trees: describe what you need, get files and original line ranges without building an index.
What JEV decides
JEV scores folders, files, and bounded code passages; local search strategies manage budgets, thresholds, and fallbacks.
fstandhartinger
A reproducible benchmark comparing JEV with open decision models, classifiers, and rerankers.
What JEV decides
Uses a dedicated TypeSafe adapter to run the same bounded tasks and preserve model, latency, token, and cost evidence.
giuliosmall
A pre-alpha PostgreSQL C extension for calling Jev from SQL for classification, yes/no judgments, and scoring.
What JEV decides
Converts SQL input into System One requests and returns answers through database functions.
ChetasLua
Creates edited videos with score meters by asking Jev to rate transcript sentences against selected rubrics.
What JEV decides
Scores transcript sentences with preset questions and scales for meters placed on the video timeline.
AkashPriyadarshii
A Rust SEO and GEO CLI with optional Jev judgments alongside deterministic checks.
What JEV decides
Judges page-level semantic findings after the crawler collects evidence.
irfndi
An autonomous liquidity agent that uses JEV inside its rebalancing decision service.
What JEV decides
Evaluates bounded liquidity actions from pool, risk, and position state.
nekuda-ai
A browser-agent benchmark harness with frozen JEV experiments across accessibility and WebMCP interfaces.
What JEV decides
Combines JEV action selection with a bounded browser executor and records drift, cost, and failure evidence.
AppitStudio
A curated JEV resource list with runnable typed-decision examples.
What JEV decides
Connects learning resources to concrete Choice, Score, and Noul examples.
Bodila51
A JEV decision layer for Grok Bot with usage gates and skill templates.
What JEV decides
Routes bounded bot decisions before more expensive generation runs.
Ying-Kai-Liao
A browser automation library, CLI, and MCP server pairing LLM plans with JEV actions.
What JEV decides
Chooses the next browser action and target from the current page observation.
1Panel-dev
A self-hosted API and web interface for Laya typed decisions.
What JEV decides
Maps Jev-compatible request shapes to local Laya predictions.
mizchi
A semantic code linter that batches repository findings through a zero-dependency JEV client.
What JEV decides
Asks many bounded questions against one file state, validates probabilities, and splits requests when token limits are reached.
yikangy873-gif
A Codex Computer Use plugin for bounded browser and macOS actions.
What JEV decides
Selects one compatible action and target from the current accessibility state.
CaptainCore
Jev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.
What JEV decides
Sends scan rules, matched snippets, and file context to Jev to assess likely true positives and suggested handling.
realZachi
An experimental Chrome extension that asks Jev whether candidate DOM elements are ads, then highlights or removes them.
What JEV decides
Batches element text, labels, and link information into Noul questions and applies a threshold.
nidhi-singh02
A CLI that routes tasks to coding agents, models, and reasoning effort with JEV.
What JEV decides
Ranks eligible routes and effort levels after local safety and quota checks.
sharziki
A Unix CLI for typed Jev judgments in text and JSONL pipelines.
What JEV decides
Returns a predicate, route, or score that shell policy can consume.
IAmUnbounded
A context cleaner that asks JEV which history to retain, truncate, or drop.
What JEV decides
Scores conversation items for retention while preserving kept content verbatim.
iamaamir
A provider-neutral TypeScript runtime for typed decisions, including Jev-compatible HTTP endpoints.
What JEV decides
Builds bounded questions and normalizes provider responses for application code.
yzfly
A Chinese JEV ecosystem guide with curated projects, practical tutorials, pricing, and independent caveats.
What JEV decides
Explains when typed decisions fit, documents counterexamples, and groups public implementations by use case.
RenaGao
A data-curation workbench with an optional Jev screening provider.
What JEV decides
Scores candidate training records before local filtering and review.
achimala
An experimental painting app that turns Jev probability distributions into pixels.
What JEV decides
Scores a fixed color palette for each canvas position before rendering.
burnigtm
An MCP server that exposes typed Jev decisions to coding agents.
What JEV decides
Chooses a prepared tool call or next coding step from bounded options.
andududu
A local proxy that visualizes Jev requests and responses as they happen.
What JEV decides
Shows submitted questions, returned probabilities, and call history without judging itself.
bnsd55
A local Apple Silicon decision layer that scores constrained fields from MLX logits and speaks System One HTTP.
What JEV decides
Accepts POST /v1/systemone payloads, maps Noul/Choice/Score questions to one-pass schema scoring, and returns probabilities.
EliaAlberti
A Claude Code plugin that selects which standing rules apply to a prompt.
What JEV decides
Judges each rule or document against the current task before adding context.
wobsoriano
An Oxlint plugin that evaluates semantic lint rules with JEV.
What JEV decides
Returns yes-probabilities for configured semantic findings before reporting them.
RJMSWD
A local Qwen experiment for closed-set visual decisions.
What JEV decides
Chooses one option for an image and question without calling the Jev API.
bilune
A UI experiment that uses Jev to select predefined visual-system options.
What JEV decides
Chooses bounded design settings before local code renders the interface.
Aayan-DEV
A search app that re-tags YC companies with Jev before ranking results.
What JEV decides
Judges whether each company matches the requested attributes and evidence.
ikermoel
An open System One-style decider that packs typed questions into one forward pass over local open models.
What JEV decides
Scores Choice options from label logits without generating text, with optional calibration helpers.
qkal
Claude Code and Codex hooks that keep an append-only ledger and optionally ask Jev Noul questions for advisory checks.
What JEV decides
Posts Noul questions to api.typesafe.ai/v1/systemone and only uses high-confidence answers to relax a stop gate.
AboveColin
A Home Assistant integration that turns typed Jev questions about house state into sensors and automation actions.
What JEV decides
Builds System One payloads via jevclient and updates entities from Noul, Choice, and Score answers under a token budget.
skeptrunedev
A local recruiting workspace built on bounded browser decisions.
What JEV decides
Chooses profile-navigation and title-screening steps while retaining source evidence.
BeatAPI · Free JEV API
JEV is live on BeatAPI. Call jev-1.14 on POST /v1/systemone; jev-1.13 keeps working with the same platform key.