OPEN-SOURCE PROJECT DIRECTORY

Jev project radar

Browse community-built Jev projects, see what they solve and where Jev makes a decision, then open the repository and reviewed source links.

Data imported from AgentBuff Awesome Jev snapshot 2026-09-21 Review method

853open projects

23project categories

587Kcombined GitHub stars

295fixed-source reviews

01 / DIRECTORY

Browse Jev projects

Search by project, author, use, or tag, then filter by category or activity. Open project details to see how it uses Jev and review its source links.

Showing 49–72 of 853 Some public source has been reviewed; inclusion is not a performance or safety endorsement

instructor-php

cognesy

049

SDK & Decision Frameworks MIT source reviewed

A TypeSafe Decision driver within Instructor PHP’s Polyglot module.

JEV · Decision point

Converts application state and typed questions into Jev requests and maps responses to PHP decision objects.

Lets PHP applications use Jev through a shared Decision interface.

multilanguage-sdktyped-decisionsagents

jev-search

superagents-lab

050

Data & Search MIT source reviewed

Searches the web with Jev choosing sources and time ranges, then ranking returned links.

JEV · Decision point

Judges search intent, source and time settings, and relevance of individual results.

Keeps links, snippets, editable filters and source-failure warnings visible.

search-retrievalclassification-ranking

typesafe-mario

fhshaik

051

High-Frequency & Simulation source reviewed

An experimental NES Mario controller that gives Jev structured emulator RAM and telemetry instead of screenshots.

JEV · Decision point

Reads motion, enemies, terrain and recent controls, then selects a predefined legal action.

Records model state and actions without screenshot input.

games-simulationtyped-decisions

tax-doc-classifier

kyotofin

052

Domain & Vertical Tools Apache-2.0 source reviewed

A tax-document page classifier that uses Jev to choose from predefined IRS form and page categories.

JEV · Decision point

Extracts PDF page text and sends it to Jev for form type, page type, and confidence.

Connects a fixed form catalog to per-page classifications for downstream document workflows.

domain-workflowsclassification-ranking

hermes-jev-skills

kerpopule

053

Routing & Cost Optimization MIT

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

JEV · Decision point

Jev returns a structured decision for the local program; consult the source for the exact decision policy.

Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.

llm-routing-costtyped-decisions

mobile-jev

droidrun

054

Browser & OS Action MIT source reviewed

Controls an Android phone through Mobilerun, with a web studio and CLI showing Jev decisions.

JEV · Decision point

Chooses apps, controls and next actions from phone state; Mobilerun executes them.

Records action traces and request latency for inspection.

desktop-ostyped-decisions

orchestkit

yonatangross

055

CLI & Pipelines MIT source reviewed

OrchestKit can optionally use Jev to classify coding sessions and set their colors when confidence meets a threshold.

JEV · Decision point

Classifies the first task prompt and branch state by work type; local policy accepts the result or falls back.

Distinguishes sessions by work type and supports a shadow comparison mode.

coding-agentsclassification-rankingagent-orchestration

jev-browser-use

wy-coliney

056

Browser & OS Action MIT source reviewed

A Skill for Codex browser workflows: Jev chooses navigation, clicks, and scrolling while Codex handles text input and final checks.

JEV · Decision point

Sends page state and permitted candidates to Jev; the existing browser connection executes the actions.

Separates repetitive page choices into decision steps while reusing the browser connection.

browser-automationcoding-agents

jev-router

gargpratyush

057

Routing & Cost Optimization MIT source reviewed

A Claude Code and CLI proxy that asks Jev to score task complexity and pick a model from the account’s available set.

JEV · Decision point

Scores task, reasoning, and tool complexity, then chooses among the exact models the account can run; failures keep the current model.

Makes model choice an inspectable closed-set decision, and never blocks a prompt when Jev is down.

llm-routing-costcoding-agents

pg-jev

realZachi

058

Data & Search source reviewed

Adds natural-language filtering, classification, and ranking of rows to PostgreSQL queries.

JEV · Decision point

Sends row content to Jev for a match decision, category, or score used by SQL conditions and ordering.

Combines semantic conditions with existing SQL and reuses cached results.

database-vectorclassification-ranking

openai-scala-client

cequence-io

059

SDK & Decision Frameworks MIT source reviewed

A dedicated TypeSafe module in a Scala client that supports multiple AI providers.

JEV · Decision point

Sends shared state and typed questions to Jev and parses structured answers.

Lets Scala applications reuse provider transport and error-handling conventions.

multilanguage-sdktyped-decisionsanthropic

1. Evaluates the configured dataset and measures uncertainty. 2. Selects ambiguous rows plus a random audit sample for you to label. 3. Uses your accumulated labels and optional rationales to run GEPA. 4. Shows the score, certainty change, and proposed definition diff. 5. Lets you accept, reject, rewind, or resume later.

JEV · Decision point

Jev returns a structured decision for the local program; consult the source for the exact decision policy.

Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.

cli-git-gatestyped-decisions

pi-fabric

monotykamary

061

SDK & Decision Frameworks MIT source reviewed

Pi’s programmable runtime includes an optional Jev loop for observing state, making decisions and running bounded actions.

JEV · Decision point

Programmed questions feed Jev judgments into local action logic under runtime budgets.

Keeps observation, judgment and execution steps in a reusable program.

coding-agentsmcp-integrationstyped-decisions

awesome-jev

cobanov

062

Community Lists

A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.

BASIC LISTING

This listing includes an overview and project link; a reviewed Jev decision point is not yet available.

Open the project link to review its source material and implementation.

openjev

razorback16

063

SDK & Decision Frameworks Apache-2.0 source reviewed

An independent System One decision server compatible with Jev’s API, running an open DiffusionGemma model.

JEV · Decision point

Accepts Jev-style state and Noul, Choice, and Score questions, producing probabilities with a local model.

Lets existing TypeSafe SDKs connect to a self-hosted compatible service.

multilanguage-sdktyped-decisions

skillbox

kitze

064

Routing & Cost Optimization MIT source reviewed

A self-hosted, versioned Agent skills library with optional Jev recommendations.

JEV · Decision point

Jev scores task relevance among skills the client is allowed to access.

Suggests relevant skills while retaining the library’s client access scope.

llm-routing-costmcp-integrations

jev-browser

jkudish

065

Browser & OS Action MIT source reviewed

Drives a browser from a task and URL, returning the final page, screenshot and action trace.

JEV · Decision point

Chooses DOM actions and judges goal completion or stalled progress; a separate model can supply typed text.

Records proposed actions, execution and stop reasons for inspection.

browser-automationtyped-decisions

notra

usenotra

066

Domain & Vertical Tools

Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions.

BASIC LISTING

This listing includes an overview and project link; a reviewed Jev decision point is not yet available.

Open the project link to review its source material and implementation.

typesafe-sdk-js

typesafe-ai

067

SDK & Decision Frameworks MIT source reviewed

The JavaScript and TypeScript SDK published by TypeSafe, with typed Jev requests and answers.

JEV · Decision point

systemOne submits state and named questions and infers answer types from the questions.

Includes ESM, CommonJS and TypeScript declarations for application integration.

multilanguage-sdktyped-decisions

jev-review

NiazMorshed2007

068

Evaluation & Observability MIT source reviewed

A local MCP code-quality reviewer returning structured scores to coding Agents.

JEV · Decision point

Jev scores correctness, complexity, tests and security; code ranks areas to improve.

Compares scores across checkpoints while leaving code changes to the primary Agent.

coding-agentsmcp-integrationsevaluation-benchmarks

OpenWhisper

Knuckles92

069

Voice & Conversation MIT source reviewed

A dictation and meeting-notes app with optional Jev checks for topic changes, note-taker instructions and sensitive text.

JEV · Decision point

Makes bounded transcript judgments for checkpoints, note-taking actions or screening before remote text cleanup.

Keeps model probabilities separate from local thresholds, switches and failure fallbacks.

voice-conversationsecurity-guardrailsclassification-ranking

System One adapter (Python)

typesafe-ai

070

Official

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

BASIC LISTING

This listing includes an overview and project link; a reviewed Jev decision point is not yet available.

Open the project link to review its source material and implementation.

interlinked-cli

QuentinCody

071

Security & Guardrails MIT source reviewed

Interlinked adds optional Jev judgments and evidence checks to local coding-agent checks.

JEV · Decision point

Assesses inputs such as test names, documentation claims and supporting evidence.

Keeps model advice distinct from deterministic rules and records checks.

coding-agentssecurity-guardrailscli-git-gates

jev-voice-browser

moritzkremb

072

Browser & OS Action MIT source reviewed

Controls a Playwright browser by sending incremental speech transcripts to Jev.

JEV · Decision point

Chooses intent, elements, URLs or verbatim spans and judges command completeness and sensitive actions.

Shows probabilities, actions and request timing during voice interaction.

browser-automationvoice-conversation