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.

Community directory snapshot 2026-09-23 Review method 2026 ecosystem report

1197open projects

23project categories

640Kcombined GitHub stars

296fixed-source reviews

HOT / 10

Popular Jev projects

Ten widely followed projects spanning browser automation, context compaction, trading, official skills, computer use, review, orchestration, and data.

01 jev-ultrafast ★ 18K 02 fast-jev-compaction ★ 6,358 03 jev-trader ★ 2,087 04 TypeSafe agent skills ★ 1,693 05 jev-desktop ★ 1,528 06 typesafe-computer-use ★ 848 07 Jev Review ★ 558 08 foreman ★ 520 09 hermes-jev-skills ★ 611 10 pg-jev ★ 316

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 1–24 of 1197 Some public source has been reviewed; inclusion is not a performance or safety endorsement

langchain

langchain-ai

001

SDK & Integrations MIT source reviewed

An optional Jev classifier integration for Python LangChain workflows.

JEV · Decision point

Submits binary, categorical and ordered-score questions and returns typed answers with probabilities.

Adds a classification step that can participate in existing LangChain pipelines.

multilanguage-sdkclassification-rankingagents

ai-hedge-fund

virattt

002

Domain & Vertical Tools MIT source reviewed

An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.

JEV · Decision point

Converts strategy questions to System One requests and normalizes native answers to the project’s result format.

Allows Jev or other model backends to be used in the same research workflow.

finance-quanttyped-decisions

litellm

BerriAI

003

Routing & Cost Optimization source reviewed

LiteLLM can use Jev to classify requests for its complexity-based model router.

JEV · Decision point

Maps requests to configured complexity classes that drive backend routing.

Makes the complexity judgment behind routing inspectable.

llm-routing-costmultilanguage-sdk

oh-my-pi

can1357

004

Routing & Cost Optimization MIT source reviewed

Oh My Pi includes an optional TypeSafe judgment provider for bounded decisions in coding-agent workflows.

JEV · Decision point

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

Adds a replaceable judgment provider to existing agent workflows.

coding-agentsmultilanguage-sdktyped-decisions

jev-model-router

davila7

005

Routing & Cost Optimization MIT source reviewed

A community Claude Code Templates mod that uses Jev to suggest subagent models and reasoning levels.

JEV · Decision point

Evaluates task tier, reasoning needs and production risk; local policy maps results to invocation settings.

Makes routing rules and per-request choices explicit and configurable.

llm-routing-costcoding-agentsanthropic

composio

ComposioHQ

006

SDK & Decision Frameworks MIT source reviewed

An optional TypeSafe provider for Composio that uses Jev to choose among tools and bounded argument options.

JEV · Decision point

Turns tool or action conditions into structured questions and passes Jev answers to local invocation logic.

Adds structured judgments to existing tool interfaces.

multilanguage-sdkllm-routing-costtyped-decisions

ai

vercel

007

SDK & Decision Frameworks source reviewed

The TypeSafe provider in AI SDK lets TypeScript applications call Jev through the shared evaluate interface.

JEV · Decision point

Maps choice, score, and yes/no questions to TypeSafe System One requests and parses typed results.

Reuses a common evaluation interface within AI SDK applications.

multilanguage-sdktyped-decisionsanthropic

cua

trycua

008

Browser & OS Action MIT source reviewed

Cua’s preview jev-use example pairs Driver observation and execution with bounded Jev browser-action choices.

JEV · Decision point

Reads DOM or supported visual-region descriptions and returns a supplied candidate action ID.

Provides Python and TypeScript loops with separate offline and live checks.

browser-automationtyped-decisionscomputer-use

pydantic-ai

pydantic

009

SDK & Integrations MIT source reviewed

An optional TypeSafe provider and Jev model integration for Pydantic AI.

JEV · Decision point

Converts supported structured output fields into typed Jev questions and maps answers back to the output model.

Lets supported classification outputs use the existing Pydantic AI interface.

multilanguage-sdktyped-decisionsagent-framework

eliza

elizaOS

010

SDK & Decision Frameworks MIT source reviewed

An optional TypeSafe HTTP adapter in Eliza’s source, not registered with the Agent runtime by default.

JEV · Decision point

Only an explicit systemOne call sends state and questions, returning validated typed answers.

Provides a reusable server-side module; its presence is not evidence of deployed Jev adoption.

multilanguage-sdktyped-decisionsagent

jev-ultrafast

browser-use

011

Browser & OS Action MIT source reviewed

A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.

JEV · Decision point

Chooses an action and its matching DOM element in one request; a text model generates input text.

Separates UI choices, text generation, and browser execution so each step can be inspected.

browser-automationtyped-decisions

langchainjs

langchain-ai

012

SDK & Decision Frameworks MIT source reviewed

An optional LangChain.js TypeSafeClassifier integration for sending state and predefined questions to Jev.

JEV · Decision point

Uses invoke to call TypeSafe and parse choice, noul, score and probability fields.

Adds typed decisions to LangChain workflows without treating Jev as a chat generator.

multilanguage-sdkclassification-ranking

json-render

vercel-labs

013

Creative Tools Apache-2.0 source reviewed

A Jev UI-composition experiment inside the json-render website that selects from predefined component and property options.

JEV · Decision point

Evaluates component configurations through Vercel AI Gateway, then composeSpec assembles the UI specification.

Provides an inspectable composition path alongside token-by-token JSON generation.

creative-multimediatyped-decisions

openchamber

014

Routing & Cost Optimization MIT source reviewed

OpenChamber’s optional automatic model router uses Jev to classify a message before selecting a configured model and reasoning level.

JEV · Decision point

Jev selects a task category; local category mappings determine the model configuration.

Keeps routing categories and their model assignments explicit.

llm-routing-costcoding-agentsagentic-engineering

rig-typesafeai

0xPlaygrounds

015

SDK & Decision Frameworks MIT source reviewed

An experimental TypeSafe crate in Rig for expressing Jev questions and answers with Rust types.

JEV · Decision point

Sends application state and questions to Jev and parses Choice, Score or Noul answers.

Reuses field layouts between questions and answers and validates answers against questions.

multilanguage-sdktyped-decisionsrust

deep-searcher

zilliztech

016

Data & Search Apache-2.0

Open Source Deep Research alternative with Jev search-stopping evaluation.

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.

search-retrievalevaluation-benchmarks

GPTCache

zilliztech

017

Data & Search MIT

Semantic cache with a Jev evaluator that uses Noul judgments to check whether a cached response can serve an incoming request.

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.

search-retrievalclassification-ranking

firstmate

kunchenguid

018

Routing & Cost Optimization MIT source reviewed

Firstmate can optionally use Jev to match task briefs to dispatch rules before local policy chooses an Agent configuration.

JEV · Decision point

Sends the task brief and candidate rules to Jev, then resolves execution profiles with confidence and local conditions.

Separates semantic matching from the final dispatch policy.

llm-routing-costcoding-agents

fast-jev-compaction

tamaratran

019

Context GC & Filter MIT source reviewed

Prunes old tool calls and outputs for Claude Code while retaining surviving text verbatim.

JEV · Decision point

Separately judges whether a tool call and its full output are still needed; code keeps, truncates or drops them.

Avoids rewriting paths, commands and errors into a new summary.

context-compactioncoding-agents

eve

vercel

020

MCP & Integrations

Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.

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.

agentgateway

021

Security & Guardrails Apache-2.0 source reviewed

A Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.

JEV · Decision point

Jev scores jailbreaks, harmful content and secret disclosure; thresholds or evaluation errors reject requests.

Demonstrates gateway integration, not guaranteed prevention of all attacks.

security-guardrailsmultilanguage-sdkagents

latitude-llm

latitude-dev

022

Evaluation & Observability MIT source reviewed

Latitude includes an optional Jev preclassifier for conversation checks and their selection records.

JEV · Decision point

Judges which checks apply and can add checks when thresholds and rate limits permit.

Records models, thresholds, latency and selection reasons alongside the baseline.

evaluation-benchmarksvoice-conversation

kev

jaredpalmer

023

High-Frequency & Simulation Apache-2.0 source reviewed

Tiny Jev-like decision head built atop Qwen2.5-0.5B that can be trained and run locally on Apple Silicon MacBooks.

JEV · Decision point

Attaches a parallel decision head to an open 0.5B model to answer discrete questions directly from token activations.

Runs entirely offline on edge hardware with minimal memory footprint, offering an accessible base for custom judgment modeling.

evaluation-benchmarkstyped-decisions

SemIf

TheoLeeCJ

024

Evaluation & Observability

Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

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.