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 313–336 of 853 Some public source has been reviewed; inclusion is not a performance or safety endorsement

LegalForecastBench

johnhughes3

313

Evaluation & Observability

LegalForecast-MTD benchmark alpha and official evaluation workflows

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.

pi-jev-guard

Reindeer-AI

314

Security & Guardrails

Check Pi code edits against repository Markdown rules with TypeSafe Jev

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.

security-guardrailstyped-decisions

questions

nitoba

315

SDK & Decision Frameworks MIT source reviewed

A TypeScript decision library that asks typed questions via Zod or native batches, defaulting to TypeSafe Jev, with optional Vercel or generative adapters.

JEV · Decision point

Posts state plus Choice, Score, or Noul questions to `/v1/systemone`, defaulting to jev-latest.

The same question definitions can target TypeSafe, Vercel, or a generative backend without rewriting callers.

multilanguage-sdktyped-decisions

riff

scale-venture-partners

316

Agent Tooling

A small, fast prose linter: ruff-style rule codes for writing, backed by TypeSafe's Jev model

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.

sift (bohutang)

bohutang

317

Browser & OS Action

Chrome extension that labels every post on X (Substance · Humor · Chit-chat · Promo · Junk · AI-written) with TypeSafe Jev, and hides the ones you don't want.

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.

typesafeai-dotnet-sdk

saibimajdi

318

SDK & Decision Frameworks MIT source reviewed

Community .NET SDK for TypeSafe AI and Jev, providing asynchronous typed evaluation for Choice, Score, and Noul primitives.

JEV · Decision point

Wraps System One API endpoints in TypeSafeClient to issue parallel question evaluations and parse responses into immutable C# records.

Brings native Jev decision primitives to the .NET ecosystem with dependency injection integration and configurable retry policies.

multilanguage-sdktyped-decisionsai

bicameral

AbdelStark

319

Agent Tooling

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

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.

claude-jev

buchmark

320

Codebase & Graph Pathfinding MIT source reviewed

Adds Jev checks to Claude Code review findings, debugging hypotheses, design options and search results.

JEV · Decision point

Scores candidate defects, explanations or options against preset questions and local policies.

Keeps a second judgment and its probabilities available for comparison.

coding-agentsast-code-graphevaluation-benchmarks

daf-jev

docxology

321

SDK & Decision Frameworks MIT source reviewed

A Python toolkit for Jev requests, batch evaluation, calibration and MCP access.

JEV · Decision point

Builds Noul, Choice and Score questions, then combines returned probabilities through local functions.

Reuses request, failure-recording and evaluation interfaces across experiments.

multilanguage-sdkevaluation-benchmarksmcp-integrations

diffjury

raihankhan-rk

322

Agent Tooling

DiffJury — TypeSafe Jev PR risk router + code review coach

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.

jev_antispam_bot

backmeupplz

323

Domain & Vertical Tools

Minimal grammY Telegram anti-spam bot powered by TypeSafe Jev

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.

jev-align

caiovicentino

324

Evaluation & Observability

Calibrated alignment verifier for LLM responses and agent plans — powered by Jev

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.

jev-browser

tontoko

325

Browser & OS Action Apache-2.0 source reviewed

Playwright browser automation with Jev decisions through a shared CLI, MCP server and TypeScript SDK.

JEV · Decision point

Jev chooses actions, matches form fields or extracts structured content from page observations; Playwright executes.

Supports persistent sessions and UI readback, which does not by itself prove database persistence.

browser-automationmcp-integrationsmultilanguage-sdk

jev-browser (vinilana)

vinilana

326

Browser & OS Action

Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.

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.

jev-grug

mkotlikov

327

Domain & Vertical Tools

Helping JEV speak <3

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.

jev-mcp

rashedInt32

328

MCP & Integrations MIT source reviewed

An MCP server and Claude Code plugin for Jev classification, scoring, checks and batched questions.

JEV · Decision point

Calls TypeSafe with Choice, Score and Noul questions and returns structured answers.

Makes the typed decision primitives available to MCP clients.

mcp-integrationscoding-agentsclassification-ranking

jev-model-tokengate

Thanh-Mathieu95

329

Security & Guardrails MIT

An OpenAI-compatible proxy that sits between your LLM and your users. It evaluates each sliding window of tokens **while the response is still streaming** and cuts the stream **before** a violating token can reach the screen.

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.

security-guardrailstyped-decisions

jev-plays-pokemon-red

valentynkit

330

Decision Tools MIT

Pokemon Red on PyBoy where Python owns the route and the arithmetic, and Jev chooses only among legal actions at actual branches.

JEV · Decision point

A Choice over legal actions at each branch; battle turns also ask Noul faints_this_turn and should_flee; failures take the code default.

The model only picks among code-proven legal moves; a failed call never loosens the script.

typed-decisionsclassification-ranking

jev-pr-labeler

1jehuang

331

Domain & Vertical Tools

Semantic GitHub PR labels using Jev's typed decisions, with conceptual scope instead of line counts

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.

jev-pref

doeixd

332

Evaluation & Observability MIT source reviewed

Turns AGENTS.md preferences into rules checked by Jev against hunks, staged files or PRs.

JEV · Decision point

Jev classifies change evidence against configured rules; code maps answers to review outcomes.

Feeds semantic-rule findings to coding Agents without replacing type checks, tests or security audits.

coding-agentscli-git-gatesevaluation-benchmarks

jev-rerank-bench

anessbelbati

333

Evaluation & Observability MIT source reviewed

Compares Jev, dedicated rerankers and chat models on the same retrieved passages.

JEV · Decision point

Ranks candidate passages with Choice, Noul and rubric scores, then computes retrieval metrics.

Publishes raw responses, scoring code and per-dataset results for inspection.

evaluation-benchmarkssearch-retrievalclassification-ranking

jev-search-rerank-eval

zhuyansen

334

Data & Search MIT source reviewed

Retrieval evaluation system measuring Jev reranking against lexical, embedding, and fusion baselines across 9,831 query-document pairs.

JEV · Decision point

Invokes Jev judges to grade multi-level relevance on bilingual queries, evaluating ranking metrics and judge-circularity effects.

Provides rigorous empirical evidence comparing discrete judgment rerankers against vector search in multilingual discovery contexts.

search-retrievalevaluation-benchmarksclassification-ranking

jev-spring-boot-starter

danvega

335

Demos & Playgrounds

A simple Spring Boot 4 starter for TypeSafe Jev using Spring MVC and RestClient

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.

jev-tool-permissions

NicolasMontone

336

Security & Guardrails source reviewed

Adds tool-call approval and tool-list pruning to the Vercel AI SDK.

JEV · Decision point

Deterministic rules run first; Jev assesses remaining call risks and tool relevance for threshold-based handling.

Approval-call failures request human review; model judgments cannot guarantee detection of every risk.

security-guardrailsmultilanguage-sdkllm-routing-cost