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 529–552 of 853 Some public source has been reviewed; inclusion is not a performance or safety endorsement

jev_projects

X0EF

529

Demos & Playgrounds

list of projects that use typesafe's 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-agent-failure-benchmark

TokenTrim

530

Evaluation & Observability Apache-2.0 source reviewed

A benchmark using Jev to attribute multi-Agent failures to an Agent, step and error type.

JEV · Decision point

Builds candidate sets from traces and submits three choice questions.

Provides evaluation scripts and author results; some baselines generate answers while Jev selects candidates.

evaluation-benchmarksclassification-ranking

jev-audio-beeper

santos-sanz

531

Domain & Vertical Tools

Low-latency audio censorship POC using Jev typed decisions and ffmpeg.

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.

What your last session knew, scored against what this one is doing. MCP server: a per-project ledger written as things happen, recalled per task with TypeSafe's Jev evaluation model via Vercel AI Gateway.

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-chess

hemanth

533

Evaluation & Observability

Chess moves, evaluations, persona opponents, and game classification with TypeSafe AI System One

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-cloud-quiz

minorun365

534

Demos & Playgrounds

三大クラウドの機能名を、TypeSafe AI の System One モデル Jev が確率つきで判定するデモ

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-context

zbush

535

Context GC & Filter MIT source reviewed

A Codex search plugin that filters ripgrep passages through Jev before returning relevant code.

JEV · Decision point

Judges passage relevance and withholds No and Unknown results.

Records paired payloads for measuring returned text under a named tokenizer.

context-compactioncoding-agentssearch-retrieval

jev-engineering

eugeniughelbur

536

Agent Tooling

Decision layer for coding agents: deterministic rules before any model call, then one Jev request, as a Claude Code PreToolUse hook, an MCP server, a loopback service and a team policy that personal overrides can tighten but not loosen. Ships the 300-call injection kit behind its own numbers.

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-eval

4esv

537

Evaluation & Observability source reviewed

Compares Jev and OpenRouter models on labeled tasks for accuracy, calibration, latency and cost.

JEV · Decision point

Collects judgments on matched tasks and computes confidence intervals and repeat-input stability.

Publishes data processing, runner and statistics code with model-specific results.

evaluation-benchmarksclassification-ranking

jev-flash-review

TheBous

538

Evaluation & Observability source reviewed

An MCP review engine that evaluates Agent-supplied diffs against explicit rules.

JEV · Decision point

Jev checks the diff, selects evidence from actual hunks and adjudicates candidate findings.

The caller supplies diffs and task boundaries; the engine does not scan the repository itself.

coding-agentsmcp-integrationsevaluation-benchmarks

jev-freeform

kesku

539

Evaluation & Observability

An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice

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-git

AkashPriyadarshii

540

Agent Tooling

Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI 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-go

guillemus

541

SDK & Decision Frameworks source reviewed

A small unofficial Go SDK for Jev calls and model listing.

JEV · Decision point

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

Packages requests and response parsing for typed decisions in applications.

multilanguage-sdktyped-decisions

jev-gomoku

XieChengYuan

542

Evaluation & Observability source reviewed

A nine-board, 15×15 Gomoku workbench comparing how two Jev players respond to different input representations.

JEV · Decision point

Jev chooses from locally generated move candidates while the experiment varies board and tactical information.

Supports labeled replays and bring-your-own-key live games with per-move records.

games-simulationevaluation-benchmarks

jev-got

phureewat29

543

Creative Tools source reviewed

A Game of Thrones text-adventure demo where a language model writes the story and Jev labels the scene.

JEV · Decision point

Classifies location, narrative beat, mood, danger and whether text remains in fiction.

Uses explicit scene state to drive backgrounds, music and the next turn.

creative-multimediagames-simulationclassification-ranking

jev-issue-radar

Patrick-SCH03

544

Domain & Vertical Tools MIT

Jev Issue Radar is a read-only dashboard for GitHub duplicate-issue triage. It retrieves likely candidates, asks Jev whether each pair is duplicate, related, distinct, or insufficiently documented, and shows selected passages from both original reports for a maintainer to review.

JEV · Decision point

The app never closes issues, posts comments, or changes labels. Retrieval is currently lexical and bounded to a recent-item scan; this limitation is explicit in the UI and README.

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

domain-workflowssearch-retrievalclassification-ranking

jev-labs

copyleftdev

545

Evaluation & Observability

Never confidently wrong: a TLA+-verified consensus kernel around TypeSafe's Jev, run through 1,680 chaos-tested pharmacy decisions with zero wrong verdicts. Film, code, and every captured call.

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-language

Nolane-x

546

Demos & Playgrounds

Give your Jev language

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

BYK

547

MCP & Integrations MIT source reviewed

An evaluation-focused Jev MCP server for individual questions, batch processing and question or threshold comparisons.

JEV · Decision point

Runs typed questions and uses labeled samples to measure accuracy and calibration.

Makes question design and threshold choices inspectable through sample results.

mcp-integrationsevaluation-benchmarkstyped-decisions

jev-mcp (benballintyn)

benballintyn

548

Agent Tooling

MCP server giving coding agents typed, calibrated judgments from 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.

jev-model-router

az9713

549

Agent Tooling

Jev (TypeSafe) model router on the Vercel AI Gateway

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-model-router (Mandrilsquad1441)

Mandrilsquad1441

550

Agent Tooling

Pick the best AI model and reasoning effort for any task in ~1s. Plugin for Claude Code, Claude Desktop and Codex, powered by TypeSafe's Jev decision model and live OpenRouter pricing. Balance intelligence, speed and cost, or choose your priority.

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-organize

nexibeo

551

Agent Tooling

Throw in a pile of company files and get them classified and organized by department, type, sensitivity, date, counterparty and PII, with an index for AI agents. Powered by TypeSafe's Jev on OpenRouter (17¢ per 1,000 files). Zero-dependency Node CLI + Claude skill + Codex agent.

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-pii-checker

coo-quack

552

Security & Guardrails MIT source reviewed

A CLI that sends text to TypeSafe Jev for PII category Nouls and a sensitivity Score, then locates spans with regex and segmentation.

JEV · Decision point

For each text chunk, asks twelve PII-category Nouls and a three-level sensitivity Score.

Judgment runs on TypeSafe servers; local code only locates spans, so this is not an offline privacy scanner.

security-guardrailstyped-decisionscli-git-gates