PROJECTS & RESOURCES DIRECTORY

Jev projects and resources

Find a Jev implementation for agent routing, browser actions, coding tools or context compaction. See which decision Jev handles, how it is integrated and whether the source evidence has been reviewed.

Community directory snapshot 2026-09-28 Review method 2026 ecosystem report

1428catalogued records
346source-reviewed entries
74project analysis pages
651Kknown deduplicated stars

The catalog includes 1,334 repository or integration records, 61 article or discussion records and 33 other resources. Repository links resolve to 1,332 unique GitHub repositories; a public link alone does not establish an open-source license.

01 / DIRECTORY

Browse Jev projects and resources

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 985–1008 of 1428 Some public source has been reviewed; inclusion is not a performance or safety endorsement

can-jev-play

carlaiau

985
Evaluation & Observability E0 · catalogued

Can Jev infer whether a bet is worthwhile from its payout table, and do recent wins or losses sway that 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.

986
Browser & OS Action E0 · catalogued

Non-Autoregressive AI Agent Decision Model. Open-source SOTA alternative to TypeSafe Jev. O(1) Tool Routing & DOM Automation on Qwen3.5-2B .

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-mod

chrishan17

987
SDK & Decision Frameworks MIT E1 · source linked

Typed decisions in Claude Code: adds $.jev over TypeSafe's Jev, through OpenRouter, Vercel AI Gateway, Cloudflare Workers AI, LiteLLM or the TypeSafe API.

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.

multilanguage-sdktyped-decisionssecurity-guardrails

claude-jev-warden

connectedGraph

988
Security & Guardrails MIT E1 · source linked

Real-time quality gate and Art Director Warden for Claude Code powered by TypeSafe Jev 1.13 non-autoregressive decision model

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
989
CLI & Pipelines MIT E1 · source linked

Fail-open Codex UserPromptSubmit hook that injects TypeSafe Jev pre-task routing metadata.

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-gatescoding-agents

commentcop

ntedvs

990
Domain & Vertical Tools E0 · catalogued

Put your code comments on trial. 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.

DataJev

zzz1YAO

991
Data & Search MIT E1 · source linked

⚡ DataJev LLM → Analyze Jev → Continue / Switch / Verify / Stop System-1 control for System-2 data agents

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-retrievaltyped-decisions

decide

gopaljigaur

992
Evaluation & Observability E0 · catalogued

One client for every decision model: Choice, Score and Noul over Jev, OpenRouter, laya, MLX, CrossEncoders and LLM fallback

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.

decido

yairshy

993
SDK & Decision Frameworks E0 · catalogued

Probabilistic decisions for Python. Use Jev or bring your own provider; crawl with Playwright.

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.

994
Evaluation & Observability E0 · catalogued

A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.

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.

995
Domain & Vertical Tools E0 · catalogued

Experimental: live X draft viral scorer 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.

dsh-jev

Excalibur9527

996
Context GC & Filter MIT E1 · source linked

This DeepSeek Harness plugin sends each round's latest user message to the systemone (Jev) API for emotion and intent classification and injects the result as plugin-sourced runtime context, with API Key and all parameters configured in the GUI settings page.

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.

context-compactionclassification-ranking
997
Security & Guardrails MIT E1 · source linked

Jev (TypeSafe System One) decision tools + live verification benchmark for DeepSeek Harness: jev_decision (choice/score/noul) and jev_verify, honest by design.

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

ego-jev

phd-peter

998
Browser & OS Action MIT E2 · source reviewed

Connects Ego Lite snapshots and browser actions to a bounded Jev decision loop.

JEV · Decision point

Selects only current snapshot candidates and supported actions; another model can supply typed text.

Executes against current snapshot references and records step state.

browser-automationtyped-decisions

ego-jev

flazouh

999
Browser & OS Action MIT E1 · source linked

Drive ego-browser pages with TypeSafe Jev: code builds the allowed actions, Jev picks one, code acts and re-checks.

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.

browser-automationtyped-decisions

Footwork

Tom-R-Main

1000
Browser & OS Action E0 · catalogued

A verified browser agent: a cheap Jev guard (evidence-checked completions, a destructive gate) in front of any LLM browser driver, with Jev taking the mechanical steps in dual mode. Built on browser-use; every number pre-registered and measured.

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.

gojev

taigrr

1001
Agent Tooling E0 · catalogued

Go harness for Jev/Kev decision models: TypeSafe, Vercel AI Gateway, and in-process Kev via llama.cpp

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.

gpt-vs-jev

TanayPadar

1002
Demos & Playgrounds E0 · catalogued

Compare GPT generated language with JEV structured Noul decisions on the same input.

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.

guard-jev

NorbertBodziony

1003
Demos & Playgrounds E0 · catalogued

Comment-moderation playground: paste a comment, Jev decides what to do with it.

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.

1004
Security & Guardrails E1 · source linked

It is a library, not a service. You call it, you get a verdict, and your code decides what to do. It runs in **Python and TypeScript**, both reading the same policy file, so the two sides of your stack cannot drift apart. Neither package has a third-party dependency.

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

harden-jev-decides

tylerjharden

1005
Demos & Playgrounds E0 · catalogued

JEV picks which stream idea becomes the live MVP. TypeSafe System One decision board.

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.

1006
Evaluation & Observability MIT E2 · source reviewed

A Hermes goal-checking skill that saves requirements, creates a run prompt and checks completion evidence.

JEV · Decision point

Local checks handle machine-verifiable requirements; Jev assesses the remaining semantic conditions.

Connects goals with checkable criteria without replacing actual acceptance evidence with model opinions.

evaluation-benchmarksmcp-integrationsagent-skills
1007
Agent Tooling E0 · catalogued

Experimental Hermes plugin: Jev-assisted model routing plans with budget and capability constraints. API access pending.

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.

hfjev

hemanth

1008
Data & Search MIT E2 · source reviewed

Python, Node and playground interfaces for classifying dataset rows with declared Choice, Score and Noul dimensions and exporting structured results.

JEV · Decision point

hfjev classifies dataset rows in parallel across typed Choice, Score, and Noul dimensions against TypeSafe System One.

Makes row-level judgments and chosen rubrics inspectable before batch use; playground mock mode is separate from live evaluation.

search-retrievalclassification-rankingevaluation-benchmarks
PROJECT DETAILS