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 193–216 of 853 Some public source has been reviewed; inclusion is not a performance or safety endorsement

Cheshi

CheshiAI

193

Agent Tooling

Jev-powered conversation memory: find past sessions and revisit decisions with original sources. A macOS workspace for OpenAI Codex. Manage AI conversations and agents, explore code with CodeGraph, and work with Git, Ghostty terminals, and Apple Notes in one app.

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_local

Argos1111

194

Evaluation & Observability

Replicating Jev with a local LLM

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-belay

valentynkit

195

Decision Tools MIT

A Claude Code Stop hook that reads the turn transcript locally and calls Jev only when files changed and no check has passed, blocking an unverified “done”.

JEV · Decision point

Four questions: whether the closing message claims done, claims checks passed, whether verification applies, and a complete / partial / blocked / other choice.

Skips the model when a check already passed; every error path lets the turn end.

typed-decisionsclassification-ranking

jev-column-race

goodrahstar

196

Evaluation & Observability

Jev vs Gemini 3.8 Flash: labelling 1,000 app reviews, 4.1× faster and 7× cheaper

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

blakestone-x

197

MCP & Integrations MIT source reviewed

Wraps Jev classification, scoring, yes/no judgments and candidate matching as MCP tools.

JEV · Decision point

The MCP server calls the TypeSafe SDK and returns choices, probabilities and scores.

Provides a shared decision interface for MCP-compatible clients.

mcp-integrationsclassification-rankingtyped-decisions

jot

runta-dev

198

Browser & OS Action

The first general-purpose System One agent for 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.

typesafe-ai-playground

BunsDev

199

Domain & Vertical Tools MIT source reviewed

Community playground for TypeSafe AI and Jev featuring 110 real-world scenarios, dilemmas, and interactive experiments.

JEV · Decision point

Submits custom states and questions to Jev via Next.js API routes, displaying discrete probabilities, latency, and confidence scores.

Offers an intuitive web interface for exploring prompt criteria, testing edge cases, and evaluating discrete decision outputs.

evaluation-benchmarkstyped-decisions

jev-guard

leepokai

200

Security & Guardrails MIT source reviewed

Tool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.

JEV · Decision point

Jev evaluates tool inputs or outputs in session context; local rules allow, warn or block.

Adds review points around Agent tools, with behavior depending on the host client.

security-guardrailscoding-agentsai-agents

jevwire

Brainwires

201

MCP & Integrations MIT source reviewed

Provides Jev MCP tools, an embeddable library and Claude Code hooks for Agents.

JEV · Decision point

Uses Jev for ranking, verification, action checks and next-step selection, with code applying policy.

Reuses the decision layer through MCP or host code; hook behavior depends on configuration.

mcp-integrationscoding-agents

system-one-open

mithalouni

202

Evaluation & Observability

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal)

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.

awesome-jev (heyjunpenn)

heyjunpenn

203

Community Lists

A verified, community-maintained catalog of 485 open-source projects built with 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.

invalidate

chopratejas

204

Domain & Vertical Tools

The invalidation layer for AI memory. Every fact gets a lease; new evidence ends it. Built on 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_apps

JackZeng

205

Evaluation & Observability

看看 Jev 能做什么：用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.

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-cli

Nasrallah-AL

206

CLI & Pipelines MIT source reviewed

The jevctl command-line tool connects verification, classification and scoring questions to text input and scripts.

JEV · Decision point

Sends input and bounded answer options to Jev, then reports judgments and probabilities using local thresholds.

Provides structured results for pipelines and CI, with request inspection and dry-run support.

cli-git-gatesclassification-rankingtyped-decisions

jev

BorisLeMeec

207

Codebase & Graph Pathfinding MIT source reviewed

A Go Claude Code plugin using Jev to find files, answer bounded questions across code and handle large reads.

JEV · Decision point

Screens and verifies code relevance before whole files enter the agent context.

Returns file locations and judgments for focused inspection.

ast-code-graphcoding-agentscontext-compaction

jev-benchmarks

AbdelStark

208

Evaluation & Observability Apache-2.0 source reviewed

A benchmark comparing Jev and GLiNER on text classification, probability calibration and selective automation.

JEV · Decision point

Runs the same labeled text tasks through both backends and records probabilities, latency and failures.

Helps examine task-specific accuracy and whether confidence scores support chosen thresholds.

evaluation-benchmarksclassification-rankingbenchmarking

jev-me

jon-devlapaz

209

Demos & Playgrounds

A grill-me style interrogation of your idea, with Jev doing the grilling.

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-reflex-autonomy-lab

khordoo

210

High-Frequency & Simulation

Multi-drone autonomy lab demonstrating TypeSafe Jev reflex decisions with optional System 2 strategy guidance.

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.

games-simulationtyped-decisions

jevalyn

Ray-Hughes

211

SDK & Decision Frameworks MIT

The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your control flow.

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-decisions

jevbetter

olanotolu

212

Evaluation & Observability

A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.

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.

jgrep

keltokhy

213

CLI & Pipelines MIT

Filters text, structured records, functions, and diff hunks against plain-English descriptions using Jev Noul judgments.

JEV · Decision point

Jev judges whether each input unit matches the user description; local code applies the probability threshold and returns matching source material.

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

cli-git-gatessearch-retrievaltyped-decisions

live-jev

vinilana

214

High-Frequency & Simulation source reviewed

A browser-based top-down driving simulator using Jev for lane and speed choices, with an optional chat-model comparison.

JEV · Decision point

Jev answers lane, speed, hazard and pedestrian-yield questions; local rules apply the actions.

Runs controllers on the same seeded course, with separate local emergency-braking logic.

games-simulationtyped-decisions

mario-jev

shantanugoel

215

Games & Simulation

Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.

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.

RoboJEV

lykycy123

216

High-Frequency & Simulation Apache-2.0

RoboJEV is a small, inspectable robotics laboratory. JEV receives **structured simulator state, not images**, selects an immediate intent, then selects X/Y/Z directions and a gripper command. A Cartesian controller executes the action using real MuJoCo contacts. Each task has independent physical success checks; model answers cannot declare success.

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.

games-simulationtyped-decisions