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.

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 ★ 19K 02 fast-jev-compaction ★ 6,653 03 jev-trader ★ 2,240 04 TypeSafe agent skills ★ 2,060 05 agent-desktop ★ 1,604 06 typesafe-computer-use ★ 937 07 Jev Review ★ 586 08 foreman ★ 540 09 hermes-jev-skills ★ 726 10 pg-jev ★ 329

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 25–48 of 1428 Some public source has been reviewed; inclusion is not a performance or safety endorsement

SemIf

TheoLeeCJ

025

Evaluation & Observability E0 · catalogued

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.

ax

ax-llm

026

SDK & Integrations Apache-2.0 E2 · source reviewed

Ax provides a TypeSafe integration for boolean or finite-class signatures and native Jev answers.

JEV · Decision point

Maps supported signatures to Jev questions or sends native System One requests.

Reuses structured signatures and Jev probabilities within Ax workflows.

multilanguage-sdktyped-decisions

memsearch

zilliztech

027

Data & Search MIT E2 · source reviewed

A Markdown-and-Milvus memory system with an optional Jev reranker that independently checks whether each retrieved passage contains the information a query needs.

JEV · Decision point

The query is shared state and each complete passage becomes a Noul question; exact answer coverage and finite probabilities are validated before stable sorting.

Adds an explicit evidence-matching stage after retrieval and raises on failed evaluation rather than silently pretending to rerank.

search-retrievalclassification-ranking

bootcamp

milvus-io

028

Data & Search Apache-2.0 E2 · source reviewed

Runnable search tutorials using Gemini embeddings, Milvus retrieval, and Jev judgments for reranking, filtering, and routing.

JEV · Decision point

Jev judges declared query routes and candidate evidence, while notebook code maps fixed choices to filters and validates all requested answer IDs.

Shows retrieval, semantic reranking and deterministic filter policy as separate stages on a small synthetic dataset.

search-retrievalclassification-ranking

jev-trader

jarrodwatts

029

Domain & Vertical Tools MIT E2 · source reviewed

A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.

JEV · Decision point

In Jev mode, order-book judgments feed code that simulates fills or submits configured post-only limit orders.

Defaults to a mock model and dry-runs without a private key; simulated results do not establish profitability.

finance-quanttyped-decisions

NanoJev

TianyuCodings

030

High-Frequency & Simulation MIT E2 · source reviewed

Nano replica of Jev featuring parallel decisions, dynamic candidate sets, and an end-to-end training and evaluation pipeline.

JEV · Decision point

Evaluates multiple questions and dynamic candidate spaces concurrently in a single forward pass, logging navigation choices.

Provides open-source training infrastructure and game environment benchmarks for investigating non-generative discrete decisions.

games-simulationevaluation-benchmarkstyped-decisions

TypeSafe agent skills

typesafe-ai

031

Official E0 · catalogued

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

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.

agent-desktop

lahfir

032

Browser & OS Action Apache-2.0 E2 · source reviewed

A desktop-agent framework with an optional Jev skill that selects controls and actions from native accessibility data.

JEV · Decision point

Jev selects a target and action and estimates presence and risk; local policy decides whether to execute.

Keeps the full UI tree out of the main Agent context while exposing the selected action.

desktop-ostyped-decisionsaccessibility

awesome-jev (yibie)

yibie

033

Community Lists E0 · catalogued

A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.

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.

vellum-assistant

vellum-ai

034

MCP & Integrations MIT E2 · source reviewed

An optional Jev provider in Vellum Assistant sends conversation state and explicit questions to TypeSafe.

JEV · Decision point

Submits state and question bundles to System One and returns structured answers to the Assistant.

Adds choices, probabilities, and scoring to an existing assistant.

mcp-integrationstyped-decisionsagent

jevlike

vinnylarouge

035

Evaluation & Observability E0 · catalogued

Train a small model that chooses among a changing list of text options, one probability per option in a single pass. Includes Doom, chess, and Wikispeedia demos.

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.

celesto

CelestoAI

036

Codebase & Graph Pathfinding Apache-2.0 E2 · source reviewed

A Celesto PR-review example prepares sandbox checks and compares a general model with Jev on candidate findings.

JEV · Decision point

Judges whether a finding was introduced by the change, is supported and merits a fix.

Shows execution records and reviewer judgments together.

coding-agentsevaluation-benchmarks

typesafe-computer-use

awlevin

037

Browser & OS Action MIT E2 · source reviewed

Builds candidate actions from OCR and UI state for Jev to control macOS, calling a text model only when writing is needed.

JEV · Decision point

Selects the next step from deterministically extracted controls and actions before desktop execution.

Separates screen reading, action selection, and text generation.

desktop-ostyped-decisionsai-agents

atomic

bastani-inc

038

Routing & Cost Optimization E2 · source reviewed

An optional Jev decision backend in the Atomic coding Agent for bounded structured choices such as routing.

JEV · Decision point

Sends predefined questions to Jev and decodes answers for callers; regular models still generate code.

Separates structured decisions from text-generation interfaces.

coding-agentsllm-routing-cost

ai-cli

vercel-labs

039

MCP & Integrations E0 · catalogued

Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.

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

040

Community Lists E0 · catalogued

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.

hermes-jev-skills

kerpopule

041

Routing & Cost Optimization MIT E1 · source linked

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

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.

llm-routing-costtyped-decisions

TypeLLM

042

SDK & Decision Frameworks Apache-2.0 E2 · source reviewed

An open typed-generation layer built on SGLang that leaves autoregressive model architecture and weights unchanged while returning schema-constrained string, integer, number, boolean, or enum Python values.

JEV · Decision point

Independent fields can run as a batch, while depends_on forms a DAG so later fields can read dependency results and reuse shared prefix caches.

Extends beyond finite choices and booleans to free strings, integers, decimals, image input, optional thinking and permutation averaging for structured-generation workflows such as receipt extraction.

typed-generationjson-schemasglang

awesome-jev-tools

v-modal

043

Community Lists E0 · catalogued

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

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.

aiavatarkit

uezo

044

Voice & Conversation Apache-2.0 E2 · source reviewed

An optional AIAvatarKit component uses Jev to judge turn endings from speech transcripts.

JEV · Decision point

Assesses utterance completeness and whether the user is likely to continue speaking.

Adds a semantic signal to silence-based turn detection.

voice-conversationtyped-decisions

kody

kentcdodds

045

Data & Search E2 · source reviewed

Optional second-stage search: widen the hybrid pool, then Score-rerank candidates with Workers AI typesafe/jev.

JEV · Decision point

Sends a Score question per candidate, reorders and drops low scores; the model id is typesafe/jev.

Attaches Jev rerank to existing MCP search instead of replacing retrieval. License is Fair Source FSL-1.1-ALv2, not OSI open source.

search-retrievalmcp-integrationsclassification-ranking

Agent

AgentiLoop

046

Security & Guardrails E2 · source reviewed

An optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.

JEV · Decision point

Adds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.

API failures generally allow the command with a warning, so it is not complete system protection.

desktop-ossecurity-guardrailsaccessibility

von

wfzyx

047

Evaluation & Observability E0 · catalogued

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to 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-cu

Sac-Y

048

Browser & OS Action MIT E2 · source reviewed

A Codex Computer Use loop sending text candidates to Jev while desktop tools observe and act.

JEV · Decision point

Chooses targets and actions and assesses completion and risk; local policy controls execution or confirmation.

Uses text candidates and starts with a dry run by default.

desktop-oscoding-agentscodex