5191 repositories with documented relationships and source evidence.
Best Skills combines registry installations and social attention into daily agent-skill rankings with downloadable CSV data. Jev checks post relevance, listing maintenance and categories; the project publishes the judgment probabilities. Start with best-100, inspect registry coverage and compare original platform counts alongside composite scores.
Foreman supervises coding workers, assessing completion, requirements, test sufficiency and the need for human input. Jev evaluates checks; a deterministic Python arbiter selects whether to continue, steer, verify, stop or escalate. Supply a repository and job with Python 3.11+, a TypeSafe key and a configured coding-agent backend.
A community directory helps readers find projects by their decision architecture and browse them with search and category filters. Browse the radar website or install its agent skill with npx skills add logicrw/awesome-jev-projects to inspect projects by domain.
The package runs Convai Innovations’ Laya model through ONNX Runtime for typed classification and scoring in Node.js and TypeScript. Install @receptron/laya on Node.js 20 or newer, load Laya, then pass state and typed questions to systemOne; close the instance afterward.
Jev Decision Atlas indexes public resources by the decision an agent makes, such as tool selection, routing or classification. Start with the reading path for a first API call, then browse decision patterns and inspect the linked implementation evidence.
The project controls a Minecraft Java 1.16.5 player through Mineflayer, using a separate model for planning and Jev for player actions. Configure the model relay and local runtime paths, install dependencies, start the vanilla server, and launch the documented nether-agent workflow.
Simple Jev uses compatible Hugging Face models to classify and score inputs, constructing JSON answers from next-token logits instead of generating a completion. Send shared context as either state or messages, plus typed questions, to POST /v1/classifier on the configured server.
The collection supplies skills for record triage, evidence checks, rubric evaluation and choosing legal actions. Follow the installation guide, choosing real Jev through TypeSafe or OpenRouter, or an explicitly labeled agent simulation.
This community guide links live builds, starter examples and independent evaluations to help readers design a concrete Jev decision. Use the first-call path, shape a bounded question, or download resources.json to explore the directory programmatically.
The English and Simplified Chinese list collects Jev applications, clients, agent tools, games and research links. Start from the official documentation and known-failures links, then use the SDK or application sections to find an implementation.
OpenJev reads typed answers from open-model probabilities and serves choices, scores and yes/no judgments, including image questions for its main model. Point the TypeSafe SDK’s base URL at your server or the documented hosted endpoint, then call system_one with state and questions.
phi is a Go terminal coding harness with file tools, subagents, diff review and on-demand MCP tool discovery. Configure a primary coding model with phi config, start phi, and supply TYPESAFE_API_KEY if enabling optimizer features.
Jev Search turns plain-language requests into web links and snippets with editable filters and visible relevance scores. For local use, configure Search1API and a Jev provider in .dev.vars, install dependencies with pnpm, and run pnpm dev.
The library identifies IRS forms and page kinds from extracted text using a JSON registry of form descriptions. Use classifyPage with text lines, jevBackend and criteria.json. PDF helpers additionally require Poppler; the backend needs a TypeSafe key.
DocJev classifies PDF, DOCX and PPTX documents or splits packets into categorized page ranges, with optional PDF exports. Install the Python package with uv, export TYPESAFE_API_KEY, and run docjev classify or split with category rules. Office formats require LibreOffice.
jev-router launches the native coding CLIs through a local proxy and selects a model tier for each new user turn. Install jev-router with npm, configure JEV_API_KEY, and launch jev-claude or jev-codex with an installed, authenticated upstream CLI.
Awesome JEV is a gallery of System One research, open models, applications and independent evaluations, with links to code and papers. Use the official primitives and known-failure links for orientation, then follow model or evaluation entries to their original sources.
Jev MCP gives agents tools for evidence verification, classification, reranking, extraction and patch review. Register npx -y @jkudish/jev-mcp in an MCP client using Node.js 22 or newer and a configured Jev provider key.
The floating chat panel displays intent and risk judgments and candidate replies that users can copy or insert into the chat input. Use an Apple Silicon Mac with macOS 13 or newer. Grant Screen Recording for screenshot-based reading and Accessibility for text access or insertion, then choose judgment and generation providers in settings.
The curated list organizes Jev providers, SDKs, agent workflows, context tools, games and evaluations with source and limitation notes. Read the Choice, Score and Noul introduction, then follow the relevant workflow category and pinned research notes to source code.
VexJoy Agent connects requests to specialist agents, reusable skills and workflows across supported coding runtimes. Install the toolkit for the desired runtime and configure direct TypeSafe or Vercel transport; the installer supports a dry-run preview.
classifier.dev exposes HTTP and CLI text classification, including batches and multiple label dimensions. Pass labels and text in a URL, install the classify CLI, or POST items and dimensions to /v1/classify.
Mobile Jev controls an Android device through Mobilerun, with a live studio, CLI and execution traces. Configure both provider keys and a ready device ID, then use pnpm dev to open the local studio and submit a goal.
Web Search Plus adds web search and page extraction tools to Hermes, with routing and fallback across configured providers. Install the Hermes plugin and configure a search provider. Enable Jev separately with setup --jev and install typesafe-sdk.