Jev AgentA source-verified directory of 487 Jev projects — browser agents, model routers, SDKs and MCP servers — each one showing the exact decision it hands to Jev. Curated by the Awesome Jev community, mirrored here under MIT.
Give Jev the current state and a few options. Get the Agent’s next step.
Core call · setup in the full example
const nextStep = choice("What next?", { login: null, askUser: null, retry: null });
const { answers } = await client.systemOne({ state: "Login form is ready", questions: { nextStep } });
console.log(answers.nextStep.choice);Node.js 20+ · Set TYPESAFE_API_KEY on your server. This page shows code and makes no model requests.
An educational AI hedge-fund prototype with an optional Jev adapter for structured judgments in fund decision workflows.
Converts strategy questions to System One requests and normalizes native answers to the project’s result format.
Allows Jev or other model backends to be used in the same research workflow.
A market-making experiment on Kuru’s MON-USDC book on Monad, with optional per-block Jev buy/sell decisions.
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.
A tax-document page classifier that uses Jev to choose from predefined IRS form and page categories.
Extracts PDF page text and sends it to Jev for form type, page type, and confidence.
Connects a fixed form catalog to per-page classifications for downstream document workflows.
Agent tool evaluation harness comparing standard LLM tool selection against Jev routing across 100 mocked tools.
Employs Jev for two-stage discrete pruning over tool catalogs, narrowing extensive tool lists down to relevant candidates in milliseconds.
Mitigates context bloat and hallucinated tool calls in complex agents by isolating candidate selection into fast discrete steps.
An experimental Hyperliquid trading bot using Jev to choose long or short and whether to open, close, or hold.
Each asset account sends market state to Jev; execution code places or cancels orders based on the decisions.
Separately records model decisions, order execution, and dashboard state.
A Solana liquidity Agent with Jev shadow judgments compared against rule-based decisions.
Evaluates entry distribution, toxic flow, holding and stress signals for calibration logs.
Adds comparable advisory signals to deterministic trading rules without claiming returns.
Jev-powered Instagram, TikTok, and LinkedIn research: typed routing, real browser evidence, streamed post cards, video capture, and cited socai reports.
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.
Turns Jev judgments into Home Assistant sensors, such as checking whether finished laundry has been left unattended.
Reads selected entity states and returns probabilities, choices, or scores that configured thresholds can use in automations.
Connects natural-language conditions to existing sensors, notifications, and scenes.
A systematic-review tool that selects verbatim evidence from papers and supplements for human checking and export.
Jev selects candidate line IDs; code copies the original text with file and location references.
Connects quotes, source locations and human verification status.
An experimental Rust SEO/GEO CLI and MCP tool combining page checks, DuckDuckGo queries and optional Jev scoring.
Classifies search intent, direct answers and content gaps, with a custom citation-likelihood rubric.
Collects local checks, search results and model judgments into reports.
Edit `.env` locally and replace the placeholder with your own key. Keep this file private; Git ignores it. Do not paste the key into frontend code, a browser field, an issue, or a command that will be saved in shell history.
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.
A demo job-search Skill for coding Agents that browses company careers pages in Chrome, uses Jev to screen AI and software-engineering roles, and saves the results.
Jev uses Choice to classify pages and Noul to assess careers links, role relevance, filter controls and candidate fit; local thresholds select navigation, job details and saved results.
Connects careers navigation, role screening and detail matching in one CLI workflow, with local JSON and Markdown reports.
A dashboard combining live crypto market data with Jev-guided paper trading; no broker or live-order API is connected.
Jev reviews completed minute candles and indicators; Python applies confidence and position limits to a simulated portfolio.
Shows market inputs, model judgments and paper positions together.
Community playground for TypeSafe AI and Jev featuring 110 real-world scenarios, dilemmas, and interactive experiments.
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.
Site: www.bles-software.com, 566 pages, 8,460 link decisions (15 candidate targets per page). Run on 19 Sep 2026. Every number below is from the run files in `out/` and `runs/`.
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.
Live Kubernetes log analysis, contextual investigation, and agent handoff powered by Jev.
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.
It provides a web and CLI demo that sends user text to Jev through OpenRouter for Choice, Score, and Noul probability judgments and compares the results side-by-side with a general LLM.
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.
Work with Jev is a local-first message classifier that uses Jev to sort work messages into urgent, to-do, worth-reading, and skippable groups with cross-chat to-do management and Feishu and WeCom adapters.
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.
Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM, Stockfish and you. One-page web app with live moves, Jev's move probabilities, saved games and win rates.
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.
Verified milestones so far: Jev can leave the Player's House, cross Pallet Town, deliver itself through Route 1 (fighting and winning any wild encounters along the way), and reach Viridian City. Further legs of the journey (Oak's Parcel, the first Gym) aren't built yet — the walk currently ends the run once it reaches Viridian City.
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.
An EVM Token screening tool with library, CLI and MCP interfaces for market-feature-based risk judgments.
Uses a deterministic local engine by default; a TypeSafe key enables real Jev judgments over features.
Shows features, decision provenance and scores together for inspection.
SQLite C extension enabling TypeSafe Jev judgments as native SQL functions for semantic scoring and choices.
Registers custom functions like jev_choice and jev_score directly inside the SQLite query pipeline.
Enables row-level semantic classification directly inside relational SQL queries without glue code.
Local coding workspace and agent decoupling tool routing via Jev from detailed argument generation via DeepSeek.
Employs Jev to classify and select the next tool action based on execution state, delegating parameter generation to DeepSeek.
Combines low-latency discrete routing with capable generative modeling, reducing overall prompt overhead and turn latency.
**PDF: how the audit was made, the scorecard and the priorities**
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.
A community-maintained directory and radar for Jev, highlighting open-source projects with verified code and clear decision architectures.
Jev is TypeSafe's decision model. This directory groups projects by how they use choices, scores and probability judgements, with implementation links to help you assess fit for your own task.
TypeSafe ↗We prioritize open-source projects with clear Jev implementation evidence. Repositories without verifiable source code are excluded from the main directory.
Directory data and design from Awesome Jev by logicrw, used under the MIT License.
