Jev JavaScript

Release notes for the official JavaScript and TypeScript SDK: the 11 September 2026 public release and the Score criteria breaking change.

A local site, games, a benchmark, and an agent skill for Laya. The public pages replay recorded runs; the clone runs the model on your machine.

The Hacker News thread for Flavio Copes' JavaScript-oriented Jev tutorial covering choices, scores, latencies, and jagged edges.

A local gateway that forwards /v1/systemone to TypeSafe, stores each call in SQLite, and draws the calls on a live map.

A Mineflayer agent for Minecraft Java 1.16.5 where a planner sets the objective and Jev picks the next bounded action from game observations.

A completed Pokémon Red run: Jev picked menus, catches, and moves from RAM, and the harness handled pathfinding. The public page records the Hall of Fame stats.

The generated API reference for the official JavaScript SDK, listing every exported class, interface, function, and type.

A semantic linting CLI that parses a repository into a method-level call graph, then asks Jev to flag likely defects and check rules written in plain English.

A Claude Code Stop hook that reads the turn transcript locally and spends one four-question Jev call only when files changed with no passing check since, blocking unverified done claims.

Wrappers for Claude Code and OpenAI Codex that ask Jev to choose a model tier for each fresh user turn while preserving each CLI's native interface, tools, sessions, permissions, and authentication. Ships as the jev-claude and jev-codex commands.

Qwen3.5-0.8B fine-tuned to play ten classic browser games from raw pixels: one frame in, one forward pass, one move out in 43 ms on an H200. Public weights and a browser demo make it an open, vision-only take on Jev-shaped game decisions.

Claude Code, Codex, and pi plugin plus MCP server and npm library that hands steps needing no text output to Jev: one batched call answers typed questions about a state, and an opt-in PreToolUse gate can only deny or ask.

CLI and GitHub Action that turn project-defined semantic preferences from AGENTS.md into Jev Noul or Choice checks over code changes, then map each result to an advisory or blocking outcome. Checks can be tuned on labeled diffs.

Standalone Android agent and React studio for Mobilerun, powered by Jev: Jev selects operations and observed targets, code rejects stale actions, and a CLI, execution traces, and latency measurements ship in the repo. No ADB connection required.

Local Codex Router extension that asks Jev for a model tier and thinking depth on each model call, including continuations after tools, then relays the native Responses request verbatim. Fails open on Jev errors and logs decisions locally.

Local Instagram, TikTok, and LinkedIn research app where Jev makes confidence-gated typed choices over the platform and next socai operation, while deterministic Node code validates each decision and the socai CLI performs read-only browser capture.

A Manifest V3 Chrome extension that finds ad-shaped DOM elements and asks Jev, one noul question per candidate, whether each is a paid advertisement; hits above the threshold are removed.

A security hook for coding agents that asks Jev three typed questions before every tool call and scans tool results for prompt injection, with adapters for Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, pi, OpenCode and ACP.

Fifteen runnable OpenRouter recipes for Jev covering support triage, database indexing, PII scanning, moderation, lead scoring, a browser agent, and a Gmail labeler, each with a small labelled dataset and saved live results.

A Codex skill (with a plugin option) that hands clicks, toggles, navigation, and scrolling to Jev over accessibility text while Codex types, interprets visuals, and verifies the outcome.

Unofficial browser automation where the calling LLM states the outcome and Jev decides each element, action, and value from a Playwright page snapshot. Ships as a library, CLI, and MCP server.

A Pi plugin that has Jev pick one model and one reasoning-effort level from a configured list at the start of a session, then keeps both pinned for the rest of it.

A browser tool that checks whether a cited paper supports the sentence citing it: code matches references and verifies quotes, Claude proposes an evidence passage, and Jev scores supports, contradicts, or says nothing.

A tldraw canvas controlled by voice and a webcam-tracked fingertip: every partial transcript triggers one Jev request through OpenRouter's Decisions API that decides the action, shape, colour, and place.

A social network where 10,000 computed personas read your post: Jev scores who the text is for to pick the first 600 readers, then answers one Choice per persona for its reaction.

A Chrome extension and small web app that skips YouTube sponsor reads: Jev names transcript lines or answers yes/no about what it heard, and code owns every timestamp that gets cut.

An experimental Codex skill and JavaScript runtime that has Jev pick macOS Accessibility elements and actions from text candidates, while local policy gates hold sensitive operations for human confirmation.

A source-backed radar of open-source Jev projects with commit-pinned code evidence across 17 domains, plus a searchable site, an agent skill, and issue-based submissions.

Claude Code hook that scores installed skills against your prompt with Jev and writes skillOverrides so irrelevant skills stay out of context; a local TF-IDF ranker runs when no API key is set.

Telegram channel X-ray that judges up to 1,500 public posts from the last year with one Jev Choice over ten post kinds and three Noul checks, then draws a shareable monthly mix card.

A Codex Computer Use plugin that adds bounded Jev decision loops: Codex scopes the task and defines allowed actions, Jev picks an operation and compatible target in one request, and Computer Use performs the click, fill, scroll, or shortcut.

A community Jev directory of 899 entries with a searchable companion site at awesomejev.com: official docs and SDKs, community clients, agent tools, browser and computer-use projects, games, benchmarks, and articles.

A structured decision plugin for agent harnesses: Jev recommends among currently available and permitted tools, skills, and agents, and evaluates output quality, returning choices, probabilities, and confidence while the host agent keeps planning and execution.

A Chrome side panel that turns the current page's WebMCP tool schemas into typed Jev questions, predicting the tool call, its arguments, confidence, and latency as you type.

A joke npm package that left-pads a string by asking Jev to choose among space_0 through space_10 in one Choice, spending a model call where padStart() would do.

A comparison arena that runs the same batch of review comments through Jev and DeepSeek, showing processing time, cost, and per-label results with CSV/Excel import, replay, and offline reports.

A curated gallery of papers, open models, and independent evaluations behind System One models and Jev, with 131 entries in 8 sections and a dated news log on a companion site.

A source-backed directory of 157 open-source projects built with Jev whose submissions are reviewed by the Jev Review Action, which checks source evidence and suggests a category while maintainers decide merges.

A Chrome and Firefox extension that scores a draft X post with Jev before posting: virality, clarity, ragebait, insult level, regret risk, and typo detection, plus a Send it / Sleep on it verdict.

An independent CUDA and vLLM take on parallel typed decisions: it scores verified single-token labels with the model's own head and assembles JSON in code.

Interactive browser experiments that expose Jev's judgments: a support-message Decision Lab and a driving simulation where structured sensor state becomes typed steer, brake, and overtake decisions.

Delegated browser execution for parent agents: Jev picks one bounded typed action from the current page snapshot, agent-browser performs it, and ambiguous or stuck flows escalate back to the parent.

A zero-dependency Node library and CLI that adds Jev natural-language predicates and decision tables to SQLite, with batching, caching, review queues, and saved decisions queryable as ordinary SQL tables.

Quickstart for @typesafe-ai/sdk on Node 20+: answer types inferred from your questions, a choice() helper, and one systemOne call to classify a support ticket.

Control a headed Chromium window by voice: one Jev request per partial transcript decides intent, target, and completeness in roughly 300 ms, while code applies thresholds and builds the action.

Grep by meaning instead of regex: Jev scores every line, meanings combine with AND, OR, and NOT, and one query matches across Japanese, French, German, Spanish, and more.

A practical tour with JavaScript examples: typed choices, scores, probabilities, real latencies and costs, the jagged edges, and how to split jobs correctly.

Official TypeScript/JavaScript client with inferred answer types, retries, and a question DSL. `npm install @typesafe-ai/sdk`.