Il post di lancio di Jev
Diogo Almeida presenta Jev, il modello di decisione strutturato di TypeSafe. Guarda il filmato di lancio e esplora il thread originale per l'approccio del modello, esempi e prestazioni riportate dall'autore.
A FIELD GUIDE TO JEV / VOL. 01
Il meglio di Jev: progetti reali, guide pratiche e idee da tutto il web.
Diogo Almeida presenta Jev, il modello di decisione strutturato di TypeSafe. Guarda il filmato di lancio e esplora il thread originale per l'approccio del modello, esempi e prestazioni riportate dall'autore.
L'annuncio ufficiale di lancio di TypeSafe introduce il laboratorio e indica agli sviluppatori di Jev. Include il filmato di lancio di Diogo Almeida e l'introduzione originale.
TypeSafe annuncia l'accesso pubblico a Jev senza lista d'attesa. La console ufficiale è il punto di partenza per provare le decisioni tipizzate nelle proprie applicazioni.
TypeSafe evidenzia l'approccio di output tipizzato di Jev: le applicazioni forniscono stato e domande, quindi agiscono su probabilità, scelte o punteggi. L'annuncio collegato copre anche l'integrazione dell'API Venice.
Start with the Launch Post. Explore four official signals.
286 risorse
AI-assisted summaries and translations. Check original sources for context and performance claims.
Agente ultra veloce per il browser: Jev seleziona l'operazione e l'elemento DOM in una sola richiesta; un piccolo LLM scrive solo quando è necessario digitare.
JEVLAB ARTSource-linked curation
Plugin per Claude Code che sostituisce il riepilogo della compattazione con decisioni Jev, valutando ogni chiamata e risultato in una singola richiesta rapida e gestendo i dati obsoleti.
JEVLAB ARTSource-linked curation
An agent system that makes one Jev decision per computational step.
JEVLAB ARTSource-linked curation
Write Cucumber tests with just the .feature file. No step definitions — Jev (TypeSafe AI) resolves each Gherkin step and Playwright runs it.
JEVLAB ARTSource-linked curation
Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell.
JEVLAB ARTSource-linked curation
A Codex plugin that uses Jev to streamline and reduce excessive tool outputs.
JEVLAB ARTSource-linked curation
Typed, confidence-aware agent skill routing with TypeSafe Jev.
JEVLAB ARTSource-linked curation
Rust CLI powered by Jev from TypeSafe.ai that ranks agent skills for the next step using live session context. Includes Claude Code hooks, structured JSON, abstention, and local feedback. Requires a TypeSafe API key.
JEVLAB ARTSource-linked curation
A developer project that uses Jev as a sensor to control access to agent tools, enhancing security and functionality.
JEVLAB ARTSource-linked curation
Route to the cheapest model in claude code for your task using jev-router.
JEVLAB ARTSource-linked curation
Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.
JEVLAB ARTSource-linked curation
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
JEVLAB ARTSource-linked curation
A developer project where Jev assists in browsing by selecting actions, with an LLM planning and citing sources.
JEVLAB ARTSource-linked curation
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
JEVLAB ARTSource-linked curation
An agent project that enforces policies by judging Claude Code tool calls.
JEVLAB ARTSource-linked curation
Context curator for Pi agent using Jev technology.
JEVLAB ARTSource-linked curation
Jev-assisted file retrieval and request caching for faster Pi workflows.
JEVLAB ARTSource-linked curation
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
JEVLAB ARTSource-linked curation
Typesafe's jev as a "fuzzy linter". give your code an ocular patdown.
JEVLAB ARTSource-linked curation
Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.
JEVLAB ARTSource-linked curation
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground.
JEVLAB ARTSource-linked curation
Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
JEVLAB ARTSource-linked curation
A developer project using Jev for plain-language MCP tool calls without an LLM.
JEVLAB ARTSource-linked curation
A developer project providing a local MCP server for running pre-made Jev question packs.
JEVLAB ARTSource-linked curation
A developer project offering semantic code search for coding agents, benchmarked on SWE-bench Lite.
JEVLAB ARTSource-linked curation
MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.
JEVLAB ARTSource-linked curation
A prose linter that sniffs out AI writing tells. Zero dependencies, countable rules plus one judgment model.
JEVLAB ARTSource-linked curation
Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://github.com/compozy/compozy.
JEVLAB ARTSource-linked curation
Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.
JEVLAB ARTSource-linked curation
Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.
JEVLAB ARTSource-linked curation
100% free ₹0 agent-first SEO & GEO CLI suite and MCP server in Rust replacing Semrush and OpenSEO via DuckDuckGo and TypeSafe Jev System One.
JEVLAB ARTSource-linked curation
Pi extension: verbatim context compaction with TypeSafe Jev decisions.
Source-linked curation
Data extraction for systematic reviews, quoted from the papers. Ask a trial report and its supplements your extraction form or a RoB 2, ROBINS-I, QUADAS-2 or TIDieR template; Jev points at the lines, every answer is a verbatim quote with its page, you check it and export the table. Files stay in your browser.
JEVLAB ARTSource-linked curation
A claude code plugin for jev.
Source-linked curation
Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model).
Source-linked curation
A guide-directed World of Warcraft agent designed to reduce expenses as it runs longer, developed on GitHub.
Source-linked curation
Pure Jev that can "type" and drive towards task completion.
Source-linked curation
Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.
Source-linked curation
Rule-based slop grader for text files powered by Jev: evaluates markdown against customizable rulesets, outputting violation flags and scores for an AI agent to auto-fix.
Source-linked curation
A developer project providing a second MCP server for Jev from the PyModel initiative.
Source-linked curation
A developer project focused on agent memory, where Jev determines what information is relevant to recall.
Source-linked curation
Talk to your Mac. Local whisper.cpp + one Jev (TypeSafe) call per command + macOS automation.
Source-linked curation
A developer project that converts vague agent requests into deterministic commands for improved reliability.
Source-linked curation
Proof of concept MCP for Typesafe's new Jev AI model.
JEVLAB ARTSource-linked curation
TypeSafe Jev as the pi coding agent's quiet decision layer.
Source-linked curation
Agent budget brake — continue / downgrade_model / stop via TypeSafe Jev.
Source-linked curation
Browser game: try to beat Jev at spotting a spam message.
Source-linked curation
An agent project aimed at reducing token usage for coding agents via an MCP server.
JEVLAB ARTSource-linked curation
2D autonomous car simulation in the browser, driven by TypeSafe's Jev decision model.
Source-linked curation
A pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and your users keep control of thresholds, weights, and actions.
Source-linked curation
Dependency-free CLI and Codex skill that send local state to Jev for batched typed judgments and return answers without echoing the state.
Source-linked curation
Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.
Source-linked curation
Experimental protocol for evidence-aware agent handoffs, with Jev-assisted review before results reach the lead agent.
Source-linked curation
Tell Claude Code which installed skill a session needs, using Jev (TypeSafe AI) for the decision and skills.sh for discovery.
Source-linked curation
Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter.
Source-linked curation
Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).
Source-linked curation
Evaluating TypeSafe's Jev as a fast monitor and action gate for agent sabotage in SHADE-Arena, compared with Gemini 2.5 Flash/Pro.
Source-linked curation
Agent skill: design judgment-assisted systems with TypeSafe Jev (System One). Maps Choice/Score/Noul onto decision theory, reranking, and routing. Composition algebra, question design, validation gates. MIT.
JEVLAB ARTSource-linked curation
Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay.
JEVLAB ARTSource-linked curation
Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.
Source-linked curation
Pick the best AI model and reasoning effort for any task in ~1s. Plugin for Claude Code, Claude Desktop and Codex, powered by TypeSafe's Jev decision model and live OpenRouter pricing. Balance intelligence, speed and cost, or choose your priority.
Source-linked curation
Ricerca semantica veloce e auditor di coerenza per assistenti di codifica AI (Antigravity, Cursor, Claude Code) alimentati dal Sistema Uno di TypeSafe.
Source-linked curation
An awesome collection of Jev use cases, workflows, and agent skills.
Source-linked curation
Privacy-first Chrome extension that semantically blocks native ads, sponsored feed cards, and video ads using TypeSafe Jev.
Source-linked curation
Sub-second Git pre-commit & pre-push semantic reflex gate powered by TypeSafe AI Jev.
Source-linked curation
Claude Code mod that routes decisions to TypeSafe's Jev model: ranks installed skills per prompt, and answers the agent's own this-or-that questions when confident.
Source-linked curation
Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.
Source-linked curation
Send Pi agents back to work when they stop before the job is done.
Source-linked curation
Experimental decision protocol whose Jev adapter evaluates framed evidence with typed choices, while application code validates permissions and commits simulated demo actions.
Source-linked curation
A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.
JEVLAB ARTSource-linked curation
Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。
Source-linked curation
Play ten browser games from the screen with a 0.8B open model that returns a probability over the game's legal moves in one forward pass, no text generated.
Source-linked curation