Post de lançamento do Jev
Diogo Almeida apresenta o Jev, o modelo de decisão estruturado do TypeSafe. Assistir ao filme de lançamento e explorar o fio original para o abordagem do modelo, exemplos e desempenho relatado pelo autor.
Latest addition
Source check
Recent activityA FIELD GUIDE TO JEV / VOL. 01
O melhor de Jev: projetos reais, guias práticos e ideias de toda a internet.
Diogo Almeida apresenta o Jev, o modelo de decisão estruturado do TypeSafe. Assistir ao filme de lançamento e explorar o fio original para o abordagem do modelo, exemplos e desempenho relatado pelo autor.
O anúncio oficial de lançamento do TypeSafe apresenta o laboratório e direciona os desenvolvedores ao Jev. Inclui o filme de lançamento de Diogo Almeida e a introdução original.
TypeSafe anuncia acesso público ao Jev sem lista de espera. O console oficial é o ponto de partida para testar decisões tipadas em seu próprio aplicativo.
TypeSafe destaca a abordagem de saída tipada do Jev: aplicações fornecem estado e perguntas, depois atuam sobre probabilidades, escolhas ou pontuações. A anúncio vinculado também aborda a integração da API Venice.
Start with the Launch Post. Explore four official signals.
1.198 recursos
AI-assisted summaries and translations. Check original sources for context and performance claims.
Jev autonomously controls multiple characters in a video game with rapid decision-making.
Source-linked curation
An image classifier using OCR and Jev processes 900 images in 40 seconds.
Source-linked curation
A Jev-inspired decision interface for existing LLMs. Explicit choices, scores, calibration, and review thresholds.
Source-linked curation
Integrates Jev into apps for smart autofill features improving user experience.
Source-linked curation
Ask a yes/no question of every function in a codebase. Ranked answers in seconds, for cents. Grep whose pattern is a question, powered by TypeSafe Jev.
Source-linked curation
Interactive TypeScript coding CLI with typed routing, decision programs, and validated formal trees driven by Jev.
Source-linked curation
Unofficial go SDK for typesafe AI, with typed answers, retries, and context support.
Source-linked curation
A GitHub project enabling voice-controlled Mac automation without vision models.
Source-linked curation
A real-time tool to analyze and categorize tweets for viral potential.
Source-linked curation
A developer project offering semantic code search for coding agents, benchmarked on SWE-bench Lite.
JEVLAB ARTSource-linked curation
An integration with jev by typesafe.ai in Rust.
Source-linked curation
One AI trade decision every Monad block. Jev on Kuru MON-USDC.
Source-linked curation
Jev tests shooting skills in the arcade game Time Crisis, with a harness to assist performance.
Source-linked curation
A show-and-tell capability study for Jev, TypeSafe's System One decision model.
Source-linked curation
Jev evaluates the pacing of a frontier-AI essay written by @DarioAmodei.
Source-linked curation
Zero-hallucination open-source repo and crate scout powered by TypeSafe AI Jev System One scoring.
Source-linked curation
High-speed recursive AI Elo tournament engine powered by Jev and Swiss matchmaking.
Source-linked curation
A community post discusses Jev as a faster general classifier/decision-maker, questioning its accuracy in complex scenarios and noting potential benefits in limited solution spaces with low latency requirements.
Source-linked curation
Official TypeSafe reference: TypeSafe Python SDK.
Source-linked curation
An unofficial Laravel package offering typed responses and test fakes for Jev integration.
JEVLAB ARTSource-linked curation
Jev was integrated with Claude Code to address context compaction challenges in agent workflows, showing promising results.
Source-linked curation
askjev.ai. A community post describing a platform where users can ask questions to Jev, which provides judgments rather than direct answers.
Source-linked curation
Official TypeSafe reference: State.
Source-linked curation
Rewrite AI drafts in your own voice with a bounded TypeSafe feedback loop.
Source-linked curation
Reduces SEO and GEO fix costs by 90% through faster data analysis and automation.
Source-linked curation
Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and ~$0.02 per 1,000 judgments, with typed escalation back to the LLM.
Source-linked curation
Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
Source-linked curation
Unofficial Go SDK for the TypeSafe AI System One API — 1:1 parity with the official JS and Python SDKs. Not affiliated with TypeSafe AI.
Source-linked curation
Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results.
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
Browser automation with Jev (TypeSafe) as decision model.
Source-linked curation
Busca semântica rápida de código e auditor de sanidade de diffs para assistentes de codificação de IA (Antigravity, Cursor, Claude Code) alimentados pelo TypeSafe System One.
Source-linked curation
A report detailing all public Jev builds in the first week, including cost, time, and repository metadata for research use.
Source-linked curation
An agent project aimed at reducing token usage for coding agents via an MCP server.
JEVLAB ARTSource-linked curation
One-pass option scoring with a local Gemma 3 4B on Apple silicon via MLX, inspired by jevlike, with a Doom demo.
Source-linked curation
Jev-style calibrated decision model (Choice/Score/Noul) on Qwen3.5-0.8B.
Source-linked curation
Test a post against 10,000 synthetic personas before you publish it.
Source-linked curation
Jev classifies emails for fraud detection, with uncertain cases handled by Kimi K3 for high accuracy.
Source-linked curation
Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.
Source-linked curation
Official TypeSafe reference: SDE cascade.
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 tool that analyzes public PR links to determine if they are safe to merge or need review, using Jev's capabilities.
Source-linked curation
A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.
Source-linked curation
Helper n8n community node for Jev by TypeSafe. Classify, route, and score text with questions you define, and get a probability for every answer so unsure items can go to review.
Source-linked curation
Probably: live BTC, ETH, and XRP prices with a shared TypeSafe buy-or-wait demonstration. No trades placed.
Source-linked curation
A 4-minute video explaining what Jev is and its limitations.
Source-linked curation
Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.
Source-linked curation
A Chrome extension that covers distracting YouTube videos with Jev. Show anyway whenever you want.
Source-linked curation
A GitHub tool that requests Jev's approval before merging pull requests.
Source-linked curation
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.
Source-linked curation
Utilizes Jev for quick coaching support and detecting and fixing slop during sessions.
Source-linked curation
Idiomatic Java SDK for TypeSafe AI Jev System One decision engine.
Source-linked curation
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.
Source-linked curation
A community post demonstrating Jev playing Flappy Apex, achieving a high score autonomously through Appduct and Fable.
Source-linked curation
Zero-shot English goals on a sim Franka. Jev chains hardcoded primitives.
Source-linked curation
Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.
Source-linked curation
MCP server that puts TypeSafe Jev on the coding loop in Cursor, Codex, and any MCP client.
JEVLAB ARTSource-linked curation
Code quality and test coverage for coding agents: Jev scores each source file so the agent knows what to fix first.
Source-linked curation
Third-party write-up of the System One primitives, pricing, and vendor workflow evals.
Source-linked curation
Official TypeSafe reference: Noul.
Source-linked curation
A community post showcasing Jev's ability to rank exam questions by likelihood of appearing on real tests within 80 seconds.
Source-linked curation
Type-safe model router. Jev (System One) banks each request to a typed catalog route.
Source-linked curation
Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway.
Source-linked curation
Fast Rust CLI for TypeSafe Jev: typed decisions, offline linting before you pay.
JEVLAB ARTSource-linked curation
A tool that monitors user interactions and intervenes only when it detects confusion or difficulty, using Jev to determine appropriate responses.
Source-linked curation
A system that quickly captures user interface flows on demand, enabled by Jev's fast processing capabilities.
Source-linked curation
Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.
Source-linked curation
A YouTube guide explaining Jev's functionality, including browser use, classification, and code review without an LLM.

Source-linked curation
SQL with natural-language predicates, powered by TypeSafe's Jev. Filter, rank, classify and score rows by meaning — batched, cached and cost-guarded.
Source-linked curation
Classifies tax documents using an LLM pipeline for efficient processing.
Source-linked curation
Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo.
Source-linked curation
Codex plugin: verbatim Jev-guided context restoration around session compaction. Port of tamaratran/fast-jev-compaction to Codex lifecycle hooks.
Source-linked curation