Jev发布帖
Diogo Almeida介绍了Jev,即TypeSafe的结构化决策模型。观看发布影片,并探索原始帖子了解该模型的方法、示例和作者报告的性能。
Latest addition
Source check
Recent activityDiogo Almeida介绍了Jev,即TypeSafe的结构化决策模型。观看发布影片,并探索原始帖子了解该模型的方法、示例和作者报告的性能。
TypeSafe的正式发布公告介绍了实验室,并引导开发者使用Jev。公告包含Diogo Almeida的发布影片和原始介绍。
TypeSafe宣布Jev向公众开放,无需等待列表。官方控制台是将类型化决策应用于自己应用程序的起点。
TypeSafe强调Jev的类型化输出方法:应用程序提供状态和问题,然后根据概率、选择或评分进行操作。相关公告还介绍了Venice API集成。
Start with the Launch Post. Explore four official signals.
1,198 项资源
AI-assisted summaries and translations. Check original sources for context and performance claims.
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 React app that estimates an age range based on a Korean name, described as a developer tool.
JEVLAB ARTSource-linked curation
Jev successfully played and won a match in the game Clash Royale.
Source-linked curation
A guide on using Jev to route between models and block risky tool calls.
JEVLAB ARTSource-linked curation
官方TypeScript/JavaScript客户端,支持推断答案类型。npm install @typesafe-ai/sdk。
Source-linked curation
Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions.
JEVLAB ARTSource-linked curation
A community post describes Jev attempting to play Resident Evil, testing its ability to handle 3D environments, objectives, and combat scenarios.
Source-linked curation
GitHub project for content moderation with category-specific probability thresholds. Enables automated content filtering.
JEVLAB ARTSource-linked curation
A developer project for the agents shelf featuring a local MCP gateway with Jev tool discovery and a dashboard.
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 community post describing 500 real-time agents operating in a 3D environment with notable performance metrics.
Source-linked curation
Utilizes Jev for quick coaching support and detecting and fixing slop during sessions.
Source-linked curation
An experiment to enable Jev to perform dogfighting, with ongoing improvements.
Source-linked curation
Explains Jev's advantages over older LLMs in decision-making and building.
Source-linked curation
A game where Jev makes decisions to keep a city on a whale alive, integrated with GPT-6 Astra and H3 Max.
Source-linked curation
A developer project for agent-native routing that selects models based on task complexity.
JEVLAB ARTSource-linked curation
Jev analyzes session replays to identify issues and generate bug fix PRs at low cost.
Source-linked curation
A deterministic model routing system for coding agents with a skill for Codex.
JEVLAB ARTSource-linked curation
Jev from @typesafeai plays Balatro, making quick decisions on cards and gameplay within 200-500ms.
Source-linked curation
A browser-based search tool that uses a 27K-parameter model to parse queries with Jev's assistance.
Source-linked curation
A user creates music by giving real-time voice commands to Jev.
Source-linked curation
Jev controls a city's traffic in a simulation project.
JEVLAB ARTSource-linked curation
A developer project generating paintings based on Jev's pixel probability calculations, collected for the tools shelf.
JEVLAB ARTSource-linked curation
Jev automates browser tasks by selecting actions from a dynamic action space.
Source-linked curation
Agent automates second-hand product search and decision-making. Processes 26 listings per minute with fast evaluation times.
Source-linked curation
A project using Jev to enable fast voice-controlled interactions with a Mac computer.
Source-linked curation
Tutorial covers API setup and building prototypes with Jev and LLMs.

Source-linked curation
Orus uses Jev to review and approve trade strategies before execution, enhancing decision-making with structured answers.
Source-linked curation
TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.
Source-linked curation
Type-safe model router. Jev (System One) banks each request to a typed catalog route.
Source-linked curation
An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.
Source-linked curation
MCP server for TypeSafe Jev: typed classify, score, check, match and screen for any agent, with confidence on every answer.
Source-linked curation
Connect JEV to MCP clients and compare its judgments against general-purpose LLMs using shared datasets and measurable accuracy.
Source-linked curation
Unofficial Java SDK for TypeSafe Jev and Vercel AI Gateway, with Spring Boot and WebClient support.
Source-linked curation
A developer project related to market analysis using Jev, collected for the markets shelf.
Source-linked curation
A resource explaining Jev's functions, costs, and evaluation metrics as TypeSafe's System One model.
JEVLAB ARTSource-linked curation
Short video explainer of how Jev's typed-decision loop works.
Source-linked curation
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI.
Source-linked curation
开源AI驱动的Mac指针伴侣,使用Jev或Gemini Live进行本地处理控制光标。
Source-linked curation
Jev is discussed with examples of Choice, Noul, and Score in a Python project.
JEVLAB ARTSource-linked curation
Jev was integrated with Claude Code to address context compaction challenges in agent workflows, showing promising results.
Source-linked curation
Emoji autocomplete at the speed of typing. TypeSafe AI Jev on a Whop-hosted TanStack Start app.
Source-linked curation
Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good).
Source-linked curation
Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.
Source-linked curation
JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.
Source-linked curation
A real-time computer assistant using Jev and local Whisper to process voice input, classify actions, and interact with the screen through a Swift app for accessibility.
Source-linked curation
Go client for TypeSafe AI's System One API (Jev), with optional Langfuse instrumentation.
Source-linked curation
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.
Source-linked curation
A real-time tool to analyze and categorize tweets for viral potential.
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
A focus group experiment using Jev to make scroll or stop decisions on ads.
Source-linked curation
A Next.js brick breaker whose paddle is controlled in real time by TypeSafe AI's Jev model. Built with Claude Code.
Source-linked curation
A Go client for the TypeSafe API, aimed at developer tools and applications.
JEVLAB ARTSource-linked curation
Jev on Sol. A community post describing an experiment where Jev analyzes Solana blockchain data in real time.
Source-linked curation
Neovim plugin that asks the buffer a plain-language question: Treesitter splits it into functions, Jev scores each one, and answers land in quickfix ranked by probability.
Source-linked curation
看看 Jev 能做什么:用中英文讲清热门应用、工作原理和各自优缺点。Explore Jev apps with plain-language examples, explanations, and comparisons.
Source-linked curation
Snake auto-played by TypeSafe's Jev model: one System One choice per tick, legal moves and facts generated in code.
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 model-judged permission gate for OMP (TypeSafe System One).
Source-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
Run a JSON Schema through TypeSafe's Jev API, and get JSON back.
Source-linked curation
A tool for evaluating coding sessions by analyzing each turn.
Source-linked curation
A code search tool for agents to find behavior patterns instead of text strings.
Source-linked curation
Official TypeSafe reference: Double-checking citations.
Source-linked curation
Jev processes 1,000 emails for category, priority, spam, and reply predictions.

Source-linked curation
A GitHub project that uses Jev to triage and route posts from the live Bluesky firehose with human oversight.
JEVLAB ARTSource-linked curation
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
Source-linked curation
CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.
Source-linked curation
CLI that finds PII in text with TypeSafe Jev: presence, sensitivity, and located spans.
Source-linked curation
A community post describes using Jev to analyze news for stock investment opportunities.
Source-linked curation
A LangChain package with TypeSafeClassifier for integrating Jev into applications.
Source-linked curation
A massively parallel browser-based adversarial testing suite for evaluating releases, costing pennies.
Source-linked curation