Latest addition
Source check
Recent activityA FIELD GUIDE TO JEV / VOL. 01
The best of Jev. Real projects, practical guides and ideas from across the internet.
THE OFFICIAL SIGNAL 4 HIGHLIGHTS
Diogo Almeida@CompleteSkepticLAUNCH POSTDiogo Almeida introduces Jev, TypeSafe’s structured decision model. Watch the launch film and explore the original thread for the model’s approach, examples and author-reported performance.
TypeSafe AI@typesafeaiOFFICIALTypeSafe’s official launch announcement introduces the lab and points builders to Jev. It includes Diogo Almeida’s launch film and original introduction.
TypeSafe AI@typesafeaiOFFICIALTypeSafe announces public access to Jev without a waiting list. The official console is the starting point for trying typed decisions in your own application.
JEVLAB ARTTypeSafe AI@typesafeaiOFFICIALTypeSafe highlights Jev’s typed-output approach: applications provide state and questions, then act on probabilities, choices or scores. The linked announcement also covers the Venice API integration.
JEVLAB ARTStart with the Launch Post. Explore four official signals.
286 resources
AI-assisted summaries and translations. Check original sources for context and performance claims.
Claude Code plugin that replaces the compaction summary with Jev decisions: every tool call and result is scored in one fast request, stale ones are dropped or truncated, everything kept stays verbatim.
JEVLAB ART
EnglishSource-linked curation
Browser Use's ultrafast agent: Jev picks the operation and DOM element in one request; a small LLM only writes text when typing is needed.
JEVLAB ARTEnglishSource-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 ARTEnglishSource-linked curation
An agent system that makes one Jev decision per computational step.
JEVLAB ARTEnglishSource-linked curation
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code.
JEVLAB ARTEnglishSource-linked curation
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
JEVLAB ARTEnglishSource-linked curation
Route to the cheapest model in claude code for your task using jev-router.
JEVLAB ARTEnglishSource-linked curation
A developer project for automatic context clearing in Pi without losing conversation history.
JEVLAB ARTEnglishSource-linked curation
Vercel's open agent framework, which ships Jev as the default evaluation model in its experimental evaluate path.
JEVLAB ARTEnglishSource-linked curation
Go CLI and single-binary MCP server exposing TypeSafe judgments to Claude Desktop, Claude Code, and Codex.
JEVLAB ARTEnglishSource-linked curation
Agent Skill: send closed coding-agent judgments to TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
A moderation system for Mastra agents that processes inputs in a single file.
JEVLAB ARTEnglishSource-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 ARTEnglishSource-linked curation
An agent project aimed at reducing token usage for coding agents via an MCP server.
JEVLAB ARTEnglishSource-linked curation
Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground.
JEVLAB ARTEnglishSource-linked curation
Standalone Android agent for Mobilerun where Jev makes every decision, with a live React studio and an Uber demo.
JEVLAB ARTEnglishSource-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 ARTEnglishSource-linked curation
A developer project that uses Jev as a sensor to control access to agent tools, enhancing security and functionality.
JEVLAB ARTEnglishSource-linked curation
Claude Code plugin: trim long Bash output with TypeSafe Jev before the model sees it.
JEVLAB ARTEnglishSource-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 ARTEnglishSource-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 ARTEnglishSource-linked curation
A developer project providing a local MCP server for running pre-made Jev question packs.
JEVLAB ARTEnglishSource-linked curation
Context curator for Pi agent using Jev technology.
JEVLAB ARTEnglishSource-linked curation
A developer project where Jev assists in browsing by selecting actions, with an LLM planning and citing sources.
JEVLAB ARTEnglishSource-linked curation
A Jev powered LinkedIn recruiting agent. Watch it browse relevant profiles, save links, and review evidence against your hiring brief.
JEVLAB ARTEnglishSource-linked curation
I kept watching coding agents burn context on decisions that aren't hard - triage 400 tickets, tag 600 files, route to one of six teams. jev-mode moves those verdicts to a typed-judgment model. I A/B'd it: 78% fewer tokens, 16x less work-attributable input, accuracy 96.1% vs 93.7%. Python, no deps, MIT.
JEVLAB ARTEnglishSource-linked curation
Typed, confidence-aware agent skill routing with TypeSafe Jev.
JEVLAB ARTEnglishSource-linked curation
A GitHub project converting agent skills into Oxlint plugins that involve Jev.
JEVLAB ARTEnglishSource-linked curation
jev-use (voice). A developer project implementing voice control for macOS with Jev as a fallback option.
JEVLAB ARTEnglishSource-linked curation
Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.
JEVLAB ARTEnglishSource-linked curation
Know before you click. A Chrome extension that reads articles and YouTube videos ahead of you and says read, skim, save, or skip — with a confidence, tuned to your goals. Open source, MV3, powered by Jev.
JEVLAB ARTEnglishSource-linked curation
Browser use using Typesafe's Jev model.
JEVLAB ARTEnglishSource-linked curation
Runtime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.
JEVLAB ARTEnglishSource-linked curation
Daf-jev: composable Python toolkit for TypeSafe's Jev (System One) decision API — question builders, confidence gates, evaluator, calibration, CLI, MCP server, agent skill.
JEVLAB ARTEnglishSource-linked curation
Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.
JEVLAB ARTEnglishSource-linked curation
Pi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning).
JEVLAB ARTEnglishSource-linked curation
Chrome extension that labels every post you scroll past on X with typed Jev judgments and a live cost counter.
JEVLAB ARTEnglishSource-linked curation
Pure Jev that can "type" and drive towards task completion.
JEVLAB ARTEnglishSource-linked curation
CLI and agent skill for TypeSafe System One (Jev): typed Choice, Score, and Noul judgments.
JEVLAB ARTEnglishSource-linked curation
Cost-optimized OpenRouter model router using TypeSafe's Jev, with a live full-catalog scorer instead of a hardcoded model list.
JEVLAB ARTEnglishSource-linked curation
PoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals. 8.7x faster, 4.4x fewer prompts, measured on 153 real commands. Approvals only.
JEVLAB ARTEnglishSource-linked curation
Pi extension: verbatim context compaction with TypeSafe Jev decisions.
JEVLAB ARTEnglishSource-linked curation
Match user goals to MCP catalog (two-stage) via TypeSafe Jev.
JEVLAB ARTEnglishSource-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.
JEVLAB ARTEnglishSource-linked curation
Search the web with TypeSafe's Jev: source selection, query understanding and relevance ranking. Built with Search1API.
JEVLAB ARTEnglishSource-linked curation
Turn your AGENTS.md preferences into a fast, Jev-powered AI linter.
JEVLAB ARTEnglishSource-linked curation
Jev (System One decision model) plugin suite for DeepSeek Harness (dsh).
JEVLAB ARTEnglishSource-linked curation
Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex).
JEVLAB ARTEnglishSource-linked curation
Filter command output for coding agents using a task description.
JEVLAB ARTEnglishSource-linked curation
Connect TypeSafe Jev to Grok Bot as a cheap decision layer - usage gates, skill template, examples.
JEVLAB ARTEnglishSource-linked curation
Fast JEV compaction extension for pi.
JEVLAB ARTEnglishSource-linked curation
在 X 的时间线上，给每条帖子标出它想让你干什么。判断来自 Jev，一个只返回概率、不生成文本的模型。
JEVLAB ARTEnglishSource-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 ARTEnglishSource-linked curation
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
JEVLAB ARTEnglishSource-linked curation
Jev-powered model-judged permission gate for OMP (TypeSafe System One).
JEVLAB ARTEnglishSource-linked curation
A developer project using Jev for plain-language MCP tool calls without an LLM.
JEVLAB ARTEnglishSource-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.
JEVLAB ARTEnglishSource-linked curation
5–10x faster browser operations: Jev clicks, Codex thinks and verifies. Built at EZCollegeApp.
JEVLAB ARTEnglishSource-linked curation
Jev-assisted file retrieval and request caching for faster Pi workflows.
JEVLAB ARTEnglishSource-linked curation
Autonomous PlayStation 2 AI Agent with real-time visual telemetry HUD powered by TypeSafe Jev System One.
JEVLAB ARTEnglishSource-linked curation
Evidence-driven frontend QA built on Jev Ultrafast and Browser Harness, with a synthetic todo demo.
JEVLAB ARTEnglishSource-linked curation
Jev plays browser table tennis in real time: structured telemetry, typed decisions, ordinary Chrome inputs, and auditable evidence.
JEVLAB ARTEnglishSource-linked curation
MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools.
JEVLAB ARTEnglishSource-linked curation
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
JEVLAB ARTEnglishSource-linked curation
Proof of concept MCP for Typesafe's new Jev AI model.
JEVLAB ARTEnglishSource-linked curation
TypeScript browser agent for ego lite: Jev Ultrafast indexed actions, TypeSafe Jev decisions, persistent observe/act CLI. No Chrome or Playwright.
JEVLAB ARTEnglishSource-linked curation
Local Instagram, TikTok, and LinkedIn research where Jev chooses bounded socai browser operations and streams captured evidence into cited reports.
JEVLAB ARTEnglishSource-linked curation
Minimal agent loop where Jev directs control flow and a LangChain chat model writes argument values and the final response.
JEVLAB ARTEnglishSource-linked curation
The first general-purpose System One agent for Jev.
JEVLAB ARTEnglishSource-linked curation
A developer project for the agents shelf featuring a local MCP gateway with Jev tool discovery and a dashboard.
JEVLAB ARTEnglishSource-linked curation
Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.
JEVLAB ARTEnglishSource-linked curation
Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev).
JEVLAB ARTEnglishSource-linked curation
Submit a find
한국어
日本語
Español
Français
Deutsch
简体中文
繁體中文
Português
Bahasa Indonesia
ไทย
Italiano
Tiếng Việt
Türkçe
Polski
Русский
4 HIGHLIGHTS
4 clicks / 7d
Agents & browsers
Source-linked curation