Launches on September 21, 2026
Repositories created on this date, ranked by GitHub stars. They launched the same day, so their stars compare directly.
- 2510
A Chrome Manifest extension that classifies and removes the text of posts on X/Twitter with TypeSafe's JEV
- 2520
Safety-first job application automation with TypeSafe Jev and Browser Use
- 2530
OpenAI-compatible judge endpoint for agent approval gates: typed judgements (Jev), any OpenAI-compatible model, or a rule file — fail-closed, calibrated, with a replay battery
- 2540
Typed decision tools for AI agents, powered by TypeSafe Jev
- 2550
Ask for the night you want. TypeSafe Jev weighs every flagship series on Netflix, Prime, Disney+, Max, Apple TV+, Hulu, Paramount+, Peacock, and Crunchyroll.
- 2560
Jev 意图雷达 — 用 TypeSafe SystemOne(Jev) 读懂消息背后的意图、情绪与风险
- 2570
A Jev practice catalog and local-first Agent skill router: map recurring logs to reusable decisions, tools, and workflows.
- 2580
bright-sight 的独立优化副本:把一句中文指令变成受控的应用操作,每一步执行完都由代码回读验证
- 2590
The Intelligent, Off-Script AI Teleprompter powered by TypeSafe Jev and Local Voice Tracking
- 2600
Non-blocking, provenance-checked Jev decisions for Bevy ECS.
- 2610
Review selected Blender object metadata and focus exact cited objects.
- 2620
Blockly extension: TypeSafe Jev judgments (Noul, Choice, Score) as first-class blocks
- 2630
Ask a question, and let TypeSafe's Jev model open the Book of Answers for you — yes/no or your own options, with the probability of every answer shown.
- 2640
Claude Code skill: typed browser automation over CDP with TypeSafe Jev decisions
- 2650
A simple interface for reviewing documentation drift.
- 2660
小红书工具
- 2670
Camunda 8 decision worker, Modeler template and BPMN example using Jev.
- 2680
Privacy-conscious Jev-powered chat signal analyzer for observable emotion, intent, engagement, and relationship signals.
- 2690
Local-first classroom signals with two-pass Chinese ASR, structured TypeSafe Jev judgments, and auditable teacher-private interventions.
- 2700
Calibrated Jev 1.13 percentages for Cline ask_question options — PreToolUse/PostToolUse hooks, a Cline plugin, a universal MCP server and a CLI.
- 2710
의사용 진단 전 체크리스트 — 실존 가이드라인 항목을 Jev(TypeSafe System One)로 정렬
- 2720
小模型只做选择,宿主掌握所有权:把「任务足够固定时,不要让模型写它能选的东西」量出来 | Selection-only: host enumerates candidates, a tiny model picks one id, host assembles deterministically. All numbers measured on one M1 Pro.
- 2730
Bridge Codex native macOS Computer Use runtime to any AI agent without login, guided by TypeSafe Jev model
- 2740
Route each Codex prompt to the right effort with TypeSafe's Jev
- 2750
Jev-powered decision workflows for Codex image generation. Explicit constraints, bounded repairs, and honest evaluation.
- 2760
Score AI agent context for relevance with Jev, and prune what's no longer useful.
- 2770
Customs Authority · Department of Snap Judgments — the decision-layer toolkit for Claude Code. Find where TypeSafe's Jev (System One) fits, write question sets that work, prove them on a gold set, ship the gated hybrid: stamp the sure, escalate the rest. From Robot Friends.
- 2780
Hosted Jev policy workspaces with tenant isolation, finite evaluations and revocable aggregate reports
- 2790
Reviewable Dify classifier migrations to Jev, with preserved branches and baseline comparisons
- 2800
Combine Jev preferences with finite constraints, exact bounded search and verifiable backend adapters.
- 2810
Decision studio for Jev: civic watch, evidence-backed scoring, human review and export.
- 2820
Side-by-side speed/quality bench for TypeSafe Jev and Laya
- 2830
Delega tarefa de codigo ao modelo escolhido pela tarefa, com permissao deterministica, verificacao por teste real e escalada so por falha provada. Jev (TypeSafe) julga o que exige significado; codigo faz o resto.
- 2840
demo trend seracher using jev
- 2850
Dertek AI - A fast, cost-efficient AI agent for coding and knowledge work. Agentic cli with TypeSafe Jev that uses fewer LLM tokens, lowers LLM cost, and routes tasks to the right model.
- 2860
Native Directus Flow operation for versioned Jev decisions with server-side credentials.
- 2870
Django model decision queue, admin history and stale-state checks for Jev.
- 2880
Score written content on house style, editorial quality, and audience fit. Regex linter for mechanical rules; semantic dimensions via a System One model (TypeSafe Jev today, backend-swappable).
- 2890
Make a scene out of repository
- 2900
Fact-checking skill for DeepSeek Harness: multi-source verification against the open web, domestic and international ecosystems, optional TypeSafe Jev (System One) judgements.
- 2910
Ask Jev (TypeSafe System One) typed questions from DeepSeek Harness: batch judgements with probabilities, configured per user in Settings.
- 2920
three.js AI town simulation: day/night economy, jobs, citizens — MCP server for AI control + TypeSafe Jev (System One) decision layer on OpenRouter
- 2930
Chrome extension: paste the exact value a form field wants, or the whole copied text.
- 2940
Resolve recurring order-reference exceptions with reviewed precedents and auditable proposals.
- 2950
A portable agent skill for bounded decisions through TypeSafe Jev and Vercel AI Gateway.
- 2960
Preserve exact context across Codex compaction with Jev. Open-source plugin, CLI, and library.
- 2970
Open-source Chrome MV3 extension: user-defined rubric categories, Jev noul scores each feed post, hide matches. BYOK Typesafe.
- 2980
Review selected Figma copy with typed Jev criteria and exact TextNode citations.
- 2990
Jev decides in a civilization with some actors
- 3000
Emendamenti alla manovra letti uno per uno: fotocopie, firmatari, esiti. Dati Camera dei deputati, analisi TypeSafe Jev.