Updated Nov 10, 2026
855 projects, posts and guides about Jev, the System One model from TypeSafe AI. Each entry links to its source and shows the cost and speed its author reported.
Diogo Almeida
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution
Newest first, 631–663 of 1072. All 1072 in curated order
Richard Seroter
@rseroter
I'm reading up on Jev (typesafe.ai/blog/introduci…) and learning how it differs from "regular" classification ML models. I gave a bunch of articles to @googlecloud Gemini Enterprise and asked it for a breakdown. Helpful. Still digging in before going hands-on.
XBenchmarks and evals
Akshay 🚀
@akshay_pachaar
Guidex.com
Akshay Pachaar’s worked example: evaluate a refund-support agent with Jev instead of a generative judge, and record the verdicts in Opik. Separates the judge from the evaluation system, and is explicit that a 0.98 is a probability about one proposition, not a percentage of the answer.
Robert Youssef
@rryssf
all things Jev in one place a GitHub collection just dropped packed with hundreds of tools, libraries, and projects built on top of Jev, from teams treating decision-making as its own primitive, separate from language generation entirely. github.com/AnotiaWang/awe…
XOpen source
XRobotics and devices
Richard
@richard_meng_01
Nitpicky, an AI generated photo detector powered by jev AI generated photos can be told from nits. That's why we build something to zoom into every detail: faces, fingers, characters, numbers, poses, where common senses fall apart, judged by jev
XDocuments and OCR
Guidegithub.com
Comet’s open-source evaluation and tracing platform, Apache-2.0. Datasets, experiments and trace-level feedback, with a custom-metric interface that takes several named scores from one call — which is how a Jev judge is wired into it.
TechVerser
@realfxw
Claude Code 的上下文终于不用再被一堆预加载技能塞满了！推荐一个非常优雅的按需加载解决方案：Jev Skill Suggestion。 以往在配置大量自定义技能（Skills）时，最头疼的就是 Context Window 膨胀问题。许多低频技能即便一次都用不上，也会在每次对话启动时常驻上下文，不仅白白消耗 Token 成本，还会稀释模型的注意力，甚至引入不必要的提示词干扰。 这个 Mod 的核心逻辑是将技能路由与主体执行彻底解耦（Just-in-Time 动态注入）： 常态零占用：将技能标记为仅用户可调用，默认状态下完全排除在上下文窗口之外，保持 Prompt 绝对干净。 轻量前置路由：用户输入指令后，Mod 会将技能列表交由 TypeSafe AI 的分类器 Jev（或兼容的 Vercel AI Gateway），快速匹配与当前任务最契合的技能。 精准单点注入：只有被分类器判定为高置信度命中的技能，才会在执行当下被动态注入给 Claude Code。 安装仅需一行命令： npx claude-code-templates@latest --mod productivity/jev-skill-suggestion 这种把“工具选择”抽离给轻量分类器、让大模型只专注“任务执行”的架构，正在成为复杂 Agent 系统降本增效的标配设计。随着技能库扩充，未来配合端侧超轻量分类模型（如社区正在探索的 MLX 移植版），整体延迟和隐私表现还会更进一步。 大家目前在 Claude Code 里常驻了多少个自定义技能？这种动态路由机制是否刚好击中了你的上下文焦虑？ #ClaudeCode #AIAgent #AgentSkills #TypeSafeAI #LLM #PromptEngineering #AI编程 #OpenSource #开发者 #独立开发 #全栈开发 #Vercel
XContext and memory
RazeDen
@razeden0
i just merge Grok 4.7 + Jev and got the smartest thing i've ever owned grok 4.7 does the thinking. jev does the deciding. together they cost less than my coffee prompt → grok bot → jev asks 6 questions → grok 4.7 opens only the good ones → campaign jev doesn't write anything. it only answers simple questions: yes or no, pick one, or a score. it can't make things up, because it can only pick from answers you allowed i gave it 3,412 leads from x, linkedin and youtube. 6 questions each is 20,472 decisions, done in 15.7 seconds for $0.41 the same reading by hand took me 6h 12m. people say 400x faster. i did the math and it's 1,421x that's $0.00012 per lead, and grok 4.7 only reads the ones worth reading the big mistake: sending everything straight to the new model. you pay the smartest thing you own to say "skip" all day setup took me 9 minutes: key in the secure field, sdk on the agent computer, one router skill, test mode first jev decides, grok bot does the work, and i still press the button on anything i can't undo everyone is talking about the new model. the cheap one deciding what it reads is where the money is
Ranjan Kumar
@ranjankumar
𝐖𝐡𝐞𝐫𝐞 𝐉𝐞𝐯 𝐁𝐞𝐥𝐨𝐧𝐠𝐬 𝐢𝐧 𝐚𝐧 𝐀𝐠𝐞𝐧𝐭 𝐇𝐚𝐫𝐧𝐞𝐬𝐬 (𝐍𝐨𝐭 𝐚 𝐌𝐨𝐝𝐞𝐥 𝐒𝐰𝐚𝐩) Your agent harness needs a decision model. Where you place it depends on one brutal fact: Jev's ordering is trustworthy. Its confidence numbers are not. Most placement guides skip this distinction entirely. They tell you to pick a threshold and execute above it. That works if you actually have a probability. You might not. 𝐓𝐡𝐞 𝐜𝐨𝐫𝐞 𝐩𝐫𝐨𝐛𝐥𝐞𝐦: A model can rank beautifully and lie about magnitude simultaneously. When you gate execution on if confidence >= 0.85: approve_transfer, you are trusting a number that was never calibrated to your prevalence, your cost ratio, or your queue. Move the threshold up and you trade recall you never measured for precision you cannot state. You have no idea how far along an unmarked axis you moved. 𝐓𝐡𝐫𝐞𝐞 𝐝𝐞𝐜𝐢𝐬𝐢𝐨𝐧𝐬, 𝐭𝐡𝐫𝐞𝐞 𝐝𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭 𝐧𝐞𝐞𝐝𝐬: Routing and ranking consume ordering only - which answer is best matters, the number beside it does not. Gated execution consumes magnitude - the threshold is your boundary and it must land on a calibrated scale. Relative logic like if top1 - top2 < 0.1: escalate consumes differences - and rescaling the score axis will flatten margins unevenly, breaking your code. The sepsis alert systems of 2020 learned this hard way. Michigan switched off alerts when COVID shifted patient prevalence beneath a fixed threshold. No weights changed. The denominator moved, the promise broke silently, and nurses drowned in false alarms. 𝐓𝐡𝐞 𝐟𝐢𝐱 𝐢𝐬 𝐬𝐞𝐪𝐮𝐞𝐧𝐜𝐞, 𝐧𝐨𝐭 𝐭𝐮𝐧𝐢𝐧𝐠: First question: is this number admissible as a probability at all? Run a calibration study on a few hundred labelled cases from your own queue. Samuel Sacco's measurements from 18 September and Adil Muhammad Pervez's 8,000 judgments both reach the same conclusion: fit your own map. The weights are shared across every account by design - there is no per-customer adaptation - so a deployer-side calibration map is your only mechanism. 𝐒𝐞𝐜𝐨𝐧𝐝 𝐪𝐮𝐞𝐬𝐭𝐢𝐨𝐧: given that the number is calibrated, where does your cost ratio put the line? That part of the familiar advice still works. Run them backwards and you are tuning a dial with no markings. Read the full analysis on calibration, harness placement, and where Jev actually fits: https://ranjankumar.in/jev-system-one-model-agent-harness-placement Follow for more practitioner insights on agentic AI systems and production AI engineering. #AgentiveAI #AIEngineering #SystemOne #Calibration #MLOps #DecisionModels #HarnessEngineering #Jev
XBenchmarks and evals
Guidelinkedin.com
Our explainer in Spanish, on LinkedIn: what a System One model is, what Jev decides, and where it fits.
Raksha T
@rakshaa_t
Jev has some invisible use cases that won’t be clickbaity but hella useful : - auto performance checks on your shipped websites - personal tools like using it for super quick chat compaction - user feedback prioritisation against most relevant data in your company - lots and lots of data sorting - quickly - pairing it with codex / claude to optimise decision making while you code with your agents etc
XTools and apps
grahma.dev
@quantium16
既然现在JEV在meta里，我就做了一个网站，让它在里面无限奔跑并收集眼镜，我觉得这个Infinity Runner应该会很高。你们还可以发你们通关的截图，你们中最好的那些人会从这个代币获得supply。 infinity-runner-rho.vercel.app
XGames and real time
Doge 🐶
@pprownets2023
💡 ยกระดับ AI Agent ให้เก่งขึ้น 100x ด้วย Jev Engineering (Decision-Making Brain) เคยเจอปัญหาไหม? เวลาทำ AI Agent แล้วสั่งงานด้วยข้อความธรรมดา (Free-form Prompting) มักได้ผลลัพธ์ที่ไม่แน่นอน ควบคุมยาก และนำไปต่อยอดในระบบแบบอัตโนมัติได้ลำบาก 🤯 เอกสาร JEV Engineering ได้เสนอแนวคิดในการแก้ปัญหานี้อย่างน่าสนใจครับ: 🔹 1. Jev คืออะไร? Jev คือ "สมองส่วนตัดสินใจ" (Decision-Making Model) สำหรับระบบ Agentic Systems ที่ไม่ได้เน้นการคุยแบบ Free-form Chat แต่เน้นการแปลงข้อมูลสถานะระบบ (Structured State) ให้กลายเป็น Typed Outputs ที่ชัดเจน เช่น ช้อยส์การตัดสินใจ, คะแนนความเกี่ยวข้อง หรือคำสั่ง ใช่/ไม่ใช่ พร้อมระบุค่าความน่าจะเป็น (Probability) 🎯 🔹 2. ทำไมถึงทำให้ระบบเก่งขึ้น 100x? การแยกส่วน "คิดตัดสินใจ" (Decision) ออกจาก "การลงมือทำ" (Execution) ช่วยลดความคลุมเครือ และทำให้ระบบเสถียรขึ้นอย่างมหาศาล โดย Jev จะส่งผลสูงสุดในจุดที่มีการตัดสินใจถี่ๆ (High-frequency Decisions) เช่น: 🔍 Research Evaluation: ประเมินความน่าเชื่อถือของแหล่งข้อมูลอัตโนมัติ 🛠️ Action Selection: เลือกใช้ Tool หรือส่งต่อ Agent ให้ถูกตัว ✍️ Content & Draft Refinement: วางแผนและเกลาเนื้อหาเชิงลึก 🚦 Human-in-the-loop Gating: ตัดสินใจว่าเคสไหนต้องส่งให้มนุษย์ตรวจต่อ 🔹 3. สรุปสถาปัตยกรรม 3 ขั้นตอน (How it Works) Input State (01): ใส่ Goal, Context, Rules และ Actions ที่ทำได้ Jev Brain (02): ประเมิน เหตุผล วางแผน และคืนค่าเป็น Typed Decision Orchestrator (03): นำผลลัพธ์ไป Validate และ Execute ร่วมกับ Agent, Tool หรือ Human สดๆ 💡 สรุปสั้นๆ: ถ้าอยากให้ AI Agent ทำงานอัตโนมัติได้อย่างแม่นยำ เลิกส่ง Free-form Prompt สั่งงานตรงๆ แล้วเปลี่ยนมาใช้ Structured State + Typed Decisions เพื่อการขยายระบบที่นิ่งและน่าเชื่อถือครับ!
XBenchmarks and evals
Guidelinkedin.com
Our piece in Spanish, on LinkedIn: Jev is closed, but 35 open projects train, adapt or replace it. The four families, the ten with the most stars, and why calibration, not accuracy, is the number to read before you trust any of them.
GitHubInbox and support
PickA reply co-pilot for phone chat apps: it reads the screen and drafts, you send.
jev-chat
7.8k
GitHubOpen source
PickThe open, local take on Jev: typed decisions without generating a token.
Rizzo AI Academy
897
GitHubAgents and browsers
LLM-written Jev harnesses, with reward reflection over the full trajectory.
TianyuCodings
542Guideyoutube.com/@ZazenCodes
ZazenCodes works through Jev hands on in Python, from a first call to typed decisions.
GitHubOpen source
A workbench for data selection, quality scoring and LoRA training.
RenaGao
63
GitHubBenchmarks and evals
Tune your Jev questions against your own labels, then confirm on held-out data.
smkrv
33Guideyoutube.com/@EdwardDonner
Edward Donner puts Jev to the test against Luna.
GitHubInbox and support
A WeChat reply helper for Windows: screenshot, local OCR, three drafts.
jev-chat
808
Guideyoutube.com/@seanai
Sean’s AI Stories: TypeSafe AI, fast judgment and evaluation, explained end to end.
GitHubGames and real time
Local MLX and hosted decisions playing T-Rex side by side.
Viraj Bhartiya
111
GitHubBenchmarks and evals
A sub-microsecond System 1 model whose accuracy is a Gaussian.
karminski
32
GitHubRobotics and devices
One-click simulation setup with Jev as the control policy.
YuanKJing
50Guideyoutube.com/@CloudCodes
Cloud Codes sets up a Jev-style decision model on local hardware.
GitHubGames and real time
Two decision models race in Snake, then fight in an arena.
PromptEngineer48
30
GitHubSDKs and integrations
A local visualiser: every Jev call your code makes, live.
andududu
62
GitHubCoding and code review
Score every test against a git diff, then emit the runner arguments.
mizchi
36Same directory, different order: the entries added most recently, rather than the curated order the home page opens in. The date on a card is the day it was added here, not the day its author published it — this directory is newer than most of the work in it.