Get started with Jev for free

Start here ↓

Jev is built for decisions, so I gave it one: which sentence on this page actually answers what I mean?

Introducing Needle, a new way to FIND (⌘F).

Cmd+F searches for words. Needle searches for meaning. Ask "what happens if I cancel?" and Jev scores the page's source sentences, picks the passages that match your intent, and highlights them in the original text.

No generated answer. No AI summary. Straight to the source.

Needle is an open-source Chrome extension with a React playground for searching your own text. Apache-2.0.

Clone Needle on GitHub

Jev API is free on Vercel AI Gateway until September 25. So if Jev FOMO has been all over your feed, you now have a working app to clone and a few days to run the model without paying for the calls.

Vercel says Jev became the fastest-adopted model in AI Gateway history, reaching nearly 13% of paid teams in 24 hours. That’s more than 2x the GPT-5.6 family and over 6x Fable 5.1.

Jev cannot generate text. It makes the tiny decisions around them. Needle is our first swing at putting that speed somewhere you can use today.

 Vercel launch and adoption report | Vercel free AI Gateway post

🚀 Jev-Shipped

Join the Jev rush through OpenRouter too, now available in beta. It also supports several typed questions about the same state in one call. That makes it fit routers, judges, guardrails, and handoff checks where the output space is already known.
OpenRouter Jev page

Jev is inside Postgres now. Zachi's pg-jev extension lets you write queries like WHERE jev(people, 'the name is European'); the database streams rows to Jev, asks one yes/no question per row, and returns the ones that pass. The public demo caps each read-only query at 20 seconds and 2,500 model-judged rows, so no, it is not a magic shortcut through a million-row production table.
pg-jev launch thread | pg-jev live demo

Jev can shrink a Claude Code session tokens by up to 90%! Why is agent compaction still a summarization prompt? Tamara Tran's fast-jev-compaction keeps user and assistant text verbatim, asks Jev which old tool calls still matter, and drops or truncates the rest. If Jev errors, lacks an API key, or cannot shrink the context enough, the plugin falls back to Claude Code's built-in summary.
fast-jev-compaction repository

This browser clicks before you finish the sentence. Moritz Kremb's jev-voice-browser sends every partial transcript to Jev, so the browser can act before you finish talking. Say "go back" and the decision can land in roughly 300ms; the app is already moving while the last word is leaving your mouth.
Voice browser thread jev-voice-browser repository

Browser Use with Jev finds flights in ~7 seconds. Browser Use shipped jev-ultrafast, an open-source BU agent where Jev chooses the browser operation and target, calling a text model only when it needs to type. It found a Google Flights itinerary in 7.073 seconds using 17 Jev requests, with median Jev latency of 178ms.
Browser Use Jev ultrafast demo| jev-ultrafast repository

Of course someone gave Jev a trading account. Jarrod Watts built jev-trader, a Bun app where Jev watches the Kuru MON-USDC order book on Monad and answers buy or sell every roughly 300ms block. It posts a limit order one tick inside the touch, cancels the previous one, and does it again when the next block arrives.
jev-trader launch thread | jev-trader repository

Cua built a Jev-like model just for filling forms. Jev introduced the System One idea: skip text generation and return fast, typed decisions that software can act on. CUA-S1-FORMS applies that same pattern to computer use. For every field or checkbox, the tiny 2.8MB model chooses what belongs there, whether to click it, or whether to leave it alone. Cua Driver then acts and checks that it worked.
CUA-S1 launch thread | Cua article on System One models

🧠 Worth Knowing

I Built Non-Autoregressive Decision Models with RL a Year Ago. Then a Frontier Lab Called It a "Breakthrough". This creator was building RL decision models 18 months before Jev.  In March 2025, he published SalesRLAgent, a reinforcement-learned model that produced live sales-conversion probabilities instead of asking an LLM for the judgment. Now he has turned that OPEN-SOURCE family for Jev-style routing, triage, guardrails, and typed decisions across 100+ languages.
Laya research page |Laya GitHub repository

Jev-as-a-Judge for agent evals. Agent evals often use another LLM to grade whether a run succeeded, which means paying a large model to answer a small question. LangChain tried Jev instead and got the same pass/fail verdict as its human labels in all 500 evaluations. The entire Jev run cost $0.34 versus $28.17 for Claude, and its scores bounced around far less between repeats.
LangChain Jev-as-a-Judge article

10-step guide for the Jev-pilled. For everyone staring at an agent stack and wondering where to put Jev, Codila wrote the 10-step version. Worker selection, source checks, continue/stop decisions, and handoff routing become typed questions; writing and tool execution stay with the models already doing them.
Jev engineering roadmap thread

Context7 finds a task where Jev gets smoked. Tested against Gemini Flash and DeepSeek across five parsing jobs. Jev tied three, won page classification 85% versus 56%, then collapsed on crawl-root selection at 27% versus 93%. It was still 10 to 170x faster and 3 to 20x cheaper. Great for bounded page-level calls; keep the bigger model around when the task needs a mental map of the whole site.
Context7 Jev test

🔧 Clone and Run

Clone & Run of the Day
Run the "poor man's Jev" on your Mac. LocalJev runs a Jev-compatible API on local models through oMLX, so the TypeSafe SDK can point at your Mac instead of the cloud. It was tested across 1,200 requests and five 4-bit models on an M5 Max. This is prompted JSON probability output, not Jev's direct-logit approach, so check the calibration before trusting it.
LocalJev GitHub repository | GitHub Next launch post

Let your coding agent find the Jev-shaped holes. Install the official TypeSafe Agent Skill, point Claude Code or another skill-compatible agent at your project, and ask it where Jev belongs. The skill helps it turn routers, checks, scores, and handoffs into typed System One calls instead of treating Jev like a chat model.
TypeSafe skills repository

Add a Jev-driven browser loop to Pi. pi-jev-browser gives Pi a Jev-driven browser loop inside isolated Playwright Chromium, plus optional macOS control through the accessibility tree. Jev sees structured page observations rather than screenshots, then chooses the next browser action.
pi-jev-browser npm package

kev is a Jev-like model you can run on a MacBook. Jared Palmer's kev is an Apache-2.0, Jev-inspired decision model built on Qwen2.5-0.5B. It runs on Apple Silicon behind a TypeSafe-compatible API and answers six questions in about 160ms, according to the README. But Jev does lead by roughly 19 points when the test moves out of domain.
kev GitHub repository

The fastest local Qwen3.8 on Apple Silicon. Splash Engine from Inco AI and LM Studio runs Qwen3.8-27B at 74 tokens/second on a 48GB M5 Pro. You can try it through LM Studio Bionic's experimental runtime. It needs an M3 or newer Mac, macOS 26.4+, and at least 36GB of unified memory.
LM Studio Splash post

MiniMax Code brings agent teams to the terminal. MiniMax Code is a terminal coding agent with subagents, web search, plugins, multimodal tools, and support for MiniMax or BYO models. It installs on macOS, Linux, WSL, and Windows, but requires sign-in or an API key.
MiniMax Code repository

Awesome LLM Apps is a curated collection of 100+ AI Agents, Agent skills, and RAG apps. It covers models from OpenAI, Anthropic, Google, and open-source models like GLM, DeepSeek, and Qwen that you can run locally on your computer. (Now accepting GitHub sponsorships)

That's all for today. Come back tomorrow for the next batch of AI tools, model drops, agent repos, and weird benchmarks worth your time.

If you found one thing to try, share the issue with someone who ships.

Unwind AI - X | LinkedIn | Threads

Awesome LLM Apps | Sponsor Us

Analytics on Live Data Without Leaving Postgres

When analytics on Postgres slows down, most teams add a second database. Then come the pipelines, the sync jobs, and a copy of your data that's always a little behind.

TimescaleDB takes a different approach: extend Postgres instead of splitting away from it. Hypertables partition your data automatically as volume grows. Hypercore compression cuts storage up to 95%. Continuous aggregates keep dashboards live without re-querying everything.

CERN runs Postgres this way for sensor data from the Large Hadron Collider.

No split architecture, no pipeline lag, no new query language to learn. Same SQL, same drivers, same tools.

Start on Tiger Cloud and get $1000 in credits.

Get $1000 Credit