Laya: The Open-Source, Faster Jev — System 1 Models Go Local

TypeSafe shipped Jev on September 15 — a "System 1" model that returns typed decisions instead of text, so it can't hallucinate. Days later, Convai Innovations shipped Laya: open source, runs on your own hardware, and benchmarks faster. Here's what System 1 models are, and whether Laya's numbers hold up.

Video thumbnail — Open Source, Faster Jev is HERE
🎬 CoderOne ⏱️ 13:02 📅 Sep 2026
Laya System 1 Decision Models Open Source

🎮 The 30-Decisions-Per-Second Snake Demo 0:00

The video opens with the cleanest possible proof of concept: an AI playing Snake, entirely on a local machine, using Laya — an open-source classification model. It makes roughly 30 decisions per second, each in under 33 milliseconds, and after running for a while the snake is over 140 long and "still never fails. It finds a way — the right direction to actually eat the points."

Laya is "basically the same" as Jev, the model that "took the entire web and the entire ML/AI industry by storm": a System 1 model — a special class that only outputs typed, structured decisions, built for classification rather than text generation.

🧠 System 1 vs System 2: What These Models Are 0:28

The framing comes straight from Daniel Kahneman's Thinking Fast and Slow (2011): System 1 is fast, instinctive, and emotional; System 2 is slow, deliberative, and logical. LLMs are System 2 — they reason, chat, find solutions. Jev, Laya, and their ilk are System 1 — they classify, instantly, without generating language.

System 1 (Jev, Laya)System 2 (LLMs)
NatureFast, instinctive, emotionalSlow, deliberative, logical
OutputTyped decisions (choice / score / null)Generated text
ExamplesJudge distance, localize a sound, 2+2, read a billboard, drive an empty roadPrepare for a sprint, count the A's in a text, reason through a problem
HallucinationStructurally can't — output is constrained to a schemaPossible

The memorable example: LLMs are System 2, and even they "fail when you say count the number of R's in the word strawberry." System 1 models are the complement — the instant classification layer you bolt in front of the slow reasoner.

🔥 Jev's First Week: Mario, Leads, and Cheap Flights 1:07

Since TypeSafe announced Jev, the demo ecosystem exploded. People wired it into Super Mario Bros, playing in real time (jump, left, move forward, pause). Others used it for high-intent lead scoring — feeding 700 leads and letting Jev classify who'll respond, the perfect message, and how to reach out. The showstopper: pairing Jev with browser-use to book flights — an entire Google Flights booking in ~7 seconds at a fraction of a cent.

The pattern is the same everywhere: a decision model in the driver's seat, calling the shots dozens of times a second while a bigger model does the actual generation only when needed.

🛠️ Swapping Jev → Laya with Claude Code 2:47

There was already an open-source demo called jev-ultrafast (from Gregor at BrowserBase), but it called the closed Jev API. The "even cooler" move was running your own open-weights model locally — faster than Jev, "maybe a little less accurate because it's the very first version," released within days of Jev and working on any Apple Silicon Mac (M1 Max, M3, M2, M4).

The swap itself is a mini-case-study in agentic coding: the host handed Claude Code the source, asked it to swap Jev for Laya, and "it almost one-shotted everything" — no back-and-forth. The resulting demo drives a real Chrome tab via Laya + browser-use: the prompt is "find one-way flights from Zurich to London on October 20, 2026 for one adult in economy; stop when matching flight options are visible", and it picks Zurich, London, the date picker, one-way, and submits — a fully controlled browser session, no Jev API, no cost.

The demo that sells it: a Google Flights search driven end-to-end by an open, local, free decision model — and a second fixture demo (open the article about "finite choices to control browser agents") where Laya correctly infers the target page from a vague prompt.

📊 Laya vs Jev: Faster, Open, Slightly Less Accurate 6:18

The honest comparison, stated plainly: Laya is "a little less precise and accurate compared to Jev" — Jev is much more accurate. But as a first version released just days after Jev, it's "a really great start for something big." The context makes it more remarkable: Jev's team spent ~3 years in stealth building the engine and decision model, and open-source "cloned it in like five days."

Claims checked: the live repos back this up — laya (~11K stars, Apache-2.0, created Sep 18 — three days after Jev) and laya-mlx (~4K stars), whose native MLX runtime advertises 7–14ms decisions on an M3 Max — no text generation, no PyTorch, no cloud. The "faster than Jev" claim holds on local hardware.

📝 The API: States, Questions, Typed Answers 9:57

Jev (now generally available, no waitlist) takes two inputs: states and questions. Questions are JSON with three types — choice (pick an option), score (position on a scale), and null (yes/no). You provide instructions, reference state variables in quotes, and define criteria — the definition the model uses to decide.

The walkthrough example is "is food a sandwich?": with food = hamburger it returns 94% true / 6% false; swap in avocado toast and it flips to 6% true / 94% false — per your own definition. The raw response carries the model, answer, token count, request ID, and evaluation time (93ms for that call). Laya runs the same shape — a slightly more complex email-routing example (which department, urgency, refund request) returns billing at 94% confidence in 39ms — roughly three times faster than Jev's timing on the comparable call.

⚖️ Verdict: The Open System-1 Future 11:55

The closing argument is about where this is heading: computer-use and voice agents where a model classifies what to click or say in tens of milliseconds. "It's not going to be closed source anymore — it's going to be literally so fast and so free and open source, and you can run it right inside your computer." A three-year stealth project was cloned in under a week; the future of System 1 classification is open, local, and cheap.

The host is clear-eyed about the current trade-off — Laya trails Jev on accuracy today — but "the future is bright for open source and open-weights lovers." For a model that decides 30 times a second on your own machine at no cost, that's a strong opening move.

💡 Key Takeaways

  1. System 1 ≠ LLM. Decision models return typed, structured answers for classification — no text generation, so they structurally can't hallucinate.
  2. Laya is Jev's open twin. Convai Innovations shipped it days after Jev (Sep 18 vs Sep 15), Apache-2.0, ~11K stars.
  3. It's fast on local hardware. ~30 decisions/sec in the Snake demo, sub-33ms per decision; the MLX runtime hits 7–14ms on M3 Max.
  4. It's honest about accuracy. Laya is slightly less accurate than Jev today — a first version, cloned in under a week.
  5. The swap is a one-shot agent job. Claude Code swapped Jev for Laya in the browser-use demo "almost one-shotted."
  6. Decisions are absurdly cheap. A full Google Flights booking via Jev + browser-use: ~7 seconds, a fraction of a cent.
  7. The API is three types. Choice (pick), score (scale), null (yes/no) — states + questions + your own criteria.
  8. The future is open and local. Closed System 1 models now have free, self-hosted alternatives — the lock-in window didn't last a week.

🔗 Resources & Links

Source video: youtube.com/watch?v=kWToHpdxScE. A companion piece to the Jev deep dives — this covers the open-source counterpart, Laya.

⏱️ Timestamp Index

0:00 Snake demo (30 decisions/sec)
0:28 What System 1 models are
1:07 Jev demos: Mario, leads, flights
2:47 Swapping Jev → Laya
6:18 Laya vs Jev comparison
7:49 System 1 vs System 2 (Kahneman)
9:57 The API: states & questions
11:55 The open System-1 future
☰ View all