I built a trading bot with Jev! Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades. It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block. Demo link → jev-trader.vercel.app
jev-plays-pokemon-red
Pokémon Red under PyBoy where ordinary Python owns the route and arithmetic and Jev is asked only at branches, with each battle turn's faint prediction scored by Brier.
- Category
- Cookbooks & Demos
- Published by
- Community
- Author
- valentynkit
- Added
- 2026-09-22
Tagscommunitypythongamesagentsevaluation
Highlights
- Code reads the Game Boy memory into a typed snapshot and hands Jev a menu of only the moves that are actually legal.
- Measured through the Vercel AI Gateway shim at about 1.3 decisions per second and $0.14 per hour at ~725 input tokens a call.
- Calibration is deliberately unpublished: the longest labeled run is n=5 turns, too small to beat a constant predictor.
- Every battle turn carries a faints_this_turn Noul labelled from RAM, and measure prints the Brier beside the base rate.
- In a recorded run Jev answered yes, 0.61 to taking Charmander and no, 0.58 to a nickname, which no fixed button survives.
Quickstart
bash
uv sync
cp .env.example .env
uv run jpp play --rom /path/to/your/red.gb --overlayWatch out
MIT-licensed. Contains no game data, so you must supply your own Pokémon Red ROM, and tests run offline against fixtures without a key.
More like this
22GitHub stars
A System One harness that plays the original StarCraft shareware mission Strongarm by reading structured game state and issuing mouse and keyboard commands from Jev choices.
Cookbooks & Demos#community#python#games
Communitytsai-sc
294GitHub stars
An experimental controller that has Jev choose NES inputs to play Super Mario Bros. from structured emulator telemetry instead of screenshots, logging every decision with probabilities and latency.
Cookbooks & Demos#community#python#games
Communitytypesafe-mario
71GitHub stars
A side-by-side T-Rex game where local Laya runs on Apple Silicon through MLX and hosted Jev uses the TypeSafe API, showing choices, latency, survival streaks, and crash replays on one course.
Cookbooks & Demos#community#python#games
Communitylaya-vs-jev
From the community
Posts from builders shipping with Jev right now.
Trading bot, one decision per block
Classifying 1,500 real emails
this model is actually insane at email classification i tested it on 1500 of my own emails to see how well it works and I am blown away
@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
Fast browser use with Stagehand
we built blazing fast computer/browser use with Jev + @Stagehanddev. this task cost $0.001 and executed at near instant speed (in a remote browser btw) the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand Show more
@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
LLM-as-a-judge, sped up
Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)
@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
Instant compaction with Jev
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant
A Claude session from 1M to 86K tokens
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be Show more
found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant