FfhshaikGames & simulations

Jev plays Mario

Less talking. More jumping. Watch Jev navigate Super Mario Bros. from game state.

Explore repository

How it uses Jev

An experimental controller that lets TypeSafe's Jev model directly choose NES controller inputs for the original Super Mario Bros.

Getting started

Inspect the exact JSON and text that will be sent to TypeSafe without launching the game or calling the API:

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to Jev plays Mario

Browse all
mario-jev project preview

mario-jev

Games & simulations
Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.
SMade byshantanugoel13
jev-snake project preview

jev-snake

Games & simulations
An experimental Snake environment where the game engine owns deterministic rules and TypeSafe AI's Jev makes the movement decision from structured state on every tick.
IMade byiammusham1
clash-jev project preview

clash-jev

Games & simulations
A Clash Royale bot with no trained policy: Jev (TypeSafe System One) makes every decision from the live game state
BMade bybytelabs-oss32
super-jev project preview

super-jev

SDKs & clients
A small, extensible decision-to-action harness for TypeSafe Jev
KMade byKevthetech14311
agent-jev project preview

agent-jev

Benchmarks & research
AgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
MMade bymalevrigns286
reflex project preview

reflex

Benchmarks & research
A small open decision model: state + typed questions -> calibrated probabilities. A Jev / System One re-creation on Qwen3.5.
KMade bykshetrajna12133
prompt2jev project preview

prompt2jev

Agent tooling
Agent skill and CLI that turn natural language, an LLM prompt, or the code that runs one into a TypeSafe Jev decision: typed state, Choice/Score/Noul questions, and a runnable script
SMade bysumleo4
jev_stock project preview

jev_stock

Benchmarks & research
An experimental JEV-powered framework for forecasting short-term stock price direction from structured market data.
SMade bysosopop13
jev-mobile project preview

jev-mobile

Browser & computer use
Fast structured Android control loops with TypeSafe Jev and Mobile MCP
FMade byFriedjof4