mario-jev

Python prototype that plays NES Super Mario Bros. from structured RAM observations, with Jev answering focused movement and jump questions.

A uv-managed Python prototype that plays NES Super Mario Bros. (level 1-1 by default). Jev receives structured RAM observations and answers focused questions about movement, starting a jump, and sustaining a jump, plus timing hops under low ceilings. Code composes their answers into controller buttons. The emulator pauses while Jev responds, then advances u…

How it uses Jev

A uv-managed Python prototype that plays NES Super Mario Bros. (level 1-1 by default). Jev receives structured RAM observations and answers focused questions about movement, starting a jump, and sustaining a jump, plus timing hops under low ceilings. Code composes their answers into controller buttons. The emulator pauses while Jev responds, then advances up to four game frames by default, stopping early on landing.…

Getting started

Put your TypeSafe key in .env :

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 mario-jev

Browse all
Jev plays Mario project preview
Games & simulations
Less talking. More jumping. Watch Jev navigate Super Mario Bros. from game state.
jev-snake project preview
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.
Games & simulations
3D chess where Jev plays both sides, or you jump in.
super-jev project preview
SDKs & clients
A small, extensible decision-to-action harness for TypeSafe Jev
siftr project preview
Benchmarks & research
Fast, cheap judgment for AI coding agents: semantic search, focused reads and list picking in ~2s. CLI + MCP server on TypeSafe Jev. Benchmarked on SWE-bench.
jevclient project preview
SDKs & clients
Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
TypeSafe Python SDK project preview
Official sync and async Python client. pip install typesafe-sdk.
agent-jev project preview
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.
jev-agent-design-with-topk-logits-choices project preview
Research design for a Jev-native agent system: tool integration, speculative parameter proposals, external helper logits Top-k proposals with Jev-controlled fallback ,decision-aware hierarchical memory, and dependency-aware replanning.Feature:Jev naturallanguage conversation prototype using external helper logits and dynamic Top-k token selection.