User repository on GitHub
TypeSafe Jev controls original StarCraft shareware through keyboard and mouse with recorded action probabilities.
- Forks
- 4
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Cookbooks
Jev plays StarCraft shareware
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.
- Stars
- 28
- Language
- Python
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- phyous
- Last verified
- Sep 2026
About this project
A TypeSafe System One harness for Strongarm, the first combat mission in the original StarCraft shareware campaign, with a game recording and Jev's actual action probabilities. Inspired by TypeSafe's Doom demo.
Quoted from the project's README. Read the full README.
Used inJev for Gaming
Highlights
- Jev completed Strongarm on development attempt 16, and the captured original victory screen was visually reviewed.
- The verified run recorded 421 model decisions, 424 API attempts, 9,445,640 input tokens, and a 382.95 ms median latency.
- The game is paused during state reads and inference, and Jev receives structured observations while screenshots are only for viewers.
- The model was requested as jev-latest and resolved to jev-1.13.0, with 3,867 game frames captured over 17 min 37.88 sec.
- Runs the 1998 Windows executable inside BottleShip and needs Python 3.11+, Node/npm, Chrome with WebGPU, and FFmpeg.
Quickstart
bash
python3 -m venv .venv
source .venv/bin/activate
pip install -e .
scripts/setup-runtime.sh
scripts/start-runtime.sh
python -m tsai_sc.run --env-file "$HOME/.config/tsai-sc/env" --run-dir runs/my-attempt --max-requests 2000Watch out
MIT-licensed harness; BottleShip is Apache-2.0 and StarCraft assets are Blizzard's, not included. Tested on macOS Apple Silicon, and the single successful run does not establish a win rate.
Questions about this entry
Short answers drawn from the linked project or page.
One win. Attempt 16 was the development attempt that first reached the original engine's committed victory outcome, and the earlier attempts include interrupted runs and runtime faults. The README says outright that attempt 16 does not mean sixteen completed matches or sixteen model defeats, and a single run sets no win rate.
The winning run recorded 421 model decisions over 17 minutes 37.88 seconds, 424 API attempts including 3 rejected responses, and 9,445,640 accounted input tokens including those rejected ones, at a 382.95 ms median API latency, with 3,867 game frames captured.
It receives structured observations of owned units, visible enemies, resources, and economy, then an intent choice among Economy, Engage, Explore, Reposition, and Continue, with a second choice inside the selected category. The prompt carries ordinary StarCraft guidance but no enemy-base coordinates and no predetermined mission route.
The documented path is narrow. It needs Python 3.11 or newer, Git, Node and npm, Chrome with WebGPU, and FFmpeg, was tested on macOS Apple Silicon, and setup downloads a pinned BottleShip revision verified by SHA-256 under an ignored .runtime directory. The separate Economy and Army schedule is still called experimental.
Strongarm, the first combat mission in the original StarCraft shareware campaign: destroy the rebel base on Chau Sara on a 96x64-tile map. The player begins with eight Marines, four SCVs, two Barracks, a Command Center, four Supply Depots, a Refinery and an Engineering Bay; enemy locations enter Jev's observations only when visible.
Success requires the original engine's committed victory outcome plus a captured, visually checked original victory dialog, and the evidence verifier passed. Release v0.1.0 ships an 8x video, a full 1x video, the victory screen and a reproducible evidence bundle with the manifest, decisions, trace, referenced frames, result and verification report.
No to the screen: Jev receives structured owned and visible state, while screenshots are recorded only for viewers, and the game is paused during state reads and inference. The harness independently implements the structured-state pattern shown in TypeSafe's Doom demonstration and does not use TypeSafe's Doom harness code.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Software Bombe and live Enigma demo where Jev ranks cribs and judges plaintext.
ag_212 pointsShow HN: Jev as the Bletchley Park Analyst: A Software Bombe on EnigmaRead the thread on Hacker NewsHacker News: Show HN for public Minecraft PvP where a diffusion LM picks moves from structured state.
2 pointsShow HN: Minecraft PvP against DiffusionGemma-as-Jev, 24 ms per decisionRead the thread on Hacker NewsHacker News: Show HN: Jev finished a Pokémon Red run, with the Hall of Fame stats on the landing page.
pancomplex272 pointsShow HN: Jev Plays Pokémon RedRead the thread on Hacker NewsHacker News: Show HN: a mouse colony where each next move is Jev or a fixed rule.
1 pointShow HN: Jev-mice – mouse colony simulation using Jev and deterministic engineRead the thread on Hacker NewsMore Jev resources like this
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.
Jev Cookbooks#community#python#games
Community
fhshaik/typesafe-marioPython
fhshaik/typesafe-marioPythonPokémon 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.
Jev Cookbooks#community#python#games
An original Civilization II browser harness for Jev: named Choice vectors cover empire policy, cities, research, diplomacy, units, exploration, and warfare, with live decision probabilities in a Roman-themed spectator display.
Jev Cookbooks#community#python#games
Communityphyous/tsai-civ2Python
phyous/tsai-civ2PythonA 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.
Jev Cookbooks#community#python#games
Community
virajbhartiya/laya-vs-jevPython
virajbhartiya/laya-vs-jevPythonAn Apache-2.0 decision engine with a TypeSafe-compatible endpoint, document answers with source passages, and a ViZDoom demo that picks actions from structured game state.
Jev Models & Reimplementations#community#python#local
Community
deepanwadhwa/OpenDecisionPython
deepanwadhwa/OpenDecisionPythonAn independent CUDA and vLLM take on parallel typed decisions: it scores verified single-token labels with the model's own head and assembles JSON in code.
Jev Practices & Patterns#community#python#javascript
Community
kikoncuo/jevfireJavaScript
kikoncuo/jevfireJavaScriptFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.