---
title: "Builds: games, simulators, robots and devices"
type: community
source_tier: community
tags: [ideas, builds, games, robotics, simulation]
created: 2026-09-25
updated: 2026-09-25
confidence: medium
sources:
  - raw/x-repos/rmalde__minecraft-agent.md
  - raw/x-repos/teknium1__hermes-and-jev-play-minecraft.md
  - raw/x-repos/valentynkit__jev-plays-pokemon-red.md
  - raw/x/umezawakanta13-2102008904842658002.md
  - raw/x-repos/Skyvern-AI__jevscape.md
  - raw/x-repos/phyous__tsai-sc.md
  - raw/x-repos/phyous__tsai-civ2.md
  - raw/x-repos/phyous__tsai-civ2__docs-campaign-lessons.md
  - raw/x/ephraimduncan-2100524915007144289.md
  - raw/x/staskulesh-2102062632517697652.md
  - raw/x/staskulesh-2102062632517697652-image.md
  - raw/x-repos/sliday__jev-chess-algo.md
  - raw/x-repos/ARCJ137442__jev-2048.md
  - raw/x-repos/phureewat29__jev-got.md
  - raw/x-repos/lbotinelly__jev-little-airways.md
  - raw/x-repos/siroccomask__snake-jev.md
  - raw/x-repos/zebedelu__sudoku-vs-jev.md
  - raw/x-repos/Prophetlab__JevPokerBench.md
  - raw/x/Raptor_zip-2101091398447505567.md
  - raw/x-repos/lykycy123__RoboJEV.md
  - raw/x-repos/TarunTomar122__jev-askable-arm.md
jev_version: "jev-1.13.0"
summary: "Community builds where Jev picks moves in games, simulators, robot arms and sims: what it decides, reported numbers (one verified StarCraft win, sudoku and snake limits), pattern IDs."
---

# Builds: games, simulators, robots and devices

> **TL;DR** 17 builds plus 3 names (sweeps of 2026-09-23 and 2026-09-24; split from the two other builds pages on 2026-09-25) where Jev picks a move, a primitive or a label while code owns the world, the legal-move list and every number. The evidence: one verified StarCraft mission win (one success, not a win rate), no Civilization II win, sudoku solved on easy and medium boards but only 1 of 5 hard ones, a snake that traps itself. Jev is text-only, so every build here needs a harness that turns the game into text ([[concepts/state]]).

**How to read.** *Builder reports* = the builder's own numbers, one run on their own setup, unverified unless marked. Price checks use $0.042/Mtok input, output free (`verified`, [[reference/models-and-pricing]]). Pattern IDs: P24 in [[ideas/patterns-data]]; P01, P16 in [[ideas/patterns-agents]] and [[ideas/patterns-data]]; P39, P41 in [[ideas/patterns-emerging]]. Agent builds: [[ideas/builds-agents]]; browser and interface builds: [[ideas/builds-browser-and-interface]]; data and business builds: [[ideas/builds-apps]]. Failure write-ups: [[ideas/failure-reports]].

## Games

| Build | Jev decides | Builder reports | P |
|---|---|---|---|
| [Jev plays StarCraft](https://github.com/phyous/tsai-sc) (phyous) | Strongarm, the first combat mission of the 1998 shareware campaign. Structured owned/visible state (no pixels) → a command, sent as ordinary mouse and keyboard input; separate Economy and Army decision points. The game is paused during state reads and inference | **One verified mission win** (development attempt 16; evidence bundle and a visually checked victory screen): `jev-1.13.0`, 421 decisions, 17 min 37.88 s, 424 API attempts (3 rejected), 9,445,640 input tokens (≈$0.40 at list price, inferred), median 382.95 ms. The author: one success does not establish a win rate, and this is not real-time play | P24 |
| [Jev × Civilization II](https://github.com/phyous/tsai-civ2) (phyous) | Named `Choice` vectors for empire policy, cities, research, diplomacy, units, exploration and war, over player-observable state (OCR plus a read-only observer), acted through keyboard and mouse | **No verified win** ([campaign lessons](https://github.com/phyous/tsai-civ2/blob/dab97616d1b5ef2ae80d277076d14b8886eac009/docs/campaign-lessons.md)). Attempt 008 stopped at 78 responses, turn 44, on runtime faults. Early campaigns piled up Warriors until the prompt explained that production repeats; attempt 009 then lost a Settler to support costs it could not foresee until the state spelled out the arithmetic, and ended in defeat after 96 responses. Direction matches the documented numeric weakness ([[concepts/jaggedness-jev-1-13]]). **Its setup script fetches the game itself from a third-party site: describe the harness, do not follow that step** | P24 |
| [Pac-Man](https://x.com/ephraimduncan/status/2100524915007144289) (@ephraimduncan) | The turn at each junction, from the maze state as JSON, in real time | No numbers (video). Our 2026-09-24 look at the live demo (not captured, `unverified`): the game keeps running and asks about a junction far enough ahead for the answer to land in time | P24 |
| [Jev Chess](https://github.com/sliday/jev-chess-algo) ([@staskulesh](https://x.com/staskulesh/status/2102062632517697652)) | Every legal move is an option of one `Choice` (SAN → a plain-language description), so an illegal move cannot be returned; four more questions ride in the same request (king safety, plan, sharpness, a tiebreak move). Code does the counting: a one-ply hanging-piece check states conclusions ("leaving you 3 points down overall"), never numbers to subtract | Share card of 2026-09-21 (image transcribed): Jev 19, humans 6 over 25 games (16 wins, 6 draws, 3 losses); compute shown as "18.2C" (last glyph unclear, a C or a cent sign). The human side is the site's anonymous visitors: weak evidence | P24, P41 |
| [Jev × 2048](https://github.com/ARCJ137442/jev-2048) (ARCJ137442) | One `Choice` over four directions per move, deliberately with no heuristic fallback, so every move is Jev's; probability, confidence, latency and token cost shown live; prompts and board rules editable | No results in the README. The hosted demo spends the author's key up to a quota, then asks for yours | P24 |
| [jev-got](https://github.com/phureewat29/jev-got) (phureewat29; renamed from got-jev) | A Game of Thrones roleplay: a story LLM (GPT-5.6 Luna via OpenRouter) writes each scene; Jev labels it (location from a closed set, beat, mood, danger, stayed in the fiction?); header, music, art and the next prompt are functions of those answers; an in-fiction `Noul` under 0.5 regenerates the scene once | None. No licence | P01, P16 |
| [Little Airways](https://github.com/lbotinelly/jev-little-airways) (lbotinelly) | Air-traffic toy: every ~1.6 s each aircraft asks four questions in one request (route, declare an emergency?, response to others, clearance); runway occupancy is enforced in code | Lessons: terse option labels gave give-way 0.46 vs maintain 0.41; operational wording gave 0.70 vs 0.05. A raw fuel fraction got "keep cruising" until the state carried time estimates (fuel minutes vs ETA). A rough-engine "declare an emergency?" came back 52/48 at confidence 0.04 beside a 0.99 divert. $0.042/Mtok, output free (`verified`) | P24 |
| [snake-jev](https://github.com/siroccomask/snake-jev) (siroccomask) | One request per tick: nine questions (wall collision, body collision, food progress, for left / straight / right); code combines them | One run: 29 foods in 461 ticks, then trapped in its own body. The author: it sees immediate hazards only, no route through the body layout | P24 |
| [sudoku-vs-jev](https://github.com/zebedelu/sudoku-vs-jev) (zebedelu) | A bridge offers locally legal moves; Jev picks one; no lookahead or backtracking | 5 games per level (2026-09-19): easy 5/5 and medium 5/5 (98% and 97% of moves forced), **hard 1/5** (75% forced: it must guess, and legal guesses reach dead ends); $0.0157 / $0.0314 / $0.0486 per 5 games (input-token arithmetic `verified`). Mean confidence 80% on easy and medium, 67% on hard | P24 |
| [minecraft-agent](https://github.com/rmalde/minecraft-agent) (rmalde) | LLM planner sets the objective; Jev picks one action from harness-built options; Mineflayer executes | Ender Dragon from a fresh world in 8:43: 131 Jev decisions, 35 planner calls | P24 |
| [hermes-and-jev-play-minecraft](https://github.com/teknium1/hermes-and-jev-play-minecraft) (Teknium) | Same split, Hermes Agent plans | Reproduced in 7:45 for $0.963 ($0.010 Jev); controller median 211-227 ms; an LLM controller ~8x slower, ~20x the cost. Bad picks fixed by changing the options offered | P24 |
| [jev-plays-pokemon-red](https://github.com/valentynkit/jev-plays-pokemon-red) (valentynkit) | Code owns route and arithmetic; Jev only at branches | Median 621 ms (n=6, gateway shim), $0.14/hour; calibration withheld, sample too small | P24 |
| [JevScape](https://github.com/Skyvern-AI/jevscape) (Skyvern-AI) | RuneScape via ~50 coded actions: `next_action`, a `this_tick` fix-up, and when to poll next | Mean peak XP/min: random 235, Jev 197, Claude Opus 118; Jev total XP 2.1x random; 1,307 decisions, $0.17. Live: 13,402 polls, $2.22, median 0.22 s, ~$0.55/h. Authors: "The catalog carries the game knowledge" | P24 |
| [Browser game timing](https://x.com/umezawakanta13/status/2102008904842658002) (@umezawakanta13) | Next action from game state | Jev HTTP 490.3 ms median inside 1,139.8 ms state-to-action (3 responses) | P24 |

Also seen, names only (vetted 2026-09-24, no results published): [jev-doom-agent](https://github.com/lukaske/jev-doom-agent) (Jev beside a labelled offline policy; no licence at top level), [jev-gomoku](https://github.com/mizchi/jev-gomoku) (MoonBit client, Jev vs Jev), [JevPokerBench](https://github.com/Prophetlab/JevPokerBench) (Hold'em: Jev vs DeepSeek vs seven local replica routes; it says action probabilities are not win probabilities).

## Robots and devices

| Build | Jev decides | Builder reports | P |
|---|---|---|---|
| [jev-askable-arm](https://github.com/TarunTomar122/jev-askable-arm) (Tarun Tomar) | A plain-English goal → one `Choice` per step over ~30 hard-coded primitives (plus a target object), from privileged sim state (xyz, gripper, distances), no images; a PD controller moves | ManiSkill Franka, seed 0: pick a cube (3 picks), place it on a target (7), press two buttons in order (4); ~1 s per pick | P24 |
| [RoboJEV](https://github.com/lykycy123/RoboJEV) (lyk) | Franka arm in MuJoCo, structured state not images: Choice of intent, then per-axis `negative/zero/positive` and gripper `open/hold/close`; malformed answers execute nothing | 100 episodes, 10 seeds each, Jev vs rule baseline: pick-place, push, peg 10/10 both; stack 8/10 vs 10/10; gate obstacle 5/10 vs 8/10. Failures: repeated wrong-direction moves exhausting the budget, one inconsistent answer | P24 |
| [Dual-arm robot](https://x.com/Raptor_zip/status/2101091398447505567) (@Raptor_zip) | Middle layer of three: the decision; IK and physics in code | ~500 ms per answer, ~0.5 yen per trial | P24 |

Home automation and drones with code: HA-Jev, jev-drone, jevpilot and OneVOneJev on [[ideas/repos-apps]].

## What these builds teach when advising

- **The options are the product.** Both Minecraft builds, askable-arm and JevScape win or lose on the menu code offers; JevScape's random baseline beat Jev on peak XP.
- **Keep lookahead and arithmetic in code.** Chess states material outcomes in words; Civ II lost a Settler until support costs were spelled out; Little Airways needed time estimates, not fuel fractions; sudoku hard boards and snake fail where a plan several moves deep is needed ([[concepts/jaggedness-jev-1-13]]).
- **Budget for the network.** StarCraft pauses the game during inference; Pac-Man asks ahead (`unverified`); 70-500 ms per call rules out fast control loops without a fallback ([[ideas/patterns-data]] P24).
- **One win is not a rate.** Ask for repeated runs and a baseline (StarCraft's author says so himself).
- **Tuned policies don't travel.** RoboJEV lost to rules on two tasks; label your own episodes ([[guides/testing-and-evaluation]]).

## Related

- [[ideas/patterns-data]] — P24 action selection from simulator or device state; [[ideas/patterns-emerging]] — P39 branched rollouts, P41 engine owns truth
- [[ideas/builds-agents]], [[ideas/builds-browser-and-interface]], [[ideas/builds-apps]] — the other builds pages; [[ideas/failure-reports]], [[ideas/head-to-head]] — breakages and comparisons
- [[concepts/jaggedness-jev-1-13]] — the documented weaknesses behind these results

## Sources

Links are inline in each row; the raw captures (2026-09-20 to 2026-09-25) are listed in the frontmatter. The Pac-Man latency note comes from our own 2026-09-24 vetting of the live demo (docs/sweep/2026-09-24-awesome-jev/part2.md), not from a capture.