User repository on GitHub
An autonomous game-playing decision engine for Tibia (Open Tibia / OTServ) powered by TypeSafe AI's Jev System One model.
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Demos & Experiments
TibiaJevBot
Autonomous Tibia bot that polls OTClient game state every 250ms, asks five parallel Jev survival, targeting, spell, and movement questions, and executes the returned actions.
- Stars
- 2
- Language
- TypeScript
- License
- MIT
- Published by
- Community
- Author
- GabrielBigardi
- Last verified
- Oct 2026
About this project
An autonomous game-playing decision engine for Tibia (Open Tibia / OTServ) powered by TypeSafe AI's Jev System One model. Unlike conversational LLMs that take 2-3 seconds to generate text, Jev returns typed probabilistic judgments in 250ms, making it fast enough to keep pace with Tibia's 200ms global cooldowns, monster combos, and kiting mechanics. You can immediately watch Jev fight in an Ankrahmun Dragon Lair simulation directly in your terminal:
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- TypeScript
Highlights
- Polls HP, mana, position, and monsters from OTClient Lua every 250ms and posts the game state to a local Node server.
- Asks survival, lethal danger, target, offensive, and movement questions together and converts answers into game actions.
- Handles healing spells and potions, wounded-target priority, strike and area runes, auto-attack, and kiting steps.
- Ships a mock Dragon Lair simulation plus tests for emergency healing, targeting, and mana recovery.
Watch out
Built for Open Tibia servers through OTClient Lua, not official Tibia; ticks need the local bot server and every decision still needs a Jev key. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
The README positions ~250ms typed judgments against multi-second generative text so decisions can keep pace with short global cooldowns, monster combos, and kiting. Network and key latency still apply per tick.
Copy the Lua module into OTClient, start the client and bot server on port 3000, then start the bot from the menu. The Lua side posts game state and the server replies with executable actions.
Run npm run simulate for a terminal Ankrahmun Dragon Lair fight with no OTClient, and npm test for healing, wounded-target priority, and mana-recovery checks before running the live server.
It asks survival healing, lethal-danger, target priority across visible monsters, offensive spell or rune, and kiting movement together, including potion use, strikes, area runes, and directional steps.
Run npm run simulate to watch Jev fight in an Ankrahmun Dragon Lair mock game harness directly in your terminal, with no client or server setup. npm test separately verifies emergency healing at critical HP, wounded-target prioritization and mana recovery.
It listens on port 3000 for game snapshots at /tick. The Lua module polls g_game and g_map every 250ms, packages HP, mana, position and monsters into JSON, and posts them; the server answers with an actions JSON that the client executes.
Copy the lua/jev_bot folder into your OTClient modules directory, launch OTClient and log in, then click the Jev AI Bot button on the top menu and Start Jev Bot. The bot then streams ticks to http://localhost:3000/tick and executes Jev's decisions.
More Jev resources like this
29.3kGitHub stars
The Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Community
trycua/cuaRust
trycua/cuaRust269GitHub stars
Three AI trading bees race each other on OKX perpetual futures. Every decision comes from Jev picking one move from the moves that are legal right now, and every order then passes a risk layer written in plain code. Paper by default, with real market prices.
Jev Demos & Experiments#community#jevbest
Community
imikerussell/beebotsTypeScript
imikerussell/beebotsTypeScript123GitHub stars
Electron desktop browser where Jev picks the next executable action from a page's observed controls while a separate text model plans; deterministic code builds the action space, validates responses, dispatches input and keeps receipts.
Jev Demos & Experiments#community#jevbest
Community
michaelswissa/jevryTypeScript
michaelswissa/jevryTypeScript75GitHub stars
A Node package that distils Jev-style typed answers into small local classifiers, trained either from saved labels or from a Jev teacher, then served in Node or a browser worker.
Jev Demos & Experiments#community#jevbest
Community
AndrewPrifer/jimothyTypeScript
AndrewPrifer/jimothyTypeScript64GitHub stars
Turns a Playwright trace into a narrated demo video through a chainable pipeline - speed control, subtitles, TTS, click and cursor overlays, zoom - with ffmpeg doing the render.
Jev Demos & Experiments#community#jevbest
98GitHub stars
Self-hosted Docker service and web UI that packages Laya structured-decision inference behind a compatible System One endpoint.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
1Panel-dev/laya-serverPython
1Panel-dev/laya-serverPythonFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.