User repository on GitHub
System One for NPCs — hot-swap scripted NPC decision points with decision models (Jev/TypeSafe, OpenAI Decisions).
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Repos & SDKs
Sys1npc
A small, mechanics-free System One decision core for game NPCs: the adapter supplies an observation and opaque legal actions, and a scripted or Jev provider picks one, with a deterministic offline provider for tests.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- SafiullahRattar
- Last verified
- Oct 2026
Used inJev for Gaming
- Languages
- Python
- Capabilities
- Open sourceRuns locally
Highlights
- Core boundary is battle.action: the adapter supplies an observation plus complete, opaque legal actions and a provider picks exactly one.
- Ships a deterministic offline provider and a Jev provider whose wire format is verified against TypeSafe's first-party docs.
- The shared coordinator validates membership and correlation and bounds how long a provider may take.
- The coordinator knows no Pokémon mechanics: it never reads the observation and never decodes action ids.
- Foundation only: the FireRed hook, patch and bridge are not implemented and there is no shipped CLI.
Watch out
README and GitHub metadata reviewed 2026-10-17; the FireRed hook, patch and bridge, the CLI and the Jev request and response formats are only described as missing or future work, so nothing can be run against a real game yet.
Questions about this entry
Short answers drawn from the linked project or page.
A mechanics-free decision core for game NPCs, built as the foundation for a FireRed trainer-battle AI: given an observation and legal actions, a provider picks one action.
The project includes a Jev provider whose wire format is verified against TypeSafe's first-party documentation, alongside a deterministic offline provider used for testing.
The game adapter asks with a game-specific observation and a set of complete, opaque legal actions, each an id plus description, and a provider returns one chosen action.
It checks that the chosen action is a member of the legal set and that the response is correctly correlated, and it bounds how long a provider may take to answer.
No. The README says the coordinator knows no Pokémon mechanics, never reads the observation and never decodes an action id; the game adapter owns legality and state decoding.
Not yet. The repository is a foundation only: the FireRed hook, patch and bridge are not implemented, there is no working game integration and no shipped CLI.
It is MIT-licensed Python with 0 stars and 0 forks, created 2026-10-14 and last pushed 2026-10-15. The deterministic provider runs offline; the Jev provider calls TypeSafe over HTTPS.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev picks which Apple HIG guides go into the agent's context. NatashaTheRobot built a small AskHIG CLI and…
X: Three decision models, one game of Snake
X: Diogo Almeida with a16z on Jev
X: Luna plans, Jev plays poker
More Jev resources like this
Open infrastructure from the SimpleJev project for training, evaluating and deploying System 1 decision models across language and multimodal backbones: one API takes a state, question and candidate options and returns a choice with probabilities.
Jev Repos & SDKs#community#github#python
Community
SimpleJev/JevAnyPython
SimpleJev/JevAnyPythonA reproducible PyTorch stack for cross-sectional factor research: 213 mask-aware factors, cost-aware backtests and auditable reports, plus a preview typed portfolio-decision adapter in the System-One/Jev style.
Jev Repos & SDKs#community#github#python
Community
initial-d/ml-quant-tradingPython
initial-d/ml-quant-tradingPythonA 24/7 market-making system built around Jev: deterministic code computes the market state, Jev answers six atomic judgments with calibrated probabilities, and the policy engine applies thresholds while hard risk vetoes stay in code.
Jev Repos & SDKs#community#github#python
Community
buberlo/jev-traderPython
buberlo/jev-traderPythonA frozen decision server that serves Gemma 4 31B — quantized to FP8 at startup — in TypeSafe's /v1/systemone format, reading the next-token distribution instead of generating tokens. It needs one FP8 NVIDIA GPU with 80 GB and has no authentication.
Jev Repos & SDKs#community#github#python
Community
krishna-gogineni-765/deck31bPython
krishna-gogineni-765/deck31bPythonAn experimental Factorio agent in which Jev chooses goals and actions as typed questions while deterministic code owns the game rules and actuation; an offline mock loop runs with no API key and no game copy, with live and hierarchical modes documented.
Jev Agents & MCP#community#github#python
An open typed-decision layer with choice, score and noul questions, calibrated probabilities and one batched call, built as a numpy-only base with eight swappable engines. The README positions it as rebuilding Jev's closed API shape on hardware you control.
Jev Repos & SDKs#community#github#python
Community
Franzferdinan51/SystemOnePython
Franzferdinan51/SystemOnePythonFrom 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.