PlayJev

What Jev does in PlayJev

The project describes itself this way: Gaming: open 0.8B vision-language model that reads one 448 px game frame, returns a probability over the moves the game lists in a single forward pass with no generated text, and hands its low-confidence steps to a search program, across ten browser games. In the Community additions category, Jev typically decides a single well-defined judgment, such as a label, a score or a yes/no check.

Verification

Verified. We confirmed this repository and its Jev relevance through the GitHub API and the source lists below. A specific file link has not been recorded yet.

Topics

• browser-games
• game-ai
• game-playing-agent
• html5-games
• imitation-learning
• jev
• jev-game
• multimodal
• openjev
• playjev
• qwen
• real-time
• small-models
• system-one

How Community additions projects use Jev

Projects added from community lists and direct submissions. Many are small, single-purpose experiments, which makes them some of the easiest places to see how a Jev question is framed in real code.

Related Jev projects in Community additions

1. Laya vs Jev arenaPromptEngineer48/laya-vs-jev-arenaModel comparison: races an open local model against Jev through Snake and a Mortal-Kombat-style arena, the same game code driving both.★ 24
   JavaScript
2. Jev Capability AtlasZaious/jev-capability-atlasA bilingual map of where Jev holds up and where it breaks, built from recorded API calls rather than a leaderboard. Its LICENSE is not a recognised open-source license.★ 24
   Python
3. RikkaHub PlusMiaoWuNYA/rikkahub-sillytavern-androidAndroid chat client with a built-in Jev client: it scores stored memories for relevance in batches before retrieval, and exposes Jev to the model as a callable judgment tool. Endpoint and key are set in its settings. Chinese documentation.★ 21
   Kotlin
4. minojevzeredy879/minojevOpen replica: a 547k-parameter model that answers runtime-defined `Choice` (2-255 candidates), `Boolean`, and `Score` questions with dev-calibrated distributions in one forward pass and zero output tokens, trained from scratch on CPU with committed datasets, predictions, and ECE results (maze 0.016).★ 25
   Python
5. Agent Chaperoneagent-chaperone/agent-chaperoneAgent safety: MCP proxy plus hooks that screen a tool call before it runs and a tool result before the agent reads it, with 45 test files behind it.★ 20
   TypeScript
6. jevscan-evmdevtooligan/jevscan-evmProduces a heat map of likely bugs in EVM code. The author's own warning: a proof of concept whose code they did not read.★ 26
   Python

See all 156 Community additions projects →

Where we found it

• yibie/awesome-jev
• MrJev/awesome-jev