Generates paintings from Jev's pixel-level probability outputs.
Read from GitHub on . Counts change daily.
count = batchPixels[method] * (["rgb", "hsl"].includes(method) ? 3 : 1),
batches = [];
for (let i = 0; i < entries.length; i += count)
batches.push({
model: "jev-latest",
state,
questions: Object.fromEntries(entries.slice(i, i + count)),
});
return batches;
Browser Use's fast browser agent where Jev picks the operation and the DOM element in a single request; a small LLM is only invoked to write text when typing is required. Demoed on a Google Flights search.
19k starsFlight search 7.1 s
Attempt to run a Jev-style System One decision model locally on a single RTX 3090. Companion site at openjev.com. The repository was renamed to TheoLeeCJ/SemIf on GitHub, and the old openjev URL now redirects to it.
TheoLeeCJOpenopenjev on github.com4.1k starsJSON vs direct 5.21x slowerPeak throughput 20.03 dec/s
Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.
jarrodwattsOpenjev-trader on github.com2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block
Open reimplementation that trains a small model to choose among a changing list of text options, emitting one probability per option in a single forward pass. Ships Doom, chess and Wikispeedia demos.
Vercel CTO reports Jev saturated an existing classifier eval that had used Gemini 2.5 Flash Lite and ran about 6x faster. Original post; TypeSafe's quote-tweet is a separate item.
Malte Ubl (@cramforce)OpenRan Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite on x.com220k viewsSpeed vs Gemini 6x faster
Rust desktop automation that reads apps through the OS accessibility tree instead of pixels. Its jev-desktop skill takes a plain-language goal and has Jev pick one operation and one target element per turn, so the 150-element tree never enters the agent's context.
1.6k starsToken reduction 78-96%
