colinmcdermott/emoji-jev

Emoji autocomplete that makes one Jev call per pause in typing: a Choice over up to 254 emojis, a Choice over eight emotions, three Scores and three booleans, answered in parallel in about 100 ms of model time per the README. TanStack Start on Cloudflare Workers through the AI SDK typesafe-ai provider, hosted on Whop, with a live demo at emoji-jev.whop.site.

colinmcdermott/emoji-jev on GitHub

Stars: 2
Forks: 0
Language: TypeScript
Last push: 17 Sep 2026

Read from GitHub on 24 Sep 2026. Counts change daily.

How it uses Jev

  const { via, key } = await resolveModel()
  const res =
    via === 'typesafe'
      ? await fetch('https://api.typesafe.ai/v1/models', { headers: { authorization: `Bearer ${key}` } })
      : await fetch('https://ai-gateway.vercel.sh/v1/credits', { headers: { authorization: `Bearer ${key}` } })
  await res.arrayBuffer()
} catch {
  // warm-up is best effort

View in src/routes/api/warm.ts

Open on GitHub

PrimitivesChoice Score

Use casesReal-time control

Jev Ultrafast (Browser Use)

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.

browser-useOpen

19k starsFlight search 7.1 s

ProjectTyped tool dispatch+2

Laya-MLX

An independent MLX port of Laya for Apple Silicon, 13.4ms median for a short English decision and 7.4ms on the multilingual checkpoint, with a Snake demo that plays at up to 75 moves per second under 1GB of memory.

mizorewwwOpen

6.1k starsShort decision 13.4 ms P50Snake demo 75.4 moves/s

ToolReal-time control

Agent Desktop

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.

lahfirOpen

1.6k starsToken reduction 78-96%

ProjectTyped tool dispatch+1

Laya-CoreML

Core ML ports of all three Laya checkpoints for Apple Silicon, reaching 4.98ms P50 on the Neural Engine for a short multilingual decision, with a Snake demo sustaining about 50 decisions per second.

mizorewwwOpen

1.4k starsShort decision 4.98 ms P50Snake demo 49-50 dec/s

ToolReal-time control

typesafe-computer-use

macOS computer-use loop that OCRs the screen, classifies the next action with Jev, then clicks. Author reports roughly $0.0002 per step.

Aaron Levin (awlevin)Open

935 starsCost/decision $0.0002, 155xLatency 0.13-0.38s

ProjectReal-time control+1

rmalde/minecraft-agent

A Minecraft agent that pairs an Astra planner with Jev as the real-time controller, with native run recording, tested routes and run verification.

rmaldeOpen

536 starsFastest run 8m 43s, -40%Decisions used 131 Jev calls

ProjectReal-time control

Menu

colinmcdermott/emoji-jev