Skip navigation
Jev has been exploding in popularity recently.
0:00 / 0:24

Jev has been exploding in popularity recently.

rody

@0x_rody5.2K followers

Visit on X
2,489 likesDownloadOriginal post

350,605 views

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren’t sure how to start experimenting with it, just copy this checklist: 1. agent-desktop Desktop automation. Read the system's accessibility tree, judge which button, menu, or input field to click next. 2. typesafe-mario Have Jev play Super Mario. No screenshots—just read the structured state in the emulator's RAM, then decide to run, jump, or dodge. 3. jev-drone Use Jev to control a drone. The underlying flight control still handles stability and safety; Jev just does higher-level judgments like climbing, braking, and navigating obstacles. 4. OneVOneJev 1v1 FPS in the browser. Every decision tick, judge movement, view angle, aiming, firing, and jumping. 5. jev-trader High-frequency market making on Monad testnet. Jev judges the next buy or sell based on spreads and trade direction, with model latency around 81ms. 6. Prism Doesn't directly have Jev place orders. It judges states like toxic flow, market pressure, mean reversion, etc., then hands off to the original strategy. 7. neo4jev Stuff Jev into a knowledge graph. At each node, judge the most worthwhile edge to take next, then follow it all the way. 8. jev-curate Use Jev to screen training data. For JSONL / Parquet, first judge quality, relevance, and risk, then decide which ones go into the next training round. 9. Canny Prevents Coding Agents from stubbornly claiming they're done. Look at tool outputs, code diffs, and test results, then judge if the completion claim is reliable. 10. killmyidea Input a startup idea, and Jev scores it from multiple angles, finally giving you KILL, FIX, or SHIP. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

19 Comments

Comments from the original post on X (Twitter)

  • rody's profile picture

    @0x_rody

    join substack to receive AI alpha, fresh model templates and copy-paste configs👇

    1 like

  • Romain Pellerin🇫🇷🇺🇸's profile picture

    @rom1_pellerin

    Nice list, will definitely try Prism and Canny. We just released Jev-enabled to triage and route prompts to the right model(s). Would love your feedback on the tool!

    1 like

  • Deep's profile picture

    @irastech

    desktop automation finally made sense to me when i stopped guessing at coordinates and started reading the accessibility tree.

    1 like

  • WAGMİ 100x💎's profile picture

    @gemsnper

    accessibility tree > screenshots for agent reliability — cheaper, deterministic, zero vision hallucinations. real question: how far is jev from executing on-chain actions? an agent that reads a dexscreener alert and swaps autonomously is the actual endgame.

  • Jay Zhou's profile picture

    @jayzhoupro

    the accessibility tree works until an app paints its own ui and leaves no tree to read. does agent-desktop fall back to vision there?

  • Nitiksh · NTXM's profile picture

    @Nitikshofficial

    That agent-desktop item is the real unlock on the checklist. Once the agent can read the accessibility tree and pick the next button or menu instead of guessing from pixels alone, the loop gets a lot less brittle. The failure mode I keep hitting on Windows is not "can it click". It is wrong-window clicks, focus stealing, and no clean stop when the agent is about to trash the focused app. Observe, ground to an element id when you can, then act, with an activity trail you can audit. NTXM Agent's Operator path is my early take on that (accessibility + set-of-marks, real terminal sessions, Keep/Revert on file edits). Still in development. Operator notes:

  • Hafiz Siddiq's profile picture

    @SiddiqAtActyte

    The interesting shift is from code completion to evaluated decisions. Which Jev workflow has been most reliable in practice: UI control, game agents, or judging its own tool outputs?

  • ShadowAguy's profile picture

    @shadowaguy

    The coding loop diagram looks clean but the desktop automation step is doing the real heavy lifting. How much of the value is the agent writing code versus the agent actually executing on a live system?

  • Brian Hadu's profile picture

    @BrianHaDu

    what’s been the most surprising result from using the agent-desktop so far?

  • 拾光的 AI 应用观察's profile picture

    @ArvinthCsk93650

    agent-desktop 那个 accessibility tree 读法的坑我踩过,按钮层级一深判断就飘,得配合视觉兜底。这个checklist倒是把入口讲清楚了👍

  • MINT's profile picture

    @MINTr5dw

    smart, semantic, diff, test ‘grep’

  • Misha_Cripto's profile picture

    @MishaAi333

    "Ten blueprints and a Mario-playing agent is the most honest demo of decision-making I've seen — nobody ships a README that fun. The Super Mario one reading RAM instead of screenshots is the real flex here."

  • morph's profile picture

    @morpphhhaw

    these are so alphas repos, thank you!

  • 安叫兽|Bird🕊️ 🔶 BNB's profile picture

    @ajs6888

    刚拿到权限的人,照着这份清单试不容易迷路

  • Brjan | AI Builder's profile picture

    @MrBrjan

    the checklist could be clearer, mentioning specific use cases would help a lot

  • Yiqi's profile picture

    @DeepcakeMini

    很齐全了!

  • Ctl-Alt-Del's profile picture

    @drop_database69

    They are open weights; self host people.

  • notgwapo's profile picture

    @notgwap0

    sounds like a solid start. lowkey curious what else you can unlock with that API. 👀

  • promptgm's profile picture

    @prompter_vm

    copy-paste configs alone gonna save me hours of tweaking subbed send that alpha bro