Aisha

[Aisha @AishaGreyratt]

@usehazeai I want to build an autonomous AI ops team managing 10,000+ project sites, finding blockers, investigating discrepancies, coordinating specialized AI agents, assigning actions, and escalating issues before they delay deployment.

[Crypto带土 @daitu0822]

Sub2Api的作者是我目前为止见过最牛逼的！

源码每天坚持日更！而且还都是更新的很实用的东西！

我每天睡醒就两件事，打开Codex升级Sub2Api与检查代充网站有没有BUG！

有想做中转站的可以用Sub2Api源码，Ai一键部署，部署完可以对接我中转站，实现躺着也赚钱。

源码地址：https://t.co/358Xklnds4

[Aisha @AishaGreyratt]

@usehazeai I want to build an autonomous AI ops team managing 10,000+ project sites, finding blockers, investigating discrepancies, coordinating specialized AI agents, assigning actions, and escalating issues before they delay deployment.

[0xMarioNawfal @RoundtableSpace]

Someone open-sourced a crypto trading bot on GitHub, completely free.

It’s called Cabbage: a spot trading bot you can backtest, paper-trade, or run live with one command.

Astra (GPT-6) built it. Jev runs it.

Astra handles the reasoning and code. Jev returns one decision in milliseconds: BUY, HOLD, or SELL. Below 0.80 confidence, it waits.

1.⁠ ⁠Signal engine
RSI 14 + EMA 12/26 confluence using closed candles only.

2.⁠ ⁠Hard risk rules
Fixed position size + percentage stop-loss on every entry.

3.⁠ ⁠Backtesting
Replays historical candles one by one and generates a full HTML report.

4.⁠ ⁠Paper trading
Uses live exchange data with simulated fills and zero money at risk.

5.⁠ ⁠Live trading
Places real orders through any exchange supported by CCXT.

6.⁠ ⁠Doctor command
Checks your config and exchange connection before any trade is placed.

State is stored in SQLite per market and pair, so restarting doesn’t wipe your positions.

Built on Investing Algorithm Framework 9. Apache-2.0.

Fork it and make it yours.

⁠ https://t.co/fpuIdcLBnY ⁠

[sopersone @sopersone]

I OPEN-SOURCED MY CRYPTO TRADING BOT ON GITHUB. 100% FREE

It's called Cabbage. A spot trading bot you can backtest, paper-trade and run live, one command each. Full step-by-step setup guide.

It runs on two models:

> Astra (GPT-6) built it. Smart but slow. It thinks, writes the code, explains every decision.
> Jev runs it. Jev doesn't talk. One word and a probability, in milliseconds. BUY, HOLD or SELL. Under 0.80 it waits.

Here's what's inside:

1. Signal engine

RSI 14 + EMA 12/26 confluence. It only reads closed candles, so no fake signals from a candle that's still moving.

2. Hard risk rules

Fixed ticket size and a percentage stop-loss on every entry. The bot can't size up because it "feels confident".

3. Backtest → HTML report

Event-driven backtest that replays history candle by candle, like it's trading live. You get a full HTML report at the end.

4. Paper trading

Real exchange data, local fills, zero money at risk. Run one iteration to test, then leave it running.

5. Live trading

Real orders on any exchange CCXT supports. Your keys stay in your own .env file.

6. Doctor command

Checks your config and exchange connection before you trade. No orders placed.

State is saved in SQLite per market and pair, so a restart doesn't wipe your positions.

Built on Investing Algorithm Framework 9. Apache-2.0, fork it and make it yours.

https://t.co/0OeUCyavnD

[Roan @RohOnChain]

send this 24/7 AI trading agent prompt to claude opus 5.5.

it will probably make you a lot of money.

you're welcome:

[Berryxia.AI @berryxia]

卧槽，成功开通Muse 不到1分钟。
刚刚刷到老杨说使用Google Gemini 来开通Muse.
赶紧去搞啊，可以送10亿token啊！

【Muse AI开通教程】

试了一下，做了一个视频教程。核心关键：大家首先要准备2个东西。

1. 要有Google的Gemini Pro账号
2. https://t.co/uhQZvlJXMN 登录Pro账号后，点击对应的Spark Beta版本测试版

登录进去后，给它发送一句话：“帮我使用远程桌面打开Google官网，首页或者之类的这种就都可以。”

输入对应的Muse AI官网，然后使用谷歌邮箱登录，输验证码，就可以了，很简单。

[0xMarioNawfal @RoundtableSpace]

JEV IS EXPLODING ACROSS GITHUB.

10 THINGS PEOPLE HAVE ALREADY BUILT WITH IT:

 1.⁠ ⁠JEV-TRADER — LIVE TRADING BOT ON MONAD, 1,911 STARS
⁠ https://t.co/QCMOd4iODS ⁠

 2.⁠ ⁠JEV-ULTRAFAST — BROWSER AGENT THAT DECIDES EVERY CLICK, 16,758 STARS
⁠ https://t.co/snYJYfMbaB ⁠

 3.⁠ ⁠JEV-DOOM-AGENT — PLAYS DOOM BY MAKING TACTICAL DECISIONS EVERY FRAME
⁠ https://t.co/13ATssVuDN ⁠

 4.⁠ ⁠JEV-T-REX-RUNNER — PLAYS THE CHROME DINOSAUR GAME AUTONOMOUSLY
⁠ https://t.co/Zi72SfEWro ⁠

 5.⁠ ⁠TYPESAFE-CHESS — JEV VS A SEARCH ENGINE IN CHESS
⁠ https://t.co/JA7R0h2X0i ⁠

 6.⁠ ⁠JEV-DRONE — CONTROLS A SIMULATED DRONE THROUGH AN OBSTACLE COURSE
⁠ https://t.co/FyVciTDwo8 ⁠

 7.⁠ ⁠TAX-DOC-CLASSIFIER — CLASSIFIES IRS FORMS AT ROUGHLY $0.001 PER PAGE
⁠ https://t.co/CYYY4wvzPM ⁠

 8.⁠ ⁠KILLMYIDEA — SCORES STARTUP IDEAS AND RETURNS KILL, FIX OR SHIP
⁠ https://t.co/VHc8jSwVun ⁠

 9.⁠ ⁠JEV-CURATE — FILTERS 1,500+ DATA ROWS PER SECOND
⁠ https://t.co/wzOn7NrVgU ⁠

10.⁠ ⁠PG-JEV — LETS YOU ASK POSTGRES TABLES QUESTIONS IN PLAIN ENGLISH
⁠ https://t.co/tZ5bulI45z ⁠

THE INTERESTING PART: NONE OF THESE NEED JEV TO WRITE PROSE.
JEV JUST MAKES THE DECISION.

[codila @0xCodila]

Send this Jev prompt to any LLM or AI agent

It sets up Jev → analyzes you → finds where you waste time and money → upgrades your AI setup beyond 95% of people...

Copy this now. Thank me later:

[そら @sora_biz]

使い切れてますか？

Google AI Proの「5TBストレージ」特典

SSDはAI需要で高騰中。

だから今回のColab特典（月200CCU）と組むのが最高なんです。

巨大オープンLLMをDriveに置き、Colabから即マウント。

ローカルを1ミリも使わず、ノートPCで試せる

Gemini目当ての方、寝かせるのはもったいない

[Aisha @AishaGreyratt]

@Da7_Tech I want to build an autonomous AI ops team managing 10,000+ project sites, finding blockers, investigating discrepancies, coordinating specialized AI agents, assigning actions, and escalating issues before they delay deployment.

[Aisha @AishaGreyratt]

@edinsoncode GEMINI I want to build an autonomous AI Management 10,000+ project sites, finding blockers, investigating discrepancies, coordinating specialized agent, assigning actions, and escalating issues before they delay deployment. Would love to see what Gemini

[atomic.chat @atomic_chat_hq]

Local Laya moggs Jev at @grok 4.7-built Tetris 🧩

An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air!

Run AI models locally -> https://t.co/RbcCOIgVkj

[雪踏乌云 @Pluvio9yte]

最近Jev爆火，拿到 Jev API 还不知道怎么玩的，可以按这个清单抄。

1. jev-ultrafast
Browser Use 做的高速浏览器 Agent。Jev 每一步只判断「做什么、点哪个元素」，要打字才叫小模型。Google Flights 搜一次航班大约 7 秒。
https://t.co/IBPb4LBRQh

2. fast-jev-compaction
给 Claude Code 做上下文压缩。每次工具调用先让 Jev 判断还有没有用，没用的删掉，留下来的原文不重写。
https://t.co/qbPTr3TFTB

3. json-render
Vercel Labs 的生成式 UI 框架。实验里 Jev 不逐 token 写 JSON，只负责选组件、属性和布局。
https://t.co/iK0x89svV1

4. typesafe-mcp
最适合刚拿到 API 的人。把 Jev 接进 Claude Code、Claude Desktop、Codex 和 Pi，随时做 Choice / Score / Noul。
https://t.co/XU16Z4xTNb

5. jev-mcp
现成的 Agent 判断工具箱：事实核验、内容筛查、语义排序、分类和信息提取。
https://t.co/Ns9tNWB4st

6. SemDecide
把 Jev 做成命令行。Shell 里直接分类、打分、过滤，适合接爬虫、CI 和数据流水线。
https://t.co/KvNFnjINNj

7. jev-codex-router
先让 Jev 判断这一轮编程任务有多难，再决定模型档位、推理深度和速度模式。
https://t.co/XJWyrbzusf

8. Winnow
给 Claude Code 做上下文垃圾回收。Read / Bash / Grep 吐一大堆时，Jev 先判断哪些真和当前任务有关。
https://t.co/cs8CtPcXq8

9. jev-review
代码审查前先过一遍 Jev，把高风险改动挑出来，再交给更贵的大模型或人。带本地看板。
https://t.co/dW0nySEIp2

10. Blink
把 Jev 当代码库导航器。每走到一层目录，就判断哪些文件和当前问题最相关，再继续往下找。
https://t.co/ZuOt4Yvpds

11. agent-desktop
桌面自动化。读系统无障碍树，判断下一步该点哪个按钮、菜单或输入框。
https://t.co/uctY97plME

12. typesafe-mario
让 Jev 玩《超级马里奥》。不看截图，直接读模拟器 RAM 里的结构化状态，再决定跑、跳、躲。
https://t.co/tzAGfK9BBE

13. jev-drone
拿 Jev 控无人机。底层飞控继续负责稳定和安全，Jev 只做爬升、刹车、穿越障碍这类上层判断。
https://t.co/lRZ9LuWc3i

14. OneVOneJev
浏览器里的 1v1 FPS。每个决策 tick 都要判断走位、视角、瞄准、开火和跳跃。
https://t.co/l4iHbyH9uU

15. jev-trader
Monad 测试网上做高频做市。Jev 根据价差和成交方向判断下一步买还是卖，模型延迟大约 81ms。
https://t.co/tGAVNWR98u

16. Prism
不直接让 Jev 下单。它判断 toxic flow、市场压力、均值回归之类的状态，再交给原来的策略。
https://t.co/LP0T9rDAWi

17. neo4jev
把 Jev 塞进知识图谱。每走到一个节点，判断下一条最值得走的边，再一路找下去。
https://t.co/Qy1RUgi8oS

18. jev-curate
拿 Jev 筛训练数据。JSONL / Parquet 先做质量、相关性和风险判断，再决定哪些进后面的训练。
https://t.co/ez9fXeTtEu

19. Canny
防 Coding Agent 嘴硬说自己做完了。看工具输出、代码 diff 和测试结果，再判断完成声明靠不靠谱。
https://t.co/O3OQZ4NZ6Q

20. killmyidea
输入一个创业点子，Jev 从多个维度打分，最后给你 KILL、FIX 或 SHIP。
https://t.co/pR4VkDrz54

[ComfyUI @ComfyUI]

Qwen-Image-2.1 is now supported in ComfyUI!

Open weights. One 7B checkpoint that generates and edits.

→ Image generation at native 2K
→ Instruction editing from up to 10 reference images in a single pass
→ RGBA output, alpha included

[Md Ismail Šojal 🕷️ @0x0SojalSec]

New Uncensored Qwen-Image-2.1 SoTA image model & you can run locally at home (Q4_K_M is 4.29 GB)

- Open weights yesterday, Uncensored overnight
- refusal layer removed
- edit with up to 10 reference images
- native transparency (stickers, cutouts, no extra mask step)
- ComfyUI + city96 GGUF loader.

[Aisha @AishaGreyratt]

@edinsoncode INTERESTED

[Nahid @nahid_pro09]

Kaggle is giving 30 HOURS of FREEE GPU every week to run deepSeek models😳

30 hours of GPU compute 100% FREEEE :
- 30 free GPU hours every week
- run DeepSeek models directly in notebook
- free NVIDIA GPU (Zero local setup)
- pre-configured environment & 1-click launch

notebook link:
https://t.co/5W4uvq3Mbu

bookmark & save this post before you forget

[Vox @Voxyz_ai]

One more thing:
want Codex to build good-looking pages without having to keep saying “make it look better”? Try these 3 design Skills together:

𝟭. 𝗜𝗺𝗽𝗲𝗰𝗰𝗮𝗯𝗹𝗲

Use it when the page is built, but something still feels off.

Too bland? Use bolder. Too cluttered? Use distill. Almost finished? Use polish to refine the details. It turns “make it look better” into specific design changes Codex can make.

https://t.co/w3i4Plx8Iw

𝟮. 𝟮𝟭𝘀𝘁 𝗗𝗲𝘀𝗶𝗴𝗻

This is a Skill I put together that gets Codex to look for components and interaction references on https://t.co/SUeM4ML7vz before building a page.

I’d suggest packaging your own go-to component library into a Skill, too. It doesn’t have to be https://t.co/SUeM4ML7vz.

Focus on the one or two sections that carry the page: a hero, a set of pricing cards, or a product showcase. Pick what fits, then adapt it to your brand, content, and existing project.

𝟯. 𝗨𝗫 𝗔𝘂𝗱𝗶𝘁

A good-looking screenshot isn’t enough. Have Codex open the browser and actually use the page.

Click buttons, fill out forms, switch to a mobile viewport, and complete the user journey. Find buttons that do nothing, confusing error messages, and steps where it’s unclear what to do next. Get reproduction steps and specific fixes.

If you can’t be bothered setting up Skills, start by adding this line to the end of your task:

“Make the best decision to improve UX, DX, and AX—without breaking existing functionality.”

Ask it to weigh the user experience, developer experience, and how easily the next agent can pick up the work.

[Aisha @AishaGreyratt]

@edinsoncode Supergrok account please