Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Something cool in edge omarchy quattro. You can type command + ` and get a dropdown terminal launching your default coding agent. I don't know why its so fun, but it is

typecraft_dev's profile picture

typecraft

26,918 subscribers

14,828 görüntüleme • 2 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

I still think Hermes agent is the most slept-on AI tool of 2026. For literally $6/mo, you can launch multiple subagents that work for you 24/7. Most people don't know you can do this, but it's a complete game-changer. Instead of one Hermes assistant doing everything sequentially, you run specialized agents in parallel, each with its own job, its own context, and its own memory. Practical example: → Research agent: scans your watchlist and competitors overnight, delivers a morning brief → Content agent: drafts and schedules your posts based on what's trending in your niche → Ops agent: manages your inbox, flags anything urgent, drafts replies for your review All three can run simultaneously and improve over time. How to start: 1. Install Hermes Terminal command: curl -fsSL | bash (can also download desktop) 2. Prompting Simply tell Hermes directly: "I want to run separate subagents for [task 1], [task 2], and [task 3]. Set them up to run independently and report back to me." For the cheapest setup, you can use a $4/month VPS with Hostinger, plug in DeepSeek V4 Flash as your default model. There isn't another AI tool with this much value in 2026. Hermes is still so underrated.
0:10

I still think Hermes agent is the most slept-on AI tool of 2026. For literally $6/mo, you can launch multiple subagents that work for you 24/7. Most people don't know you can do this, but it's a complete game-changer. Instead of one Hermes assistant doing everything sequentially, you run specialized agents in parallel, each with its own job, its own context, and its own memory. Practical example: → Research agent: scans your watchlist and competitors overnight, delivers a morning brief → Content agent: drafts and schedules your posts based on what's trending in your niche → Ops agent: manages your inbox, flags anything urgent, drafts replies for your review All three can run simultaneously and improve over time. How to start: 1. Install Hermes Terminal command: curl -fsSL | bash (can also download desktop) 2. Prompting Simply tell Hermes directly: "I want to run separate subagents for [task 1], [task 2], and [task 3]. Set them up to run independently and report back to me." For the cheapest setup, you can use a $4/month VPS with Hostinger, plug in DeepSeek V4 Flash as your default model. There isn't another AI tool with this much value in 2026. Hermes is still so underrated.

Miles Deutscher

82,643 görüntüleme • 3 ay önce

IM NOT AFRAID (of closing my terminal) ANYMORE. 1. dmux uses tmux 2. tmux is background server 3. terminal closing doesn't kill tmux 4. your coding agent keeps working 5. type `dmux` and you're right back where you were. ➡️
0:17

IM NOT AFRAID (of closing my terminal) ANYMORE. 1. dmux uses tmux 2. tmux is background server 3. terminal closing doesn't kill tmux 4. your coding agent keeps working 5. type `dmux` and you're right back where you were. ➡️

Justin Schroeder

51,893 görüntüleme • 7 ay önce

I don't know who but I can guarantee that this will awaken something in a few of you.
0:17

I don't know who but I can guarantee that this will awaken something in a few of you.

Klara

25,194 görüntüleme • 3 ay önce

Hermes Agent has a new Blank Slate setup mode. The default Quick/Full setup modes work great for most, but if you would rather build your agent from the ground up you can now start with just a provider, model, file operations, and terminal, then manually add in anything else.
0:15

Hermes Agent has a new Blank Slate setup mode. The default Quick/Full setup modes work great for most, but if you would rather build your agent from the ground up you can now start with just a provider, model, file operations, and terminal, then manually add in anything else.

Nous Research

327,299 görüntüleme • 4 ay önce

You can now build translucent dropdown menus, selects, and comboboxes on shadcn/create. Mix in your custom styles, icons, fonts, and radii and build something different. Your own preset. All it takes is a few clicks.
0:13

You can now build translucent dropdown menus, selects, and comboboxes on shadcn/create. Mix in your custom styles, icons, fonts, and radii and build something different. Your own preset. All it takes is a few clicks.

shadcn

154,078 görüntüleme • 8 ay önce

"Why is this request pending?" ⏳ Don't waste time digging through headers manually. Select the network request in DevTools and ask your coding agent to solve the mystery for you. It's that simple. Get started →
0:15

"Why is this request pending?" ⏳ Don't waste time digging through headers manually. Select the network request in DevTools and ask your coding agent to solve the mystery for you. It's that simple. Get started →

Chrome for Developers

17,331 görüntüleme • 10 ay önce

Agreed. It's why we've been building a command center in the Warp terminal so you don't need to learn tmux to manage agents. - All conversations are searchable from history - Close tabs and revisit later with session restore - Track both local and cloud agent runs
0:17

Agreed. It's why we've been building a command center in the Warp terminal so you don't need to learn tmux to manage agents. - All conversations are searchable from history - Close tabs and revisit later with session restore - Track both local and cloud agent runs

Zach Lloyd

37,857 görüntüleme • 8 ay önce

Today, AI can generate tons of code—but how do we know if it's good? That's why we built Sculptor: the first coding agent environment. Sculptor helps you catch issues, write tests, and improve your code—all while you work in your favorite editor.
0:12

Today, AI can generate tons of code—but how do we know if it's good? That's why we built Sculptor: the first coding agent environment. Sculptor helps you catch issues, write tests, and improve your code—all while you work in your favorite editor.

Kanjun 🐙

137,543 görüntüleme • 1 yıl önce

you kinda can sabergroundskate and its very fun, fakeskating with it is way faster than i thought it would be though thats really cool
0:13

you kinda can sabergroundskate and its very fun, fakeskating with it is way faster than i thought it would be though thats really cool

watter

35,342 görüntüleme • 11 ay önce

I sometimes need to remind myself how crazy cool is a project I built. It is CRAZY that you can open 500k files repo in your editor and start searching it IMMEDIATELY having results in real type as you type EVEN WITH TYPOS RESISTANCE CONTENT SEARCH AAAAAAAA
0:17

I sometimes need to remind myself how crazy cool is a project I built. It is CRAZY that you can open 500k files repo in your editor and start searching it IMMEDIATELY having results in real type as you type EVEN WITH TYPOS RESISTANCE CONTENT SEARCH AAAAAAAA

Dmitriy Kovalenko

11,640 görüntüleme • 5 ay önce

I built a design MCP server for Claude Code, Codex, and OpenCode. It searches hundreds of beautiful websites and gives your coding agent design inspiration. Launching next week.
0:10

I built a design MCP server for Claude Code, Codex, and OpenCode. It searches hundreds of beautiful websites and gives your coding agent design inspiration. Launching next week.

Hassan

28,773 görüntüleme • 2 ay önce

I don't know why this flea flicker lateral is so funny to me. Herbert is so clearly overthinking it, like a short putt you KNOW you're gonna miss. He totally hooks it, and it just kinda hangs in the air while he watches it. And then the ending. Just a stupid, fun play.
0:10

I don't know why this flea flicker lateral is so funny to me. Herbert is so clearly overthinking it, like a short putt you KNOW you're gonna miss. He totally hooks it, and it just kinda hangs in the air while he watches it. And then the ending. Just a stupid, fun play.

Robert Mays

93,651 görüntüleme • 3 yıl önce

There is something wrong, but I don't know what it is
0:17

There is something wrong, but I don't know what it is

FIGHTFLIX

183,110 görüntüleme • 10 ay önce

I made it into a QuickShell plugin for Omarchy Quattro. Sending and receiving are possible. Multiple files at once.
0:14

I made it into a QuickShell plugin for Omarchy Quattro. Sending and receiving are possible. Multiple files at once.

Bjarne Øverli

14,200 görüntüleme • 3 ay önce

Some of the smartest people I know are those who will flat out tell you when they don't know something Hasan does not fall into that category Why not say: "I'm not sure, but if it is I will stop drinking it. Its hard to check on every product I buy, but I do put in effort"
0:19

Some of the smartest people I know are those who will flat out tell you when they don't know something Hasan does not fall into that category Why not say: "I'm not sure, but if it is I will stop drinking it. Its hard to check on every product I buy, but I do put in effort"

Dan Saltman

909,972 görüntüleme • 1 yıl önce

Ever wished your AI coding agent had perfect memory? 🧠 Memory Bank is a game-changing approach that gives AI persistent memory across coding sessions. Here's how it works and why you should be using it: 🧵/
0:12

Ever wished your AI coding agent had perfect memory? 🧠 Memory Bank is a game-changing approach that gives AI persistent memory across coding sessions. Here's how it works and why you should be using it: 🧵/

Cline

64,644 görüntüleme • 1 yıl önce

Friendly reminder that --v 6 is still not the default in Midjourney So if you haven't gone to /settings and selected --v 6 from the dropdown menu, you still might be running things in --v 5.2 Once you select it --v 6 will automatically get appended to the end of your prompt 💪
0:18

Friendly reminder that --v 6 is still not the default in Midjourney So if you haven't gone to /settings and selected --v 6 from the dropdown menu, you still might be running things in --v 5.2 Once you select it --v 6 will automatically get appended to the end of your prompt 💪

Nick St. Pierre

13,998 görüntüleme • 2 yıl önce

I don't think there's a single terminal ux that handles agent swarms well With slate, you can literally use Opus 4.6 and GPT 5.4 at the exact same time But making it intuitive took a ton of work So heres a thread on how it works and how to actually use it 🧵
0:11

I don't think there's a single terminal ux that handles agent swarms well With slate, you can literally use Opus 4.6 and GPT 5.4 at the exact same time But making it intuitive took a ton of work So heres a thread on how it works and how to actually use it 🧵

akira

139,114 görüntüleme • 8 ay önce