Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Added terminal support to the OpenCode desktop app. The OpenCode server now exposes APIs for creating PTY sessions. - server buffers messages on ws disconnect - client persists buffer on unmount - tabs are unmounted when not active - only one PTY ws connection active at a time

adamdotdev's profile picture

Adam

32,822 subscribers

18,077 görüntüleme • 7 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

So I created a simple Expo app for remotely connecting to an OpenCode server (running on my mac) so I can remotely control & prompt from my iPad or phone. Not very polished but it works pretty well and its kinda interesting that you can see the feedback loop live.
1:35

So I created a simple Expo app for remotely connecting to an OpenCode server (running on my mac) so I can remotely control & prompt from my iPad or phone. Not very polished but it works pretty well and its kinda interesting that you can see the feedback loop live.

ryan vogel

50,706 görüntüleme • 7 ay önce

To the dreamers and builders shaping Rwanda with passion and hustle: the future isn’t waiting, we are creating it now. One connection and one breakthrough at a time. Click on the link to listen to the full anthem.
0:33

To the dreamers and builders shaping Rwanda with passion and hustle: the future isn’t waiting, we are creating it now. One connection and one breakthrough at a time. Click on the link to listen to the full anthem.

MTN Rwanda

1,566,084 görüntüleme • 1 ay önce

I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI on top. Now I run Claude Code from my browser. From my phone. From anywhere. Same $200/month subscription. Zero extra API costs. bunx the-vibe-companion
0:20

I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI on top. Now I run Claude Code from my browser. From my phone. From anywhere. Same $200/month subscription. Zero extra API costs. bunx the-vibe-companion

Stan Girard

693,421 görüntüleme • 5 ay önce

React tip: "use client" misconceptions (2/5) 🚫 "You cannot nest Server Components inside Client Components because "use client" turns everything into Client Components." ✅ We can pass the rendered result of Server Components to Client Components as props. Simple example: (Server Component) (Client Component) (Server Component) is designed for the client. It needs to instantly open and close when clicked. is designed for the server. It uses packages that don't work in the browser and needs to fetch data close to where it's stored without exposing credentials. So, how can we nest a component that uses server APIs inside a component that uses client APIs... without using `import`? React props to the rescue! --- (0:00) 1-4: Reminder: Importing code forms a module dependency graph. Adding dependencies to a server or client bundle. (0:23) 5-6: Reminder: Using components eventually forms a rendered component tree. (0:37) 9: Oh no! We get an error when trying to `import` a client API (useState) into a server module. (0:44) 10: We know the trick by now: Add "use client" to mark `2.js` as a client entry point. This moves the module to the client bundle and allows us to use client APIs like `useState.` (0:51) 11: But we get a new error! "use client" moved all imported dependencies into the client bundle, including our ORM package, which doesn't work in the browser. (0:59) 13: Let's refactor without changing our rendered component hierarchy. First, we move the `Cart` import to the parent file that imports `Modal`. This moves `Cart` outside the "use client" boundary and consequently the client bundle. (1:11) 15: Then, we pass down the rendered result of `Cart` as a prop to `Modal`. This allows `Cart` to be entirely rendered on the server as a Server Component before being passed down. `Modal` has no knowledge of what the `cart` prop is. Its only responsibility is placing whatever it receives into the `{cart}` slot. (1:15) 16: Finally, it's common to use the special `children` prop for a component's primary content. The key insight is that we were able to use props to retain our desired component hierarchy even though we changed our module dependency graph.
1:24

React tip: "use client" misconceptions (2/5) 🚫 "You cannot nest Server Components inside Client Components because "use client" turns everything into Client Components." ✅ We can pass the rendered result of Server Components to Client Components as props. Simple example: (Server Component) (Client Component) (Server Component) is designed for the client. It needs to instantly open and close when clicked. is designed for the server. It uses packages that don't work in the browser and needs to fetch data close to where it's stored without exposing credentials. So, how can we nest a component that uses server APIs inside a component that uses client APIs... without using `import`? React props to the rescue! --- (0:00) 1-4: Reminder: Importing code forms a module dependency graph. Adding dependencies to a server or client bundle. (0:23) 5-6: Reminder: Using components eventually forms a rendered component tree. (0:37) 9: Oh no! We get an error when trying to `import` a client API (useState) into a server module. (0:44) 10: We know the trick by now: Add "use client" to mark `2.js` as a client entry point. This moves the module to the client bundle and allows us to use client APIs like `useState.` (0:51) 11: But we get a new error! "use client" moved all imported dependencies into the client bundle, including our ORM package, which doesn't work in the browser. (0:59) 13: Let's refactor without changing our rendered component hierarchy. First, we move the `Cart` import to the parent file that imports `Modal`. This moves `Cart` outside the "use client" boundary and consequently the client bundle. (1:11) 15: Then, we pass down the rendered result of `Cart` as a prop to `Modal`. This allows `Cart` to be entirely rendered on the server as a Server Component before being passed down. `Modal` has no knowledge of what the `cart` prop is. Its only responsibility is placing whatever it receives into the `{cart}` slot. (1:15) 16: Finally, it's common to use the special `children` prop for a component's primary content. The key insight is that we were able to use props to retain our desired component hierarchy even though we changed our module dependency graph.

Delba

43,989 görüntüleme • 2 yıl önce

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.
1:15

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Rohan Paul

33,431 görüntüleme • 4 ay önce

day ???/??? ascii art generation i have successfully added a performant terminal rendering pipeline! frames are rendered as and when they are decoded now (what you see in the video is real time) here's the opening to Serial Experiments Lain on wezterm. 60 fps, locked. with zero hiccups. enjoy (ps. i added audio in post) (i'll add audio support after web app release)
1:42

day ???/??? ascii art generation i have successfully added a performant terminal rendering pipeline! frames are rendered as and when they are decoded now (what you see in the video is real time) here's the opening to Serial Experiments Lain on wezterm. 60 fps, locked. with zero hiccups. enjoy (ps. i added audio in post) (i'll add audio support after web app release)

rohit

34,345 görüntüleme • 1 yıl önce

🚀 Rocket tracking app with Expo Router and React Server Components! ◆ Started with DOM Components ◆ Migrated to native one route at a time ◆ iOS, Android, web, even runs in Expo Go! ◆ Data fetched securely on the server, no hooks needed ◆ Offline support for layouts, loading, scrolling, animations, transitions, and error states We're just getting started ⚡️
0:38

🚀 Rocket tracking app with Expo Router and React Server Components! ◆ Started with DOM Components ◆ Migrated to native one route at a time ◆ iOS, Android, web, even runs in Expo Go! ◆ Data fetched securely on the server, no hooks needed ◆ Offline support for layouts, loading, scrolling, animations, transitions, and error states We're just getting started ⚡️

Evan Bacon 🥓

25,393 görüntüleme • 1 yıl önce

Added support for colored light :D While this doesn't support *more* than one color at a time, I do plan on adding that in the future when I can figure out how to
0:36

Added support for colored light :D While this doesn't support *more* than one color at a time, I do plan on adding that in the future when I can figure out how to

blue

49,444 görüntüleme • 3 yıl önce

The Hermes Desktop App is insanely good. It's now the best way to run AI agents on your computer. Here's the full setup, start to finish. Enjoy! Chapters: 00:00 - why Hermes desktop is a game changer 00:46 - downloading and installing the desktop app 01:47 - picking your model and provider 02:52 - sessions, settings, and gateway connection 04:08 - adding a custom MCP server 04:58 - memory and context (the three-tier system) 06:52 - connecting to Telegram 09:45 - skills and tools 11:06 - the skills hub (built-in and community skills) 11:50 - creating a custom skill 14:18 - artifacts 15:11 - going from one to many agents (profiles and personas) 18:12 - agents working as a team (Hermes Kanban) 19:01 - outro I have also written an article on Hermes masterclass, the same is quoted below.
19:13

The Hermes Desktop App is insanely good. It's now the best way to run AI agents on your computer. Here's the full setup, start to finish. Enjoy! Chapters: 00:00 - why Hermes desktop is a game changer 00:46 - downloading and installing the desktop app 01:47 - picking your model and provider 02:52 - sessions, settings, and gateway connection 04:08 - adding a custom MCP server 04:58 - memory and context (the three-tier system) 06:52 - connecting to Telegram 09:45 - skills and tools 11:06 - the skills hub (built-in and community skills) 11:50 - creating a custom skill 14:18 - artifacts 15:11 - going from one to many agents (profiles and personas) 18:12 - agents working as a team (Hermes Kanban) 19:01 - outro I have also written an article on Hermes masterclass, the same is quoted below.

Akshay 🚀

102,942 görüntüleme • 1 ay önce

The Codex app server was such a brilliant stroke of foresight that really doesn't get enough love Not only are you allowed to use your chatgpt account with any harness, but you can build your own apps directly on top of theirs. They just make building on and with codex such a great experience To demonstrate this utility, I want to highlight the kitty litter app, made by SIGKITTEN. Instead of having to build the entire harness, and all the infrastructure, he's plugged into the app server for a unified experience between mobile and dev machine. When I create a session on my computer, it's automatically available on my phone. All of the chats you see in this video automatically populated when we connected to the app server. All my skills. My agents. My sessions. My folders. My prompts. They're all ready to use - automatically. Because they're exposed by the app server, along with many other endpoints. It's a great ux/dx that really deserves some love. It's almost like they want you to build on top of their products ;) Btw Litter is great 👍
0:37

The Codex app server was such a brilliant stroke of foresight that really doesn't get enough love Not only are you allowed to use your chatgpt account with any harness, but you can build your own apps directly on top of theirs. They just make building on and with codex such a great experience To demonstrate this utility, I want to highlight the kitty litter app, made by SIGKITTEN. Instead of having to build the entire harness, and all the infrastructure, he's plugged into the app server for a unified experience between mobile and dev machine. When I create a session on my computer, it's automatically available on my phone. All of the chats you see in this video automatically populated when we connected to the app server. All my skills. My agents. My sessions. My folders. My prompts. They're all ready to use - automatically. Because they're exposed by the app server, along with many other endpoints. It's a great ux/dx that really deserves some love. It's almost like they want you to build on top of their products ;) Btw Litter is great 👍

am.will

265,669 görüntüleme • 3 ay önce

Introducing Privacy TWAP It is a challenge for size traders to trade on Hyperliquid using normal TWAPs as it tends to broadcast their full position sizing. This is why such traders tend to use specialized desktop terminals that not only obfuscates their trade sizing, but also stick to tools that do not front-run them. Based's Privacy TWAP changes the game on Hyperliquid: 🔸 Orders are executed fully client-side (inside the user’s desktop client). 🔸 No one, not even us as the trading terminal can frontrun or see your execution path. 🔸 This makes TWAP execution completely private. Trade with size, trade with confidence on Based. Stay Based. Hyperliquid
0:29

Introducing Privacy TWAP It is a challenge for size traders to trade on Hyperliquid using normal TWAPs as it tends to broadcast their full position sizing. This is why such traders tend to use specialized desktop terminals that not only obfuscates their trade sizing, but also stick to tools that do not front-run them. Based's Privacy TWAP changes the game on Hyperliquid: 🔸 Orders are executed fully client-side (inside the user’s desktop client). 🔸 No one, not even us as the trading terminal can frontrun or see your execution path. 🔸 This makes TWAP execution completely private. Trade with size, trade with confidence on Based. Stay Based. Hyperliquid

Based

27,150 görüntüleme • 10 ay önce

🚨 There are more cool things in PostHog: - Max AI has evolved into PostHog AI. It can now navigate the app, create feature flags, and is automatically aware of the active tab. - PostHog AI's updated chat UI now shows its reasoning, planning, and tool calling all in real-time. - You can now schedule changes to *existing* feature flags, making it even easier to manage release conditions. - Export up to 15 second session replay clips to MP4 or GIFs. Memes not guaranteed. - Our new beta SDK Doctor will alert you when you're running an out-of-date SDK - Android and Flutter SDKs now support error tracking (beta) - Long session replays now take less time to buffer by only loading 15 mins at a time - New tab UI that shows you most recently visited pages at the top - You can now pin tabs, so you can now have pinned tabs inside your pinned tabs. We call this Tabception - Sort error tracking issues by revenue impact (if you've setup revenue analytics, so you should probably do that!) - TikTok Ads as a data source
3:54

🚨 There are more cool things in PostHog: - Max AI has evolved into PostHog AI. It can now navigate the app, create feature flags, and is automatically aware of the active tab. - PostHog AI's updated chat UI now shows its reasoning, planning, and tool calling all in real-time. - You can now schedule changes to *existing* feature flags, making it even easier to manage release conditions. - Export up to 15 second session replay clips to MP4 or GIFs. Memes not guaranteed. - Our new beta SDK Doctor will alert you when you're running an out-of-date SDK - Android and Flutter SDKs now support error tracking (beta) - Long session replays now take less time to buffer by only loading 15 mins at a time - New tab UI that shows you most recently visited pages at the top - You can now pin tabs, so you can now have pinned tabs inside your pinned tabs. We call this Tabception - Sort error tracking issues by revenue impact (if you've setup revenue analytics, so you should probably do that!) - TikTok Ads as a data source

PostHog

12,050 görüntüleme • 8 ay önce

what have I been working on for the last 2 weeks at OpenCode? we are bringing workspaces in as a first-class concept: agents will be able to run anywhere: local directory/container/worktree, remote sandbox, or anything. instead of having a single server that only knows about local directories, the server will act as a "control plane" that routes prompts to where they should go it will manage all of the sessions across these environments and provide a unified layer for all clients to interact with them we will be smart about this: it's not *only* about routing. we will sync all data from remote environments into the local control plane server. this means the remote env can be destroyed, and we will be able to later recreate a new env with exactly the same state. it's reproducible note: this is very early and experimental, the UI you see the video is just a prototype and not guaranteed to make it to prod. We hope to start shipping something soon-ish though!
1:29

what have I been working on for the last 2 weeks at OpenCode? we are bringing workspaces in as a first-class concept: agents will be able to run anywhere: local directory/container/worktree, remote sandbox, or anything. instead of having a single server that only knows about local directories, the server will act as a "control plane" that routes prompts to where they should go it will manage all of the sessions across these environments and provide a unified layer for all clients to interact with them we will be smart about this: it's not *only* about routing. we will sync all data from remote environments into the local control plane server. this means the remote env can be destroyed, and we will be able to later recreate a new env with exactly the same state. it's reproducible note: this is very early and experimental, the UI you see the video is just a prototype and not guaranteed to make it to prod. We hope to start shipping something soon-ish though!

James Long

170,530 görüntüleme • 4 ay önce

Zebra for iOS and Android are on the way! Zebra is currently available to download via electron desktop client. Our engineers have been building the next installment for Zebra. This next phase will see Zebra’s doors open for all, via their relevant App/Play Store. The video attached shows our backend work and transparency! Zebra, reclaiming your privacy one message at a time. Download today!
0:23

Zebra for iOS and Android are on the way! Zebra is currently available to download via electron desktop client. Our engineers have been building the next installment for Zebra. This next phase will see Zebra’s doors open for all, via their relevant App/Play Store. The video attached shows our backend work and transparency! Zebra, reclaiming your privacy one message at a time. Download today!

zKML

21,844 görüntüleme • 2 yıl önce

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.
0:33

This Chinese guy created agents in Claude Code for MCP servers and single-handedly serves 6 marketing agencies a month from one iPhone, earning $5,000 from each. Inside he runs a pipeline of 7 agents on Claude Sonnet 4.6 that every Monday pulls a scan of the tech stack from a selected agency, develops an MCP server for its ad accounts, and over the course of a week brings it to production code ready to connect to Claude Desktop. No DevOps, no senior developer, no project manager. Just a Mac Mini in a work corner, an iPhone in the pocket, and a single API key. And traditional dev shops keep 5 people on project rates for the same contract, while his entire P&L is tokens, dirt-cheap hosting on Cloudflare, and Calendly. 7 agents run under a shared orchestrator-router and burn about 5 million tokens a day, which in the API bill comes out to $540 a month. The Mac Mini itself sits at home and keeps the entire orchestrator running 24/7, and from the iPhone the owner connects to it through a secure remote terminal and sees the output of any session right on the smartphone screen, wherever he happens to be. His starting system prompt looks like this: "you run a solo shop for custom MCP servers for marketing agencies. you hand out read-only tasks to 6 sub-agents and own all commits and shipping yourself. sub-agents: // Hunter (finds marketing agencies of 15 to 60 people that have no MCP access to Google Ads, Meta Ads, TikTok Ads, and HubSpot) // Mapper (pulls their tech stack, identifies 3 to 5 integration pains, and simultaneously writes the technical spec for the server: which tools, resources, and prompts to export through MCP, which auth flow and rate limit) // Coder (generates an MCP server in Python through the MCP SDK, deploys 8 to 15 tools for ad accounts and CRM) // Validator (connects the server to Claude Desktop, runs real client API keys in a sandbox, and checks for compliance with the MCP spec) // Shipper (writes a README, integration guide, deployment manual, packages the server, and hosts it on Cloudflare Workers or pushes to the GitHub of the client) // Mobile (always online on the iPhone, books demo calls in Calendly, picks up hot fixes, and confirms contracts through a secure remote terminal to the Mac Mini). only 1 owner agent works on 1 contract, no overlaps. you pull the owner out of observation mode only when a deal goes above $7,500 or the test coverage of the server drops below 85%." This prompt gives the system an understanding of its role and the limits of intervention from the very first line. It knows it is supposed to find agencies on its own. It knows it is supposed to bring every MCP server to production on its own. It knows it connects the live owner only on large deals or when the tests do not converge. → The pipeline runs without breaks, day or night → Hunter goes through about 130 marketing agencies on LinkedIn and Clutch per day → Mapper rolls out 4 audit reports with the tech stack and a final spec for each → Coder writes 1 to 2 MCP servers per week in Python with 8 to 15 tools → Validator validates every server through Claude Desktop with real client API keys → Shipper rolls out the full documentation package and pushes the finished product to Cloudflare Workers or the GitHub of the client And only when a contract breaks $7,500 or test coverage drops below 85% does the orchestrator pull the owner from whatever he is doing. And when the owner at that moment is behind the wheel or at a meeting in a coworking space, the Mobile agent in his iPhone picks up 1 contract in progress: confirms a meeting with the agency CMO in Calendly, opens a live demo of the MCP server through a secure terminal to the Mac Mini, and writes the test result to the shared state. The owner just swipes "approve" and in 15 minutes joins the Zoom demo. The fresh system log from last Wednesday looks like this: "hunter report: 132 agencies checked on LinkedIn and Clutch, 19 without MCP integrations, 8 with active requests for AI tooling in job posts, 4 with an open Q4 budget. passing to mapper." "coder: MCP server for Northwave Performance Marketing built in Python, 11 tools for Google Ads, Meta Ads, and GA4, 320 lines of code. exported to /Users/dev/mcp-shop/clients/northwave/server.py. validator connecting to Claude Desktop." "validator: 11 tools passed validation through Claude Desktop, test coverage 92%, average latency 380 ms. passing to shipper." "eval flag: contract with Pacific Reach Agency at $8,200 exceeds the approved limit of $7,500. sending for manual review." In his work setup there is no cloud server, no external team, and not even a separate office. At home sits a Mac Mini with a sandbox at /Users/dev/mcp-shop, on top runs an MCP router with a single API key to Claude, and the same key is forwarded to a secure terminal on the iPhone. Out of everything I have seen this year, this is the cleanest solo shop for custom MCP servers for marketing agencies: $540 a month on the API, about $30,000 into the account, and between them 7 system prompts, 1 Mac Mini in a work corner, and 1 iPhone that never leaves the pocket.

Blaze

55,926 görüntüleme • 2 ay önce

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:
2:44

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Avthar

10,723 görüntüleme • 3 ay önce

Congratulations to the Cohere team on releasing North Mini Code 1.0 🔥 We provide day-0 support on MLX thanks to our close collaboration with the Cohere team. North Mini Code 1.0 is a 30B param MoE model with 3B active. It runs at ~66 tok/s in BF16, truly impressive speeds before any compression. Here is a quick demo I built using Pi by Mario Zechner & Armin Ronacher ⇌ as my agent hardness. Get started today: 1. Install mlx-vlm from source: > uv pip install git+ 2. Start the server and power your favourite agents (pi, opencode, hermes and etc) > uv run mlx_vlm.server --model CohereLabs/North-Mini-Code-1.0 New release tomorrow
4:34

Congratulations to the Cohere team on releasing North Mini Code 1.0 🔥 We provide day-0 support on MLX thanks to our close collaboration with the Cohere team. North Mini Code 1.0 is a 30B param MoE model with 3B active. It runs at ~66 tok/s in BF16, truly impressive speeds before any compression. Here is a quick demo I built using Pi by Mario Zechner & Armin Ronacher ⇌ as my agent hardness. Get started today: 1. Install mlx-vlm from source: > uv pip install git+ 2. Start the server and power your favourite agents (pi, opencode, hermes and etc) > uv run mlx_vlm.server --model CohereLabs/North-Mini-Code-1.0 New release tomorrow

Prince Canuma

35,367 görüntüleme • 1 ay önce

🚨An Important Announcement about the future of BensBets🚨 From 1st April I'll be introducing a cap on the amount of active memberships in order to protect the edge that members currently have. I'll be launching a free Discord server which will act as a waiting list for when slots are available. Please have a watch of this video which explains in more detail.
2:36

🚨An Important Announcement about the future of BensBets🚨 From 1st April I'll be introducing a cap on the amount of active memberships in order to protect the edge that members currently have. I'll be launching a free Discord server which will act as a waiting list for when slots are available. Please have a watch of this video which explains in more detail.

BensBets

75,038 görüntüleme • 3 ay önce