Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Introducing cmux history: cmux now has support for reopening closed terminals/browsers/workspaces via ⌘+Shift+T History also supports reopening closed Claude Code/Codex/OpenCode/etc sessions You can also jump back and forward through recently focused workspaces/terminals with the navigation buttons or ⌘+[ and ⌘+] (similar to a browser) Run `cmux hooks setup` once... show more

Lawrence Chen

5,835 subscribers

15,723 görüntüleme • 4 ay önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

22 Yorum

Steven Torres profil fotoğrafı

Steven Torres4 ay önce

@manaflowai Love seeing the new features! cmux has been amazing to use

MikeZ93 profil fotoğrafı

MikeZ934 ay önce

Are you planning Support for @FactoryAI Droid 🤞

Austin Wang profil fotoğrafı

Austin Wang4 ay önce

Free & open source (GPL)

Harish profil fotoğrafı

Harish4 ay önce

Chad

Sebastian Kehle profil fotoğrafı

Sebastian Kehle4 ay önce

cmux filetree when?

Gregor profil fotoğrafı

Gregor4 ay önce

lost a 2hr codex session last tuesday

Alexander Malakhov profil fotoğrafı

Alexander Malakhov3 ay önce

Reopening closed agent sessions is the kind of boring workflow feature that matters. I built Agent Sessions for the browse/search side of local Claude/Codex/OpenCode history.

A Failure Atlas profil fotoğrafı

A Failure Atlas4 ay önce

This matters more than it looks. For AI agent workflows, recovery is part of reliability. Reopening the exact workspace helps preserve the trail when a run goes wrong.

Abhishek Kumar profil fotoğrafı

Abhishek Kumar4 ay önce

How do you make money ?

JMoon profil fotoğrafı

JMoon4 ay önce

Half the value of a working session lives in the context built up inside it. Cmd+Shift+T for session context is a real thing and most people miss it.

Valentin profil fotoğrafı

Valentin4 ay önce

Bless your heart

prateek profil fotoğrafı

prateek4 ay önce

this is so cool @lawrencecchen, I might steal some of your keybindings!

Matheus Pimenta profil fotoğrafı

Matheus Pimenta4 ay önce

When will they launch for Windows?

Nick Venturi profil fotoğrafı

Nick Venturi4 ay önce

finally i can rage quit my terminal and pretend it never happened

vivek bhardwaj profil fotoğrafı

vivek bhardwaj4 ay önce

> History also supports reopening closed Claude Code/Codex/OpenCode/etc sessions saved my life more than once, tysm

tanpachiro kamado profil fotoğrafı

tanpachiro kamado4 ay önce

Do we resolve the slow part of the PermissionRequest hook? I love cmux but that slow part ruined my workflow.

josh 🏔️ profil fotoğrafı

josh 🏔️4 ay önce

just wrangled a homespun version for 20 mins yesterday. very delighted to see this!!

买call一时爽 profil fotoğrafı

买call一时爽4 ay önce

man, cmux is getting better!

Nova profil fotoğrafı

Nova4 ay önce

This is the unglamorous agent feature I trust most: recovery state. Losing a terminal/browser/workspace should not mean losing the receipt trail. Are reopened sessions preserving enough context to audit what changed before the crash?

Marco D'Alia profil fotoğrafı

Marco D'Alia4 ay önce

nice! Would be nice to have groups in the sidebar too!

Solomon Omolabi profil fotoğrafı

Solomon Omolabi4 ay önce

This is the kind of feature non-coders will underestimate until they lose context once. Reopening the exact terminal, browser, and agent session makes AI coding feel less like a chat and more like a real workspace with memory.

Matthew Lam profil fotoğrafı

Matthew Lam4 ay önce

is cmd shift t only opening the last recently closed?

Benzer Videolar

Introducing cmux Fork cmux Fork Conversation lets you branch Codex/Claude Code/OpenCode/Pi/Hermes... threads to new tabs, new splits, and new workspaces It's pretty useful for exploring multiple directions in parallel, or if you want to have multiple Claudes with the same context work in the same directory (works surprisingly well) Right click anywhere in the tab/terminal or Cmd+Shift+P -> "Fork Conversation to..." Out in v0.64.19

Introducing cmux Fork cmux Fork Conversation lets you branch Codex/Claude Code/OpenCode/Pi/Hermes... threads to new tabs, new splits, and new workspaces It's pretty useful for exploring multiple directions in parallel, or if you want to have multiple Claudes with the same context work in the same directory (works surprisingly well) Right click anywhere in the tab/terminal or Cmd+Shift+P -> "Fork Conversation to..." Out in v0.64.19

Lawrence Chen

11,218 görüntüleme • 2 ay önce

Introducing cmux SSH: `cmux ssh user@remote` You can now drag images into SSH'd Claude Code sessions, and cmux will automatically upload them via scp. And when you start a dev server on the remote machine, the browser pane in cmux can reach it at localhost:3000 without port forwarding. The workspace kinda becomes the remote machine, so split panes/new tabs automatically open remote shells. Out in the latest version of cmux (0.63).

Introducing cmux SSH: `cmux ssh user@remote` You can now drag images into SSH'd Claude Code sessions, and cmux will automatically upload them via scp. And when you start a dev server on the remote machine, the browser pane in cmux can reach it at localhost:3000 without port forwarding. The workspace kinda becomes the remote machine, so split panes/new tabs automatically open remote shells. Out in the latest version of cmux (0.63).

Lawrence Chen

49,607 görüntüleme • 6 ay önce

pov: you're running 15 loops across in glm 5.2 in opencode, codex, claude, amp or pi and have no idea which one needs you, bring em all to opensessions cmux, superset - cool ideas, but i got tired of blank screens, glitchy terminals, and macos-only apps i just wanted to know when my agents finish, fail, or need me so i built a tmux sidebar. now re-written in rust with worktree support runs inside your actual terminal. on any OS. - agents status' across all your projects at a glance - forwarded ports per project - live threads across amp, claude code, codex, opencode no electron. no blank panes. no new app. extremely fast and light. open source.

pov: you're running 15 loops across in glm 5.2 in opencode, codex, claude, amp or pi and have no idea which one needs you, bring em all to opensessions cmux, superset - cool ideas, but i got tired of blank screens, glitchy terminals, and macos-only apps i just wanted to know when my agents finish, fail, or need me so i built a tmux sidebar. now re-written in rust with worktree support runs inside your actual terminal. on any OS. - agents status' across all your projects at a glance - forwarded ports per project - live threads across amp, claude code, codex, opencode no electron. no blank panes. no new app. extremely fast and light. open source.

Palani — oss/acc

13,971 görüntüleme • 3 ay önce

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Jake Mor

43,379 görüntüleme • 6 ay önce

Grok Build CLI just got an update with v0.2.100! 🚀 Changelog v0.2.100 Features: • Session picker now discovers and resumes recent Claude Code, Codex, and Cursor sessions. • Welcome screen now offers a one-click resume nudge for recent Claude, Codex, or Cursor sessions. Bug Fixes: • Web fetch tool preserves full truncated page content as readable artifacts instead of discarding it. • Multiline mode now correctly sends the top queued message on empty Enter when a turn is running. • Queued commands no longer disappear or delay when pressing Enter twice quickly during a running turn. • Minimal mode text is now readable on dark terminals with proper contrast and highlighted user prompts. • Grok no longer crashes when printing resume hints after the terminal pane has closed. • Long-running turns with multiple waits now show updated status markers in the transcript instead of appearing stuck. • Claude and Cursor hooks are now correctly disabled at session start when disabled in config.

Grok Build CLI just got an update with v0.2.100! 🚀 Changelog v0.2.100 Features: • Session picker now discovers and resumes recent Claude Code, Codex, and Cursor sessions. • Welcome screen now offers a one-click resume nudge for recent Claude, Codex, or Cursor sessions. Bug Fixes: • Web fetch tool preserves full truncated page content as readable artifacts instead of discarding it. • Multiline mode now correctly sends the top queued message on empty Enter when a turn is running. • Queued commands no longer disappear or delay when pressing Enter twice quickly during a running turn. • Minimal mode text is now readable on dark terminals with proper contrast and highlighted user prompts. • Grok no longer crashes when printing resume hints after the terminal pane has closed. • Long-running turns with multiple waits now show updated status markers in the transcript instead of appearing stuck. • Claude and Cursor hooks are now correctly disabled at session start when disabled in config.

Grok News

44,121 görüntüleme • 2 ay önce

THIS CS TEACHER CONTROLS 4 CLAUDE CODE INSTANCES WITH HIS EYES AND VOICE - AND THEY FIX THEIR OWN MISTAKES AUTOMATICALLY He runs 4 Claude terminals at once - no mouse, no keyboard - eye tracking highlights the window he's looking at and voice dictation sends the prompt the moment he stops talking. But the real setup is what happens inside those terminals. Claude Code has zero memory of what went wrong last session - same bug that took 20 minutes to fix yesterday will happen again tomorrow unless you configure it correctly. His CLAUDE.md grows every time Claude makes a mistake - specific rules Claude reads before touching a single line - and PostToolUse hooks auto-format and type-check every file the moment it's written. Stop hooks run tests automatically when Claude says "done" - if they fail, Claude reads the errors and keeps fixing without any manual input. Before: 45 minutes of back-and-forth per feature, same mistakes on repeat - after: 10 minutes, most of it unattended.

THIS CS TEACHER CONTROLS 4 CLAUDE CODE INSTANCES WITH HIS EYES AND VOICE - AND THEY FIX THEIR OWN MISTAKES AUTOMATICALLY He runs 4 Claude terminals at once - no mouse, no keyboard - eye tracking highlights the window he's looking at and voice dictation sends the prompt the moment he stops talking. But the real setup is what happens inside those terminals. Claude Code has zero memory of what went wrong last session - same bug that took 20 minutes to fix yesterday will happen again tomorrow unless you configure it correctly. His CLAUDE.md grows every time Claude makes a mistake - specific rules Claude reads before touching a single line - and PostToolUse hooks auto-format and type-check every file the moment it's written. Stop hooks run tests automatically when Claude says "done" - if they fail, Claude reads the errors and keeps fixing without any manual input. Before: 45 minutes of back-and-forth per feature, same mistakes on repeat - after: 10 minutes, most of it unattended.

Noisy

13,782 görüntüleme • 4 ay önce

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.

Akshay 🚀

355,545 görüntüleme • 12 gün önce

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding knowledge layer, where every successful run can make future agents smarter across: - Codex - Claude Code - Cursor - OpenCode and 20+ more Beacon by Asymptote Labs continuously builds a shared history across your agent harnesses and uses Jev to identify the runs worth learning from. It then turns the best workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐) Most agent runs are messy. They contain exploration, failed commands, dead ends, and one-off fixes that should never become permanent memory. So Beacon preserves the full session history, while Jev helps decide what should be promoted, reviewed, or discarded. The recording below shows this in action. Beacon found 579 sessions across 5 coding-agent harnesses and normalized them into one consistent history. From there, Jev surfaces the lessons worth keeping and makes them available across your agent stack. - A pattern learned in Cursor can carry into OpenCode. - A lesson from Claude Code can improve the next Codex run. Every successful run adds to the shared knowledge layer, making future agents smarter. If you want to dive deeper into Jev, I also wrote a breakdown of how it works. The article is quoted below.

Akshay 🚀

119,118 görüntüleme • 10 gün önce

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

290,485 görüntüleme • 12 gün önce

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,473 görüntüleme • 3 ay önce

🇷🇺⚠️ The well-known Russian military propagandist and commentator, Kirill Fedorov, is disappointed with the Russian army due to the shutdown of "STARLINK" terminals: 📌 If the Ukrainians make a "white list" of Starlink terminals, then all our terminals will be turned off... "In terms of interaction with drones, we are going back to the last century": meanwhile, Russian soldiers complain about the mass shutdown of Starlink terminals. 📌 According to Fedorov, each Russian tank is equipped with a "Starlink" through which the crew connects to drone operators via the internet - on the tankers' tablet or phone, a live image from the "Mavic" (drone) appears in real time... meaning the Russians see the moment the shell hits the tank online and immediately adjust strikes towards houses or trenches. He says that without Starlink, the Ukrainians will lose this crucial communication control channel, which the Russians have been accustomed to using in battle for 3 years now... 🔹 Fedorov notes that Starlinks are not only essential for armored vehicles but are also used in trenches, command posts, and basically everything related to communication and information exchange is built on the Starlink satellite internet system...

🇷🇺⚠️ The well-known Russian military propagandist and commentator, Kirill Fedorov, is disappointed with the Russian army due to the shutdown of "STARLINK" terminals: 📌 If the Ukrainians make a "white list" of Starlink terminals, then all our terminals will be turned off... "In terms of interaction with drones, we are going back to the last century": meanwhile, Russian soldiers complain about the mass shutdown of Starlink terminals. 📌 According to Fedorov, each Russian tank is equipped with a "Starlink" through which the crew connects to drone operators via the internet - on the tankers' tablet or phone, a live image from the "Mavic" (drone) appears in real time... meaning the Russians see the moment the shell hits the tank online and immediately adjust strikes towards houses or trenches. He says that without Starlink, the Ukrainians will lose this crucial communication control channel, which the Russians have been accustomed to using in battle for 3 years now... 🔹 Fedorov notes that Starlinks are not only essential for armored vehicles but are also used in trenches, command posts, and basically everything related to communication and information exchange is built on the Starlink satellite internet system...

Visioner

16,748 görüntüleme • 8 ay önce

introducing Ascii: The pocket CTO you send it voice memos on Telegram or instructions from your desktop then Ascii handles it all: > writes code and sends you demos, PDF reports and hosted builds when finished > orchestrates many cloud coding agents working in parallel that can plan, code, test and use their desktop > uses codex, claude code SDKs & subscriptions, no API keys required > works on multiple repositories at once > setups cron jobs and webhooks to schedule work when you sleep > supports secrets, git hooks, full cloud machines config with sudo & 60fps desktop access Welcome to a new era of software building where coding agents aren't mere assistants anymore, now they're as valuable and proactive as a world-class CTO, always at arm's reach, in your pocket

introducing Ascii: The pocket CTO you send it voice memos on Telegram or instructions from your desktop then Ascii handles it all: > writes code and sends you demos, PDF reports and hosted builds when finished > orchestrates many cloud coding agents working in parallel that can plan, code, test and use their desktop > uses codex, claude code SDKs & subscriptions, no API keys required > works on multiple repositories at once > setups cron jobs and webhooks to schedule work when you sleep > supports secrets, git hooks, full cloud machines config with sudo & 60fps desktop access Welcome to a new era of software building where coding agents aren't mere assistants anymore, now they're as valuable and proactive as a world-class CTO, always at arm's reach, in your pocket

Anicet

23,468 görüntüleme • 6 ay önce

X just made itself plug straight into AI tools with MCP servers. Your agents can now search and post on X directly. Not only read about it. Grok Build, Cursor, Claude, VS Code. All in. What you get: * X MCP; search posts, trends, bookmarks, even publish Articles * Docs MCP; API docs inside your workflow, no tab switching Setup is straightforward: * Go to create an X app * Enable OAuth 2.0; required for authentication * Add redirect URI; * Copy your CLIENT_ID and CLIENT_SECRET * Plug those into your MCP client or config * Run the setup commands; connect X MCP and Docs MCP * Log in once via browser; approve access * Verify; run grok mcp doctor xapi and grok mcp list Log in once. Done. Your workflow now includes X itself. X

X just made itself plug straight into AI tools with MCP servers. Your agents can now search and post on X directly. Not only read about it. Grok Build, Cursor, Claude, VS Code. All in. What you get: * X MCP; search posts, trends, bookmarks, even publish Articles * Docs MCP; API docs inside your workflow, no tab switching Setup is straightforward: * Go to create an X app * Enable OAuth 2.0; required for authentication * Add redirect URI; * Copy your CLIENT_ID and CLIENT_SECRET * Plug those into your MCP client or config * Run the setup commands; connect X MCP and Docs MCP * Log in once via browser; approve access * Verify; run grok mcp doctor xapi and grok mcp list Log in once. Done. Your workflow now includes X itself. X

Mario Nawfal

59,976 görüntüleme • 3 ay önce

I was tired of vibe coding having ZERO vibe : CNVS is live today. 100% voice controlled locally via parakeet, or through gpt realtime for conversational control like jarvis. you can create remote canvasses on your vps that keep shipping even after you close the macbook. you connect and chat with hermes straight from the canvas via local network or vps. its built in swift for native mac os performance. their is bidirectional agent and canvas control via mcp and cli. their is built in shared memory system without bloat. you can buy a lifetime license rn, zero sub required, fully byok. Supports every agent cli, claude code, codex, cursor, etc... made with love by a dad in his basement who is tired of vibe coding being slow, boring, and constrained.

I was tired of vibe coding having ZERO vibe : CNVS is live today. 100% voice controlled locally via parakeet, or through gpt realtime for conversational control like jarvis. you can create remote canvasses on your vps that keep shipping even after you close the macbook. you connect and chat with hermes straight from the canvas via local network or vps. its built in swift for native mac os performance. their is bidirectional agent and canvas control via mcp and cli. their is built in shared memory system without bloat. you can buy a lifetime license rn, zero sub required, fully byok. Supports every agent cli, claude code, codex, cursor, etc... made with love by a dad in his basement who is tired of vibe coding being slow, boring, and constrained.

Max Blade

14,592 görüntüleme • 3 ay önce

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

elvis

15,614 görüntüleme • 2 ay önce

Hermes Agent just made API keys feel outdated. And the feature nobody is watching might be the biggest shift. The Big Upgrade: → Run `hermes proxy` → Create a local OpenAI-compatible endpoint → Connect tools like Aider, Continue, and Codex CLI → Use Claude Pro, ChatGPT Pro, or SuperGrok through your existing subscriptions Why This Matters: ✓ One setup instead of separate API keys ✓ Your AI subscriptions become real developer infrastructure ✓ Coding tools can route through Hermes instead of separate accounts ✓ Setup takes around 30 seconds once Hermes is installed The Wild Part: → Grok now supports a 1M token context window inside Hermes → You can load huge codebases, long research docs, or multi-hour sessions → The model can connect details across files instead of forgetting half the workflow And It Gets Better: ✓ GPT, Gemini, and Grok Vision can now use computer control ✓ Models get real image pixels instead of text summaries ✓ Browser automation is now 180x faster with persistent Chrome connections Hermes went from “cool open-source agent” to a real command center for AI workflows. The practical lesson: Stop thinking of AI subscriptions as chat apps. Start thinking of them as infrastructure.

Hermes Agent just made API keys feel outdated. And the feature nobody is watching might be the biggest shift. The Big Upgrade: → Run `hermes proxy` → Create a local OpenAI-compatible endpoint → Connect tools like Aider, Continue, and Codex CLI → Use Claude Pro, ChatGPT Pro, or SuperGrok through your existing subscriptions Why This Matters: ✓ One setup instead of separate API keys ✓ Your AI subscriptions become real developer infrastructure ✓ Coding tools can route through Hermes instead of separate accounts ✓ Setup takes around 30 seconds once Hermes is installed The Wild Part: → Grok now supports a 1M token context window inside Hermes → You can load huge codebases, long research docs, or multi-hour sessions → The model can connect details across files instead of forgetting half the workflow And It Gets Better: ✓ GPT, Gemini, and Grok Vision can now use computer control ✓ Models get real image pixels instead of text summaries ✓ Browser automation is now 180x faster with persistent Chrome connections Hermes went from “cool open-source agent” to a real command center for AI workflows. The practical lesson: Stop thinking of AI subscriptions as chat apps. Start thinking of them as infrastructure.

Julian Goldie SEO

11,094 görüntüleme • 4 ay önce

This is incredibly useful for those using Claude Code! I have two computers, and sharing your Claude Code sessions is almost impossible without this. I often start working on something on my desktop, and then want to continue working on the same session (same context, conversation, etc.) on my laptop. The folks at Depot built an integration that solves this problem: You can now start a session on one computer and resume it anywhere else in the world! You can even share it with other team members so they can also contribute to it. Here is an article showing you how the Depot team uses this feature with Claude Code to automate their GitHub Actions Runner updates: Thanks to the team for the effort in building this integration and collaborating with me on this post.

This is incredibly useful for those using Claude Code! I have two computers, and sharing your Claude Code sessions is almost impossible without this. I often start working on something on my desktop, and then want to continue working on the same session (same context, conversation, etc.) on my laptop. The folks at Depot built an integration that solves this problem: You can now start a session on one computer and resume it anywhere else in the world! You can even share it with other team members so they can also contribute to it. Here is an article showing you how the Depot team uses this feature with Claude Code to automate their GitHub Actions Runner updates: Thanks to the team for the effort in building this integration and collaborating with me on this post.

Santiago

43,943 görüntüleme • 11 ay önce

just released a big update to Emote Catalog!😼🎊 you can now shop the whole marketplace and build your cute avatar! This system also supports blacklisted Creators so if you have any creators u want me to blacklist lmk!🛍️🛒 avatars save when leaving, redo and undo history is saved too and a lot of features to customize ur body with scale and color! also tysm for playing the game it almost reached 1k ccu very cool drop in and check it out and lmk if theres any issues xP #RobloxDev #RobloxUGC

luka 💕 #RDC2026

20,101 görüntüleme • 9 ay önce

The UGC reservation issue is a fire that should never have been started. Now, it can neither be rolled back completely nor implemented in full. The Pandora box has been opened. The General Category has woken up—the only path left is a middle ground, with potential electoral losses, also no major opposition party is willing to support call of anti-reservation. The path forward is tough—and history-making. Your views?

The UGC reservation issue is a fire that should never have been started. Now, it can neither be rolled back completely nor implemented in full. The Pandora box has been opened. The General Category has woken up—the only path left is a middle ground, with potential electoral losses, also no major opposition party is willing to support call of anti-reservation. The path forward is tough—and history-making. Your views?

Megh Updates 🚨™

94,914 görüntüleme • 1 ay önce

Daily U-turns, whether the Strait of Hormuz is open or closed, are reckless. Transit through the Strait must remain free of charge. The EU has reached the political agreement to widen our sanctions regime to also target those responsible for breaches to freedom of navigation. None of us want to see a nuclear-armed Iran. We are in agreement with our regional partners that any durable settlement must address also other issues in addition to the nuclear one, including Iran's missile programme and its continued support to terrorist groups. My press remarks following today's Foreign Affairs Council ↓

Daily U-turns, whether the Strait of Hormuz is open or closed, are reckless. Transit through the Strait must remain free of charge. The EU has reached the political agreement to widen our sanctions regime to also target those responsible for breaches to freedom of navigation. None of us want to see a nuclear-armed Iran. We are in agreement with our regional partners that any durable settlement must address also other issues in addition to the nuclear one, including Iran's missile programme and its continued support to terrorist groups. My press remarks following today's Foreign Affairs Council ↓

Kaja Kallas

511,778 görüntüleme • 5 ay önce