Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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)... show more

Lawrence Chen

5,836 subscribers

11,166 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

16 Comments

Saatvik2 months ago

forking across harnesses would be cool

Lawrence Chen2 months ago

interesting idea i like

SloaneTsui2 months ago

Wow!

solknight2 months ago

forking with the session context right ?

Lawrence Chen2 months ago

yup

Marco D'Alia2 months ago

very cool! is super hard today to fork a current conversation (at least with claude), and I need it all the time. will be possible to extend this with plugins?

Lawrence Chen2 months ago

how would you like to extend? we're gonna add a cli command in next version that lets you identify which claude/codex session id is associated with each terminal, so you could add your own cmd shift p or right click action to dispatch new workspace/run the claude resume/fork command yourself and do customizations there

Marco D'Alia2 months ago

wow that would be perfect I think!

Kris Constable2 months ago

I've built cmux forking into my workflow a month or two ago, I should have submitted a PR (not as feature rich as yours). It's crazy powerful when you have pi manage this functionality in your workflow automation. pi's cmux windows are more intense than mine 😅

tiff ☀️2 months ago

yessss need this for exploring a different thread so i dont mess up the original context of the OG one

Mahesh Rijal2 months ago

This is super handy. Thanks!

RUFY2 months ago

Kindly check your dm

Chris G.2 months ago

conversation forking solves the biggest problem with long agent sessions. you want to try three different approaches but context is expensive. right now I copy-paste system prompts into new tabs like a barbarian. this is the fix

Ivan Pereira2 months ago

I've been doing this with tmux on pi if anyone is interested

Moez Zhioua2 months ago

Nice work, the ability to branch contexts in parallel cuts down on context drift. I’ve seen similar tricks with hooks, but this feels smoother. Keep context isolated, it prevents accidental state bleed

Luke Jackson2 months ago

Excellent! I was doing this manually with hooks 🪝 Thank you!

Related Videos

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 Out in 0.64.11

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 Out in 0.64.11

Lawrence Chen

15,723 views • 3 months ago

💡 Small Codex tip: You don't have to be limited to looking at one thread at a time. 🪟 Open multiple full windows in parallel 💬 Use /side to fork a conversation to ask temporary follow ups 🛟 You can also set a hot key for the Codex pop up Window to quickly fire off new tasks

💡 Small Codex tip: You don't have to be limited to looking at one thread at a time. 🪟 Open multiple full windows in parallel 💬 Use /side to fork a conversation to ask temporary follow ups 🛟 You can also set a hot key for the Codex pop up Window to quickly fire off new tasks

dominik kundel

109,178 views • 4 months ago

finally ported my fav Claude Code feature into Pi: `/subtask` a subtask is a fork of your current conversation, it inherits everything you've discussed, works in the background, and sends only its final answer back into the conversation that spawned it. Less context pollution/bloating and you can continue the main conversation as subtasks are running. here's what's packed into the Pi extension: - a live panel under the prompt: ↑↓ to select, enter to watch a fork work in real time, x to stop or dismiss it - steer a running fork mid-task, or resume a finished one without losing its progress - the model can spawn subtasks on its own and keep working while it waits for the result - forks reuse the parent's prompt cache, so they're cheaper than briefing a subagent - every fork's transcript is a real pi session: reopen it any time with `pi --session `

finally ported my fav Claude Code feature into Pi: `/subtask` a subtask is a fork of your current conversation, it inherits everything you've discussed, works in the background, and sends only its final answer back into the conversation that spawned it. Less context pollution/bloating and you can continue the main conversation as subtasks are running. here's what's packed into the Pi extension: - a live panel under the prompt: ↑↓ to select, enter to watch a fork work in real time, x to stop or dismiss it - steer a running fork mid-task, or resume a finished one without losing its progress - the model can spawn subtasks on its own and keep working while it waits for the result - forks reuse the parent's prompt cache, so they're cheaper than briefing a subagent - every fork's transcript is a real pi session: reopen it any time with `pi --session `

Victor M

18,394 views • 27 days ago

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 views • 2 months ago

Codex 0.107.0 is here, and with it: FORKS🍴 This minor update includes the ability to fork your current chat history directly with custom multi agents with just a quick prompt. "Fork this session using n subagent(s)" This unlocks some interesting use-cases where you can launch multiple agents that retain all of your chat history up to that point, each in their own independent session. For example, you've been discussing architecture with Codex for 20 minutes, talked through constraints, reviewed existing code, settled on a model. Now you want to see two different implementation strategies side by side. Fork lets both children start from that full shared understanding. With a normal spawn, you'd have to re-explain the entire context to each child, and they'd inevitably miss nuance from the earlier conversation - which is basically a form of compaction/compression. With something like this, you could also just tell it to fork itself 5 times, and implement the same UI/frontend 5 different times in their own worktree to see which one you like the most. Other potential uses: - branching after reviews - try and rollback patterns using worktrees - parallel debugging strategies Otherwise, this is a minor update with improvements to the app server, realtime transcription, and memory. Enjoy!

Codex 0.107.0 is here, and with it: FORKS🍴 This minor update includes the ability to fork your current chat history directly with custom multi agents with just a quick prompt. "Fork this session using n subagent(s)" This unlocks some interesting use-cases where you can launch multiple agents that retain all of your chat history up to that point, each in their own independent session. For example, you've been discussing architecture with Codex for 20 minutes, talked through constraints, reviewed existing code, settled on a model. Now you want to see two different implementation strategies side by side. Fork lets both children start from that full shared understanding. With a normal spawn, you'd have to re-explain the entire context to each child, and they'd inevitably miss nuance from the earlier conversation - which is basically a form of compaction/compression. With something like this, you could also just tell it to fork itself 5 times, and implement the same UI/frontend 5 different times in their own worktree to see which one you like the most. Other potential uses: - branching after reviews - try and rollback patterns using worktrees - parallel debugging strategies Otherwise, this is a minor update with improvements to the app server, realtime transcription, and memory. Enjoy!

am.will

42,504 views • 6 months ago

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

New Release: Claudex Mode For the first time in mankind claude code and codex will be on the same team On the Blackbox CLI you can send the same task for Claude Code to implement and Codex to verify and test. You can choose more ways where they can collaborate on the same task to get the highest level of performance on your tasks

BLACKBOX AI

304,664 views • 6 months ago

I never use planning mode in Codex. GPT 5.5 loves to research, so I just have a conversation and reach a pseudo-plan in chat. Then, I let it implement, maybe with a /fork beforehand to keep that plan as a revisit-able point. Probably the biggest switch coming from Claude Code

I never use planning mode in Codex. GPT 5.5 loves to research, so I just have a conversation and reach a pseudo-plan in chat. Then, I let it implement, maybe with a /fork beforehand to keep that plan as a revisit-able point. Probably the biggest switch coming from Claude Code

Ben Holmes

156,737 views • 4 months ago

How to manage multiple AI agents at once: I run 10 to 15 parallel AI agent threads a day. Some days even more. Hermes, OpenClaw, Claude Code, Codex, all going at once. But the problem is more agents doesn't equal more output. Past a certain number of threads, you lose context. You forget what you told which agent. You duplicate work across two threads doing the same job. This is how we're solving for it:

How to manage multiple AI agents at once: I run 10 to 15 parallel AI agent threads a day. Some days even more. Hermes, OpenClaw, Claude Code, Codex, all going at once. But the problem is more agents doesn't equal more output. Past a certain number of threads, you lose context. You forget what you told which agent. You duplicate work across two threads doing the same job. This is how we're solving for it:

ericosiu

11,868 views • 2 months ago

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Y Combinator

61,650 views • 7 months ago

NEW: Vivek Ramaswamy says America is at a "FORK IN THE ROAD" over SOCIALISM 🚨 "Do you want LOWER electric bills by producing MORE energy? Or do you want SPIRALING electric bills through the GREEN NEW DEAL?" ⚒️ "I think Americans have the good sense to know COMMON SENSE PREVAILS in the END" 🇺🇸🔥

NEW: Vivek Ramaswamy says America is at a "FORK IN THE ROAD" over SOCIALISM 🚨 "Do you want LOWER electric bills by producing MORE energy? Or do you want SPIRALING electric bills through the GREEN NEW DEAL?" ⚒️ "I think Americans have the good sense to know COMMON SENSE PREVAILS in the END" 🇺🇸🔥

Jesse Watters

132,667 views • 11 days ago

New ChatGPT Atlas release out! Just hit "update" in the top right. - extensions import - icloud passkeys - new downloads ui - setting to use control + tab to cycle to most recently used tab - select multiple tabs at once (shift + click) - ability to set google as default search - "insert" button from Ask ChatGPT sidebar - faster Ask ChatGPT sidebar and by popular demand: vertical tabs! more coming early next week.

New ChatGPT Atlas release out! Just hit "update" in the top right. - extensions import - icloud passkeys - new downloads ui - setting to use control + tab to cycle to most recently used tab - select multiple tabs at once (shift + click) - ability to set google as default search - "insert" button from Ask ChatGPT sidebar - faster Ask ChatGPT sidebar and by popular demand: vertical tabs! more coming early next week.

Adam Fry

668,532 views • 9 months ago

Introducing Cross-Project Referencing. Lovable can now pull in context from across your workspace (files, components, even chat history) so new projects don’t start from scratch. This means you don't have to rebuild the same components, rewrite the same context, or re-explain the same decisions.

Introducing Cross-Project Referencing. Lovable can now pull in context from across your workspace (files, components, even chat history) so new projects don’t start from scratch. This means you don't have to rebuild the same components, rewrite the same context, or re-explain the same decisions.

Lovable

70,522 views • 6 months ago

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:

How to run GLM-5.2 (Or Minimax or Qwen or Deepseek or Kimi) in Claude Code No JSON editing. No vim 😮‍💨 1. Install Claude Code npm install -g Paul Jankura-ai/claude-code 2. Grab a Fireworks API key → 3. Install FireConnect + drop in your key (one line): curl -fsSL | FIREWORKS_API_KEY="fw_..." bash 4. Flip it on: fireconnect claude on 5. Switch to GLM-5.2 and bam! Swap models with: fireconnect claude model select Docs to do the same for Pi, Opencode, and Codex:

Sinan Ozdemir

149,913 views • 2 months ago

Have you tried forking chat sessions in VS Code? Create a new independent session that keeps the conversation history so you can explore alternative approaches without losing your original context. Watch the video to see how it works.

Have you tried forking chat sessions in VS Code? Create a new independent session that keeps the conversation history so you can explore alternative approaches without losing your original context. Watch the video to see how it works.

Visual Studio Code

28,488 views • 6 months ago

I’m usually skeptical of “AI workspace” products, but Bloome has a few ideas I actually like: You can put humans + multiple agents in the same conversation. One agent can draft something, another can poke holes in it, and another can clean up the final version. You can also bring in different agents/models like Claude, ChatGPT, DeepSeek, etc. instead of constantly bouncing between tabs. And because the whole conversation stays in context, teammates can join later and still understand how the work got to the final output. It also works across web, desktop, and mobile, though if you’re using it for real work, I’d especially recommend trying the desktop app. Feels closer to how real teams actually work.

I’m usually skeptical of “AI workspace” products, but Bloome has a few ideas I actually like: You can put humans + multiple agents in the same conversation. One agent can draft something, another can poke holes in it, and another can clean up the final version. You can also bring in different agents/models like Claude, ChatGPT, DeepSeek, etc. instead of constantly bouncing between tabs. And because the whole conversation stays in context, teammates can join later and still understand how the work got to the final output. It also works across web, desktop, and mobile, though if you’re using it for real work, I’d especially recommend trying the desktop app. Feels closer to how real teams actually work.

AI Breakfast

78,285 views • 2 months ago

Introducing Multi-select ✨. Edit multiple screens with a single prompt. 1. Hold SHIFT and click to select all the screens you want to edit (Fix for CMD/Ctrl rolling out now) 2. Write one prompt to apply your prompt across all the selected screens Perfect for creating consistent variations or updating entire flows in seconds. Let your imagination run wild!

Introducing Multi-select ✨. Edit multiple screens with a single prompt. 1. Hold SHIFT and click to select all the screens you want to edit (Fix for CMD/Ctrl rolling out now) 2. Write one prompt to apply your prompt across all the selected screens Perfect for creating consistent variations or updating entire flows in seconds. Let your imagination run wild!

Stitch by Google

60,501 views • 1 year ago

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

Claude

20,958,489 views • 2 months ago

Granular code control or prompt-driven development? In Antigravity, you exist in both worlds. Dive into the Editor for deep work. Pull back to the Agent Manager to manage multiple agents across workspaces. Switch between them instantly. Watch the Manager and Editor in sync 👇

Granular code control or prompt-driven development? In Antigravity, you exist in both worlds. Dive into the Editor for deep work. Pull back to the Agent Manager to manage multiple agents across workspaces. Switch between them instantly. Watch the Manager and Editor in sync 👇

Google Antigravity

70,384 views • 9 months ago

is now the AI builder for everyone. The new v0 uses agentic AI to plan, research, build, and debug. It works in context, across multiple steps, and adapts as you go. If you have an idea, v0 can build it.

is now the AI builder for everyone. The new v0 uses agentic AI to plan, research, build, and debug. It works in context, across multiple steps, and adapts as you go. If you have an idea, v0 can build it.

v0

453,449 views • 1 year ago

Hermes just made its in-app browser a whole lot more useful. You can now keep multiple browser tabs open inside Hermes Desktop instead of every new page replacing the one you were already using. And that matters more than it sounds. Because this is not just about “having tabs.” It means Hermes can work across multiple pages without forcing you to keep losing your place every time you open the next thing. Research one source, keep it open, open another tab, compare them side by side, and keep moving. Check a few products before buying something. Look at multiple hotel or travel options at once. Keep a YouTube tutorial open in one tab while Hermes looks through docs or another page in the next. And because this lives inside Hermes Desktop, you are not limited to one basic browser view either. You can keep multiple tabs open. You can view two pages side by side. You can stack them top and bottom. You can even run a four-panel view when you want several pages open at once. So the browser inside Hermes is starting to feel a lot more like a real workspace instead of one page you keep replacing. There is also some nice polish that comes with it. Browser tabs now label themselves based on the page, and the address bar behaves more cleanly while pages are loading. And remember, this is the same in-app browser Hermes can already read, click through, type in, scroll, and annotate. So this is not just a prettier browser. It is a more capable workspace for the browser Hermes is actually using. If Hermes is going to do more of your work on the web, this is exactly the kind of browser upgrade it needed.

Hermes just made its in-app browser a whole lot more useful. You can now keep multiple browser tabs open inside Hermes Desktop instead of every new page replacing the one you were already using. And that matters more than it sounds. Because this is not just about “having tabs.” It means Hermes can work across multiple pages without forcing you to keep losing your place every time you open the next thing. Research one source, keep it open, open another tab, compare them side by side, and keep moving. Check a few products before buying something. Look at multiple hotel or travel options at once. Keep a YouTube tutorial open in one tab while Hermes looks through docs or another page in the next. And because this lives inside Hermes Desktop, you are not limited to one basic browser view either. You can keep multiple tabs open. You can view two pages side by side. You can stack them top and bottom. You can even run a four-panel view when you want several pages open at once. So the browser inside Hermes is starting to feel a lot more like a real workspace instead of one page you keep replacing. There is also some nice polish that comes with it. Browser tabs now label themselves based on the page, and the address bar behaves more cleanly while pages are loading. And remember, this is the same in-app browser Hermes can already read, click through, type in, scroll, and annotate. So this is not just a prettier browser. It is a more capable workspace for the browser Hermes is actually using. If Hermes is going to do more of your work on the web, this is exactly the kind of browser upgrade it needed.

Hermes Release Watch

52,493 views • 19 days ago