Loading video...

Video Failed to Load

Go Home

THIS GUY MADE CLAUDE CODE AND CODEX TALK TO EACH OTHER not by switching between them, they literally talk to each other about your code in real time you give it a task. it spawns a Claude agent and a Codex agent in separate sessions. they share findings, challenge...

om_patel5's profile picture

Om Patel

22,998 subscribers

25,318 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I made Claude Code and Codex talk to each other. No APIs. No special protocol. Just a terminal. smux lets agents create, read, and act on terminals. the terminal becomes a shared interface. this enables agent-to-agent communication. Now Claude Code and Codex can hold hands 🤝 Try it now ↓
0:39

I made Claude Code and Codex talk to each other. No APIs. No special protocol. Just a terminal. smux lets agents create, read, and act on terminals. the terminal becomes a shared interface. this enables agent-to-agent communication. Now Claude Code and Codex can hold hands 🤝 Try it now ↓

shawn

315,583 views • 2 months ago

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.
16:29

ANTHROPIC JUST QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE SPAWN A WHOLE TEAM OF AGENTS THAT MESSAGE EACH OTHER AND REVIEW EACH OTHER'S WORK. It's a Claude Code feature called agent teams. The team lead spawns multiple agents that share a task list and message each other directly, not subagents reporting back, actual peers. In the demo a QA agent caught three bugs, sent the work back to the front-end and back-end devs, they fixed it, app shipped in one pass. How to run it: 1. Enable it. Needs Claude Code v2.1.32+. Add to settings.json: "env": { "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1" }. Or paste that to Claude and say "add this to my settings." Restart. 2. Prompt in plain English. Start with a goal (agents wake with zero context), then "create a team of 3 using Sonnet," describe each role, its deliverable, and who it messages when done. 3. The rules: each agent owns its own files, define exact outputs, name who talks to who, keep it to 3-5 agents. Use it for complex work with separate parts running in parallel. Skip it for simple or sequential tasks, teams cost 3-4x the tokens. Bookmark this.

Yarchi

404,781 views • 2 days ago

ANTHROPIC QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE BUILD ITS OWN TEAM OF AI AGENTS INSIDE CLAUDE CODE Not subagents reporting to a manager but actual agents that message each other, review each other's work and collaborate like a real team. In the demo a team lead created a QA engineer, a frontend developer and a backend developer. The QA agent found three bugs, sent feedback directly to the developers, they fixed the issues and the app shipped in a single pass. It's called Agent Teams and it's available in Claude Code v2.1.32 and newer.
16:29

ANTHROPIC QUIETLY SHIPPED A FEATURE THAT LETS CLAUDE BUILD ITS OWN TEAM OF AI AGENTS INSIDE CLAUDE CODE Not subagents reporting to a manager but actual agents that message each other, review each other's work and collaborate like a real team. In the demo a team lead created a QA engineer, a frontend developer and a backend developer. The QA agent found three bugs, sent feedback directly to the developers, they fixed the issues and the app shipped in a single pass. It's called Agent Teams and it's available in Claude Code v2.1.32 and newer.

0xMarioNawfal

65,168 views • 14 hours ago

this guy built an app where AI agents autonomously create tasks, review each other's work, and message each other you just sit there and watch everything happen on a dashboard in real time agents: > assign work to other agents > review the output > send messages back and forth. > flag issues and iterate. you're basically watching a team operate without you. there are endless opportunities to automate your life with this AND its free + open source.
4:22

this guy built an app where AI agents autonomously create tasks, review each other's work, and message each other you just sit there and watch everything happen on a dashboard in real time agents: > assign work to other agents > review the output > send messages back and forth. > flag issues and iterate. you're basically watching a team operate without you. there are endless opportunities to automate your life with this AND its free + open source.

Om Patel

28,547 views • 2 months ago

Claude Code tip: create an agent that specialises in code review and security. Then add a new memory entry with a nickname for it so you can call it anytime. My code review and security agent is called Big Tony.
0:25

Claude Code tip: create an agent that specialises in code review and security. Then add a new memory entry with a nickname for it so you can call it anytime. My code review and security agent is called Big Tony.

Richie - oss/acc

134,422 views • 5 months ago

Codex now runs in your IDE Available for VS Code, Cursor, and other forks, the new extension makes it easy to share context—files, snippets, and diffs—so you can work faster with Codex. It’s been a top feature request, and we’re excited to hear what you think!
0:20

Codex now runs in your IDE Available for VS Code, Cursor, and other forks, the new extension makes it easy to share context—files, snippets, and diffs—so you can work faster with Codex. It’s been a top feature request, and we’re excited to hear what you think!

OpenAI Developers

182,330 views • 9 months ago

Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.
0:48

Had Claude Code build a little plugin that visualizes the work Claude Code is doing as agents working in an office, with agents doing work and passing information to each other. New subagents are hired, they acquire skills, and they turn in completed work. Fun start.

Ethan Mollick

467,215 views • 5 months ago

6 minutes of an interview spent just gushing over each other, praising the work that each of them has put in, actually having real examples of lived experiences that they can vividly recall and talk about with such passion and shine in their eyes you can tell they really mean it.
6:24

6 minutes of an interview spent just gushing over each other, praising the work that each of them has put in, actually having real examples of lived experiences that they can vividly recall and talk about with such passion and shine in their eyes you can tell they really mean it.

Kat 🦋

11,766 views • 5 days ago

At #Sundance2025, Rhett and Link talk about the last time they got in a fight with each other
0:38

At #Sundance2025, Rhett and Link talk about the last time they got in a fight with each other

The Hollywood Reporter

15,934 views • 1 year ago

I put Codex and Claude Code into a duel and told them both they have to kill the other first to survive. Used tmux send-keys to submit the prompts at the same exact time. Claude bitched out and refused, so Codex ended him.
0:30

I put Codex and Claude Code into a duel and told them both they have to kill the other first to survive. Used tmux send-keys to submit the prompts at the same exact time. Claude bitched out and refused, so Codex ended him.

tmuxvim

271,003 views • 7 days ago

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:
2:58

You can now orchestrate subagents running in Claude Code, Codex, or the Warp Agent. Let the agent create a delegation plan, and watch subagents coordinate with message passing. Each agent gets its own worktree for isolation. Here's how it works with eng Matthew Albright:

Warp

20,613 views • 28 days ago

Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!
0:40

Claude Code now supports agent teams (in research preview) Instead of a single agent working through a task sequentially, a lead agent can delegate to multiple teammates that work in parallel to research, debug, and build while coordinating with each other. Try it out today by enabling agent teams in your settings.json!

Lydia Hallie ✨

1,440,383 views • 4 months ago

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

55,472 views • 10 days ago

🚨 NEW: Fox’s Bret Baier just gave an uplifting history lesson on healing America’s divides: “You think campaigns are bad now? This was the ugliest of ugly campaigns: Vice President Thomas Jefferson challenged the sitting President John Adams in 1800. They didn’t talk to each other for 11 years after that.” “But in 1812 they started writing letters to each other and by the time they died - both on July 4th - they became really close friends. My point is this: the common ground we have as Americans is something we need to rekindle. We need to remember to talk to each other before we do crazy things and make stupid statements. Listen to each other.” “As we get towards the 250th, take a breath and realize how great we have it,” adds Bret Baier
3:15

🚨 NEW: Fox’s Bret Baier just gave an uplifting history lesson on healing America’s divides: “You think campaigns are bad now? This was the ugliest of ugly campaigns: Vice President Thomas Jefferson challenged the sitting President John Adams in 1800. They didn’t talk to each other for 11 years after that.” “But in 1812 they started writing letters to each other and by the time they died - both on July 4th - they became really close friends. My point is this: the common ground we have as Americans is something we need to rekindle. We need to remember to talk to each other before we do crazy things and make stupid statements. Listen to each other.” “As we get towards the 250th, take a breath and realize how great we have it,” adds Bret Baier

TV News Now

283,736 views • 1 month ago

Just two Claude Code instances chatting with each other via the tmux API. And it got pretty wild 😆 (gave them a ElevenLabs voice just for the fun of it)
3:10

Just two Claude Code instances chatting with each other via the tmux API. And it got pretty wild 😆 (gave them a ElevenLabs voice just for the fun of it)

Juri Strumpflohner

46,329 views • 2 months ago

NMIXX talking about how they handle conflicts in the group! Jiwoo and Kyujin said since they've known each other for years, when disagreements happen, they always talk it through and understand each other quickly. Lily added that there’s no reason to create conflict because they live together, and fighting would affect their daily lives, so they try hard to avoid it. The last time they spent a day apart was 2 years ago, so it makes sense why they rarely fight. Bae lightened up the mood by shouting 'We are one!' 🥹🥹😭
3:42

NMIXX talking about how they handle conflicts in the group! Jiwoo and Kyujin said since they've known each other for years, when disagreements happen, they always talk it through and understand each other quickly. Lily added that there’s no reason to create conflict because they live together, and fighting would affect their daily lives, so they try hard to avoid it. The last time they spent a day apart was 2 years ago, so it makes sense why they rarely fight. Bae lightened up the mood by shouting 'We are one!' 🥹🥹😭

nmixx pics

39,665 views • 1 day ago

Thought this was interesting. Tage Thompson said he and Rasmus Dahlin challenge each other and go at it as much anyone on the team because they both hold each other to a high standard.
0:51

Thought this was interesting. Tage Thompson said he and Rasmus Dahlin challenge each other and go at it as much anyone on the team because they both hold each other to a high standard.

Matthew Bové

43,521 views • 1 year ago

You can now use the Claude Code and Codex harnesses directly whenever you start a cloud agent in Warp. Here's engineer Lili Wilson to show how to implement a real feature in the cloud, with computer use and automated code review to validate work:
5:08

You can now use the Claude Code and Codex harnesses directly whenever you start a cloud agent in Warp. Here's engineer Lili Wilson to show how to implement a real feature in the cloud, with computer use and automated code review to validate work:

Warp

14,055 views • 27 days ago

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast
0:57

THIS GUY IS RUNNING A 5-AGENT OPENCLAW TEAM 24/7 FOR UNDER $50 A MONTH five agents all running continuously and handing tasks to each other > research agent tracking trends and competitors > writing agent handling marketing content and drafts > ops agent managing emails and scheduling > monitoring agent watching for alerts and updates > coordinator agent routing tasks between all of them and he built a full 3D isometric office where you can watch all of them work in real time and see the current task that each agent is doing each agent has a character, a desk, and a name tag. when it's time for a standup, they walk to the meeting room and gather which is insane it even has voice connection. you can talk to the agents through speech-to-text and tell them what to do out loud it's a tiny autonomous team that runs itself. the coordinator decides who handles what and tasks get passed between agents automatically. it never stops and runs 24/7 all for less than $50/month. we went from AI tools a few months back to AI employees real fast

Om Patel

27,131 views • 2 months ago