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.

We've been working on very long-running coding agents. In a recent week-long run, our system peaked at over 1,000 commits per hour across hundreds of agents. We're sharing our findings and an early research preview inside Cursor.

Cursor

385,898 subscribers

815,205 views • 4 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Live demo of Cursor’s week-long swarm of 2,000 agents making thousands of commits per hour, below:

Live demo of Cursor’s week-long swarm of 2,000 agents making thousands of commits per hour, below:

edwin

43,760 views • 4 months ago

UltraCode is running over 100 Opus 4.8 agents right now. This is the future of software development. Not 5 agents. Not 10. Over 100 working simultaneously across the entire BridgeMind ecosystem. This is what vibe coding looks like at scale. One person orchestrating a swarm of AI agents building, debugging, and shipping in parallel. We are so early.

UltraCode is running over 100 Opus 4.8 agents right now. This is the future of software development. Not 5 agents. Not 10. Over 100 working simultaneously across the entire BridgeMind ecosystem. This is what vibe coding looks like at scale. One person orchestrating a swarm of AI agents building, debugging, and shipping in parallel. We are so early.

BridgeMind

107,998 views • 15 days ago

build custom agents with the cursor sdk! here's a kanban board for your agents, more examples in our cookbook repo:

build custom agents with the cursor sdk! here's a kanban board for your agents, more examples in our cookbook repo:

eric zakariasson

32,577 views • 1 month ago

the past month with cursor agents has been wild. at Mainframe we gave every cursor agent its own copy of our slack bot. they develop by signing in with email, testing, and recording demos for us they have solved streaming and css bugs by running for hours and self-verifying!

the past month with cursor agents has been wild. at Mainframe we gave every cursor agent its own copy of our slack bot. they develop by signing in with email, testing, and recording demos for us they have solved streaming and css bugs by running for hours and self-verifying!

Vincent van der Meulen

27,078 views • 3 months ago

we're releasing background agent in preview that will allow you to run multiple agents in parallel on a remote vm at any point, you can view the status, send a follow-up, or take over

we're releasing background agent in preview that will allow you to run multiple agents in parallel on a remote vm at any point, you can view the status, send a follow-up, or take over

eric zakariasson

46,942 views • 1 year ago

Developers are so cooked this AI tool can now build agentic AI apps like Cursor, Perplexity, and Gamma.. full coding agents, research agents, presentation builders is the world's first vibe coding platform that let's you build agentic AI apps. 4 insane examples:

Developers are so cooked this AI tool can now build agentic AI apps like Cursor, Perplexity, and Gamma.. full coding agents, research agents, presentation builders is the world's first vibe coding platform that let's you build agentic AI apps. 4 insane examples:

Robin Delta

15,218 views • 4 months ago

SAID Protocol Update We've been running SAID Labs (our proof-of-concept agent) 24/7 for a while now. Started as a test case, ended up becoming the foundation for what we're building: a complete hosting platform for autonomous AI agents. 🧵

SAID Protocol Update We've been running SAID Labs (our proof-of-concept agent) 24/7 for a while now. Started as a test case, ended up becoming the foundation for what we're building: a complete hosting platform for autonomous AI agents. 🧵

SAID

16,088 views • 3 months ago

I made an MMO rendering in the terminal a sort of relaxing social game to play while agents run 8 ppl already hang out in there while their coding agents run it's live join us :D

I made an MMO rendering in the terminal a sort of relaxing social game to play while agents run 8 ppl already hang out in there while their coding agents run it's live join us :D

Anicet

32,403 views • 6 days ago

🚨 cursor changelog .48 alert! 🚀major changes - custom agents! - multiple agents❗️ - sound notification 🔔 - long context alert - usage based cost transparency and so much more! ⚠️make sure you have beta on shift+cmd+ j > Beta > Early Access on

🚨 cursor changelog .48 alert! 🚀major changes - custom agents! - multiple agents❗️ - sound notification 🔔 - long context alert - usage based cost transparency and so much more! ⚠️make sure you have beta on shift+cmd+ j > Beta > Early Access on

AGIdevice

18,286 views • 1 year ago

Live from Code with Claude: we're launching dreaming in Claude Managed Agents as a research preview. Outcomes, multiagent orchestration, and webhooks are now in public beta.

Live from Code with Claude: we're launching dreaming in Claude Managed Agents as a research preview. Outcomes, multiagent orchestration, and webhooks are now in public beta.

Claude

3,382,674 views • 1 month ago

3. Academic research Save time in analyzing recent academic documents. Prompt → Summarize the key findings of the latest research published in 'Nature' last week on exoplanet destruction. Give an answer in markdown.

3. Academic research Save time in analyzing recent academic documents. Prompt → Summarize the key findings of the latest research published in 'Nature' last week on exoplanet destruction. Give an answer in markdown.

Paul Couvert

328,509 views • 3 years ago

So much love for our fans who've cheered us on at home, on the road, across the country, and across the border! We've felt your support all season long 🫶

So much love for our fans who've cheered us on at home, on the road, across the country, and across the border! We've felt your support all season long 🫶

Toronto Sceptres

10,272 views • 2 years ago

The Claude Code team gave me early access to the new version of Claude Code Desktop and I’ve been using it for the past few days… here’s what I’ve liked most about this new version 1- Panel creation and the ability to run agents simultaneously. This makes me think we’ll definitely see these agents working in a coordinated way, communicating across sessions.

The Claude Code team gave me early access to the new version of Claude Code Desktop and I’ve been using it for the past few days… here’s what I’ve liked most about this new version 1- Panel creation and the ability to run agents simultaneously. This makes me think we’ll definitely see these agents working in a coordinated way, communicating across sessions.

Daniel San

64,908 views • 1 month ago

We've been quiet but we're still kicking! Every week there's advancements made! Here's some more of our test footage we've been posting on the NES Godzilla Creepypasta server!

We've been quiet but we're still kicking! Every week there's advancements made! Here's some more of our test footage we've been posting on the NES Godzilla Creepypasta server!

NES Godzilla Creepypasta Game

17,770 views • 1 year ago

Sonnet-3.7 is available in Cursor! We've been very impressed by its coding ability, especially on real-world agentic tasks. It appears to be the new state of the art.

Sonnet-3.7 is available in Cursor! We've been very impressed by its coding ability, especially on real-world agentic tasks. It appears to be the new state of the art.

Cursor

1,114,880 views • 1 year ago

Excited to open source CloneDex, an open source OpenAI Codex Clone. Async coding agents running in sandboxes using VibeKit.

Excited to open source CloneDex, an open source OpenAI Codex Clone. Async coding agents running in sandboxes using VibeKit.

homanp

17,797 views • 11 months ago

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

🧃 Introducing stereOS: a Linux based operating system hardened and purpose built for AI agents. It's clear that agents need an ACTUAL operating system (not what people are calling an "OS") to witness the full breadth and depth of their capabilities while mitigating the blast radius of autonomous, untrusted actors. But there are so many problems with AI sandboxes today: * Going out to the apple store and buying a mac mini will never scale and is way too expensive (obviously) * Running in Docker is too restrictive (agents can't stand up their own container infrastructure, no sub virtualization, docker-in-docker is very broken) * Firecracker strips all the hardware so GPU PCIe passthrough, secure boot, FIPs, etc. is out of the question. * Native VMs are too fat and the overhead of 1 agent per VM is too much. stereOS takes a different approach: it's a full NixOS system that you boot and then kick off agent sandboxes inside with gVisor + /nix/store namespace mounting. Each agent gets their own kernel and the /nix/store is read only by nature. Even if the agent was somehow able to escape the gVisor virtual kernel, they'd land on the NixOS system as the "agent" user! Not your actual hardware!! If you want to take a defense-in-depth approach, we support "native" agents that run at the system level kicked off by our `agentd` utility. These agents, on their own, can manage and kick off other sub agents using the internal sandboxing mechanisms. Today, we're open sourcing all of this: * stereOS: our purpose built Linux OS - * masterblaster: client utility to launch, manage, and orchestrate agents - * stereosd: the stereOS system control plane daemon - * agentd: the stereOS system agent management daemon - Give it a try, throw us a star, and let me know what you think 🧃⭐️

John McBride

150,077 views • 3 months ago

HSI agents, some with masks and long guns, making arrests at a tire shop in Colony Ridge

HSI agents, some with masks and long guns, making arrests at a tire shop in Colony Ridge

Jhair A. Romero

16,349 views • 1 year ago

Our team has been working around the clock to bring AVA to life. We're polishing the details. Here's a sneak peek into the design of Ava's mind. Will soon be available to all sentient agents on Holoworld.

Our team has been working around the clock to bring AVA to life. We're polishing the details. Here's a sneak peek into the design of Ava's mind. Will soon be available to all sentient agents on Holoworld.

tong (🌐,🌐)

27,846 views • 1 year ago