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're working on making Linear your favorite launchpad for cloud coding agents Today's update adds a preview terminal attached to your coding environment, before starting an agent. Never interrogate your agent about how it set up the environment again 🫡

Ryan Delaney

1,081 subscribers

13,850 views • 12 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 Comments

Bilal Harouchi12 days ago

Love this. I hacked something similar a few week ago: a Linear webhook that fires a Claude Code routine on every bug ticket. Claude spins up its cloud env, reproduces the bug, fixes it, tests it and opens a PR.

Vlad12 days ago

I have a seperate machine for agent dev work, I set up a t3 code there and a layer from linear, to delegate issues to that machine. Can i do it better somehow from linear to spin up dev sessions?

Ryan Delaney12 days ago

Yes! Check out We set up the remote sandboxes for you with the spec from your coding environment, and then launch either Codex or Claude Code. Agent conversation is all done right from Linear, and works really well on mobile too

Vlad12 days ago

oh wait, so it can not use my other computer for it?

Ryan Delaney12 days ago

We don't support bring-your-own-compute yet unfortunately

Vlad12 days ago

I see, i guess I will stick to my t3 layer pipeline for now, thanks for your replies tho!

Automater12 days ago

A preview terminal is useful because it makes the environment part of the artifact. Next I’d want a machine-readable preflight: image, repo/ref, env vars, network policy, and tool versions recorded before the agent gets a shell.

Marius11 days ago

Awesome product and new feature 🤌

Related Videos

Today we're launching Mastra remote sandboxes Give your agent a secure, isolated environment to run untrusted user code... like a vibe coding agent...

Today we're launching Mastra remote sandboxes Give your agent a secure, isolated environment to run untrusted user code... like a vibe coding agent...

Alex Booker

22,210 views • 7 months ago

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:

🔗 Announcing LangChain OSS Skills LangChain has the most popular frameworks for building AI agents — and now your coding agent can be an expert in it. We're excited to release the first iteration of LangChain OSS Skills, giving your agent expertise in our open source frameworks. The skills include guidance on how to use langchain, langgraph, and deepagents to effectively build agents. ➡️ Install our OSS skills for your coding agent here: ➡️ Read more:

LangChain OSS

65,840 views • 7 months ago

Moving your Coding Agents to the Cloud (ft. Codex Desktop & GPT-6 Astra) 00:00 The limitations of running agents locally 01:13 Parallel development and Git worktrees 02:03 Moving your coding agent to a remote machine 02:25 Introducing Railway Cloud Agents 02:52 Installing the CLI and signing in 03:03 Configuring your project and default agent 03:42 Bringing your agent skills 04:24 Connecting the Codex desktop app 04:48 How SSH configuration works 05:10 Adding the SSH connection in Codex 05:39 Creating a remote project and starting a chat 06:09 Long-running tasks and remote execution 06:26 ChatGPT mobile access 07:03 Using Railway from your coding agent 07:15 Orchestrating multiple cloud agents

Moving your Coding Agents to the Cloud (ft. Codex Desktop & GPT-6 Astra) 00:00 The limitations of running agents locally 01:13 Parallel development and Git worktrees 02:03 Moving your coding agent to a remote machine 02:25 Introducing Railway Cloud Agents 02:52 Installing the CLI and signing in 03:03 Configuring your project and default agent 03:42 Bringing your agent skills 04:24 Connecting the Codex desktop app 04:48 How SSH configuration works 05:10 Adding the SSH connection in Codex 05:39 Creating a remote project and starting a chat 06:09 Long-running tasks and remote execution 06:26 ChatGPT mobile access 07:03 Using Railway from your coding agent 07:15 Orchestrating multiple cloud agents

Railway

82,044 views • 1 month ago

Introducing Oz: the platform to orchestrate agents in the cloud. Spin up hundreds of agents from your terminal, browser, the API, or your phone. Each agent gets a @docker environment to build, test, and write PRs. Come back from your lunch break to code that’s ready to merge.

Introducing Oz: the platform to orchestrate agents in the cloud. Spin up hundreds of agents from your terminal, browser, the API, or your phone. Each agent gets a @docker environment to build, test, and write PRs. Come back from your lunch break to code that’s ready to merge.

Warp

2,372,098 views • 7 months ago

Introducing Duet CLI. Now coding agents like Claude Code and Codex can call Duet (our agent-building agent) directly from the terminal to build and modify Decagon agents. Duet handles work within Decagon and returns the result while your coding agent stays focused on the broader task.

Introducing Duet CLI. Now coding agents like Claude Code and Codex can call Duet (our agent-building agent) directly from the terminal to build and modify Decagon agents. Duet handles work within Decagon and returns the result while your coding agent stays focused on the broader task.

Decagon

770,006 views • 1 month ago

This is actually useful. LangChain just released OpenWiki. It's an open-source agent that creates a wiki for your codebase, connects it to your coding agent, and keeps it updated as your repo changes. Your AI coding agent gets long-term repo context without stuffing everything into CLAUDE.md. Here's how to setup. Save this.

This is actually useful. LangChain just released OpenWiki. It's an open-source agent that creates a wiki for your codebase, connects it to your coding agent, and keeps it updated as your repo changes. Your AI coding agent gets long-term repo context without stuffing everything into CLAUDE.md. Here's how to setup. Save this.

Min Choi

126,315 views • 3 months ago

Now you can use your favorite AI agent to control your Coinbase account (or a sub-account), with Coinbase for Agents. Here’s a quick demo on how to set it up and some of the cool things you can get your agent to do.

Now you can use your favorite AI agent to control your Coinbase account (or a sub-account), with Coinbase for Agents. Here’s a quick demo on how to set it up and some of the cool things you can get your agent to do.

Brian Armstrong

213,812 views • 3 months ago

How to self-host your dev environment and run multiple coding agents on your project. This is open-source and free to use. You can run it on your computer or a server in the basement. • Multiple agents • Configurable Templates + Workspaces • Open and free

How to self-host your dev environment and run multiple coding agents on your project. This is open-source and free to use. You can run it on your computer or a server in the basement. • Multiple agents • Configurable Templates + Workspaces • Open and free

Santiago

17,935 views • 8 days ago

We've open sourced my favorite Devin feature: /handoff Hand off jobs to cloud Devins from your local machine Install it as a plugin in Claude Code or Codex or any other coding agent Close your laptop without pausing your agents 😉

We've open sourced my favorite Devin feature: /handoff Hand off jobs to cloud Devins from your local machine Install it as a plugin in Claude Code or Codex or any other coding agent Close your laptop without pausing your agents 😉

Jared Zoneraich

309,048 views • 3 months ago

Capy's haris on why Patrick Collison is right that agentic coding harnesses shouldn't be primarily terminal-based: "We saw this yesterday, and we kind of realized he's talking specifically about what we're building. We're building Capy to be a web-based agent platform where you could start an agent from Slack, from Linear, from Sentry, from your phone or wherever you use your agents." "We've seen in the past 40, 50, 60 years that we started with text editors in our terminals, like Vim, NeoVim, et cetera. And we moved to VS Code, to Cursor, and now we're going back to the terminal." "I think we're gonna go back to more of a desktop IDE environment where all of your agents are living in one centralized place rather than in your terminal and kind of scattered everywhere." nalin Capy

Capy's haris on why Patrick Collison is right that agentic coding harnesses shouldn't be primarily terminal-based: "We saw this yesterday, and we kind of realized he's talking specifically about what we're building. We're building Capy to be a web-based agent platform where you could start an agent from Slack, from Linear, from Sentry, from your phone or wherever you use your agents." "We've seen in the past 40, 50, 60 years that we started with text editors in our terminals, like Vim, NeoVim, et cetera. And we moved to VS Code, to Cursor, and now we're going back to the terminal." "I think we're gonna go back to more of a desktop IDE environment where all of your agents are living in one centralized place rather than in your terminal and kind of scattered everywhere." nalin Capy

MTS

13,507 views • 1 month ago

🚀 Announcing LangSmith Skills + CLI 🚀 Agent improvements are increasingly driven by coding agents themselves. We're releasing LangSmith Skills alongside the LangSmith CLI to make coding agents experts at the agent engineering lifecycle. LangSmith Skills enable agents to debug traces, create datasets, and run experiments - and thanks to the CLI, agents are able to do it all natively through the terminal, where they're most comfortable. Try out LangSmith Skills and the CLI with your own coding agents! ➡️ Skills: ➡️ CLI:

🚀 Announcing LangSmith Skills + CLI 🚀 Agent improvements are increasingly driven by coding agents themselves. We're releasing LangSmith Skills alongside the LangSmith CLI to make coding agents experts at the agent engineering lifecycle. LangSmith Skills enable agents to debug traces, create datasets, and run experiments - and thanks to the CLI, agents are able to do it all natively through the terminal, where they're most comfortable. Try out LangSmith Skills and the CLI with your own coding agents! ➡️ Skills: ➡️ CLI:

LangChain

49,662 views • 7 months ago

The Perplexity CLI is now available, giving coding agents the ability to search the web. Copy this to your agent to get set up: "Read: and install this skill."

The Perplexity CLI is now available, giving coding agents the ability to search the web. Copy this to your agent to get set up: "Read: and install this skill."

Perplexity Developers

161,818 views • 2 months ago

Factory benchmarks let you build your own model bench using your past coding agent runs. - Mirrors your environment, secrets, and MCPs for each run - Scores output on judging criteria you define - Generates a report with model recs using cost vs. quality Here's how it works:

Factory benchmarks let you build your own model bench using your past coding agent runs. - Mirrors your environment, secrets, and MCPs for each run - Scores output on judging criteria you define - Generates a report with model recs using cost vs. quality Here's how it works:

Warp

72,768 views • 1 month ago

Introducing jevgrep - a research agent CLI powered by jev from TypeSafe AI that reduces your coding agent cost by 40% (verified on SWE-bench) Make sure to use the built in skill so your coding agent knows to use jg for context collection

Introducing jevgrep - a research agent CLI powered by jev from TypeSafe AI that reduces your coding agent cost by 40% (verified on SWE-bench) Make sure to use the built in skill so your coding agent knows to use jg for context collection

David

447,582 views • 11 days ago

Introducing Ara A loop that talks to your coding agent for you. Self-improving codebase pr's that it builds on its own. Never prompt again. 10X usage limits for everyone

Introducing Ara A loop that talks to your coding agent for you. Self-improving codebase pr's that it builds on its own. Never prompt again. 10X usage limits for everyone

Adi

185,431 views • 4 months ago

Create your Copy-Trading Agent with vibe-coding in Lucy. Input and monitor any wallet address, and let your agent automatically seize smart money routes 24/7. An agentic automated trading terminal should be democratic for everyone. See how easy it is to build now.

Create your Copy-Trading Agent with vibe-coding in Lucy. Input and monitor any wallet address, and let your agent automatically seize smart money routes 24/7. An agentic automated trading terminal should be democratic for everyone. See how easy it is to build now.

Delysium - $AGI 🟨

15,770 views • 1 year ago

.InsForge turns your coding agent into a principal backend engineer. Backend servers, database, LLM gateway, frontend deployment, and more. Every primitive built for how coding agents actually work, so they can run your entire infrastructure. Congrats on the launch, Hang Huang & Tony Chang!

.InsForge turns your coding agent into a principal backend engineer. Backend servers, database, LLM gateway, frontend deployment, and more. Every primitive built for how coding agents actually work, so they can run your entire infrastructure. Congrats on the launch, Hang Huang & Tony Chang!

Y Combinator

151,857 views • 4 months ago

AI coding agents have access to your API keys, your codebase, your production environment. One prompt injection and they work for someone else. Gate AI sits inline on every request and stops it. Launching June 2026.

AI coding agents have access to your API keys, your codebase, your production environment. One prompt injection and they work for someone else. Gate AI sits inline on every request and stops it. Launching June 2026.

Constellation²

12,136,687 views • 4 months ago