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.

Just implemented Code Sandbox for TypingMind 🥳 I was looking at various options for sandbox and code execution, but for now the most obvious choice is to use the built-in sandbox provided by all popular providers: OpenAI/Gemini/Claude. It can create files but not yet able to accept file input,... show more

Tony Dinh

204,560 subscribers

50,398 views • 8 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Rohidas8 months ago

Nowadays I forgot about Open AI playground. 😀 Need to revisit.

Dimi8 months ago

Is it on the client-side or on the server side?

Tony Dinh8 months ago

Server side

Dimi8 months ago

Met this guy in Da nang, building this: seems dope for what you're doing

Tony Dinh8 months ago

Pretty cool! So curious they didn't put the limitations in the website. It seems too good to be true.

Dimi8 months ago

he's doing some upgrades rn, but overall seems cool because you can delegate heavy stuff onto the users machine :)

Rex Pearson8 months ago

Hi Tony I’m currently trying to get in touch with your business support Ngoc and having trouble reaching him about our instance of typing mind for schools. Is there any way to get a response as we are about to launch your product in the education space….

ShipAloneCEO8 months ago

That's awesome! Built-in sandboxes can really simplify things. - Explore custom configurations next. - Evaluate performance from users too. - Keep an eye on updates for new features.

Andrew Humanji8 months ago

What's the biggest limitation you've hit so far?

Yash Solanki8 months ago

@fermionapp also provides sandbox execution

Related Videos

we are open sourcing devin but better. Zuse brings cloud agents: - use your own subscriptions, only pay for sandbox runtime - Boat (super cheap) or E2B (fast spinups) for sandboxes more coming soon - sync files to local to test - run commands on your Mac without reinstalling CLIs in the cloud - clone / open repos using SSH link in reply

we are open sourcing devin but better. Zuse brings cloud agents: - use your own subscriptions, only pay for sandbox runtime - Boat (super cheap) or E2B (fast spinups) for sandboxes more coming soon - sync files to local to test - run commands on your Mac without reinstalling CLIs in the cloud - clone / open repos using SSH link in reply

swaraj

31,835 views • 14 days ago

Claude Code is turning vibe coding into a video game. In a few days Vibecode will be the easiest way to use Claude Code to build professional mobile apps, and web apps. Use Claude Code in a safe sandbox. Create any interface or application. Create skills and commands. Add integrations and API's. And a lot more. For early access reply below. I'll DM you.

Claude Code is turning vibe coding into a video game. In a few days Vibecode will be the easiest way to use Claude Code to build professional mobile apps, and web apps. Use Claude Code in a safe sandbox. Create any interface or application. Create skills and commands. Add integrations and API's. And a lot more. For early access reply below. I'll DM you.

Riley Brown

96,365 views • 9 months ago

OpenAI's new Agents API is a hosted Codex runtime that can connect to sandboxes like E2B. OpenAI manages the model, harness, and agent sessions, while code executes on an isolated E2B machine with its own filesystem and preinstalled tools. We built an agent workbench where each chat runs on its own machine. It starts from a custom template, auto-pauses between turns, forks to try another approach from the same starting point, and can even act on videos inside the sandbox. Thanks Ondrej for the workbench demo! Try it: e2b sbx create openai-agents-api-python-sdk Build on top of the workbench: Docs:

OpenAI's new Agents API is a hosted Codex runtime that can connect to sandboxes like E2B. OpenAI manages the model, harness, and agent sessions, while code executes on an isolated E2B machine with its own filesystem and preinstalled tools. We built an agent workbench where each chat runs on its own machine. It starts from a custom template, auto-pauses between turns, forks to try another approach from the same starting point, and can even act on videos inside the sandbox. Thanks Ondrej for the workbench demo! Try it: e2b sbx create openai-agents-api-python-sdk Build on top of the workbench: Docs:

Vasek Mlejnsky

23,210 views • 28 days ago

I just love creating/designing using awesome AI driven tools like the new The Sandbox Studio + Codex from OpenAI (I personally use GPT 5.5, I prefer it over Claude models) But I cleaned up some bottlenecks, so now it's running 60 FPS, and added some basic 🕷️ models to attack and changed the path design + animated grass and trees with a stylized look. And added some animated wtaer ripples near the edges which I like. But I'll probably add some color variation like I had before back into the mix. Definitely not perfect yet, but, work in progress! #SAND #vibecoding #gamedev #gamejam The Sandbox Creators Three.js

I just love creating/designing using awesome AI driven tools like the new The Sandbox Studio + Codex from OpenAI (I personally use GPT 5.5, I prefer it over Claude models) But I cleaned up some bottlenecks, so now it's running 60 FPS, and added some basic 🕷️ models to attack and changed the path design + animated grass and trees with a stylized look. And added some animated wtaer ripples near the edges which I like. But I'll probably add some color variation like I had before back into the mix. Definitely not perfect yet, but, work in progress! #SAND #vibecoding #gamedev #gamejam The Sandbox Creators Three.js

Ricardo de Zoete | Hammy(.eth)

18,696 views • 3 months ago

Have you tried Gemini Managed Agents? A single API call gives you a cloud sandbox where the Antigravity agent can research, code, and complete tasks. Can try it in the Google AI Studio playground or use our SDK to build agents into your own apps. Lots more on this soon! 😀

Have you tried Gemini Managed Agents? A single API call gives you a cloud sandbox where the Antigravity agent can research, code, and complete tasks. Can try it in the Google AI Studio playground or use our SDK to build agents into your own apps. Lots more on this soon! 😀

Jack Wotherspoon

11,727 views • 13 days ago

$Running Claude Code Agents in Docker and it's working great 👏 Just executed this and watched Claude build a complete Express REST API inside an isolated container: npx claude-code-templates@latest --sandbox docker \ --agent development-team/backend-architect \ --prompt "Create a REST API with Express with validation and error handling" - Container spins up - installs Claude Agent SDK - downloads the agent - Claude starts coding Everything visible in Docker logs. Output: Full Express project with routes, validation, error handling. All files extracted to local after execution. Next tutorials: Adding Telemetry and Hooks to monitor what Claude does inside the container. Running these agents on ECS or Kubernetes would be interesting 🤔$

Running Claude Code Agents in Docker and it's working great 👏 Just executed this and watched Claude build a complete Express REST API inside an isolated container: npx claude-code-templates@latest --sandbox docker \ --agent development-team/backend-architect \ --prompt "Create a REST API with Express with validation and error handling" - Container spins up - installs Claude Agent SDK - downloads the agent - Claude starts coding Everything visible in Docker logs. Output: Full Express project with routes, validation, error handling. All files extracted to local after execution. Next tutorials: Adding Telemetry and Hooks to monitor what Claude does inside the container. Running these agents on ECS or Kubernetes would be interesting 🤔

Daniel San

100,028 views • 11 months ago

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 views • 7 months ago

Agent37 - is the most affordable sandbox for teams building agents. We're 94% lower cost than most sandbox providers. Every team building an AI agent product ends up rebuilding the same plumbing. Each agent needs its own private computer that keeps its files, wakes when someone messages it, and costs almost nothing while idle. That's why we built Agent37. It comes with - Ready to launch templates for agent harness like Hermes, Claude Code, OpenCode etc. - Managed MCPs for 1000+ app integrations - Metered payments per minute instead of locking into monthly subscriptions. Tag anyone who's building agents today. I will send them my calendar link & help launch real quick. Y Combinator

Agent37 - is the most affordable sandbox for teams building agents. We're 94% lower cost than most sandbox providers. Every team building an AI agent product ends up rebuilding the same plumbing. Each agent needs its own private computer that keeps its files, wakes when someone messages it, and costs almost nothing while idle. That's why we built Agent37. It comes with - Ready to launch templates for agent harness like Hermes, Claude Code, OpenCode etc. - Managed MCPs for 1000+ app integrations - Metered payments per minute instead of locking into monthly subscriptions. Tag anyone who's building agents today. I will send them my calendar link & help launch real quick. Y Combinator

An Engineer's Log

187,108 views • 9 days ago

Theorem co-founders Rajashree Agrawal + Jason Gross on how you actually prove an AI agent can’t escape its sandbox, and what happens when the proof exposes a way out: Jason Gross: "Anything that the agent does inside the sandbox will not result in some canary file outside the sandbox getting changed." Rajashree Agrawal: "We intend to have one by the end of the year. We've got a verified sandbox now, and the goal is to keep adding features in collaboration with the AI labs." Jason Gross: "If the AI can guess the secret root key of the package server, then it can do anything. Either I try to prove that the AI is not going to be able to guess that, or I design the system so that the channel just doesn't allow it to authenticate that way." "You also want to prove that on most inputs there's no change in behavior. Because otherwise it could make it inescapable by saying, well, sandbox just shuts down as soon as it starts." Theorem

Theorem co-founders Rajashree Agrawal + Jason Gross on how you actually prove an AI agent can’t escape its sandbox, and what happens when the proof exposes a way out: Jason Gross: "Anything that the agent does inside the sandbox will not result in some canary file outside the sandbox getting changed." Rajashree Agrawal: "We intend to have one by the end of the year. We've got a verified sandbox now, and the goal is to keep adding features in collaboration with the AI labs." Jason Gross: "If the AI can guess the secret root key of the package server, then it can do anything. Either I try to prove that the AI is not going to be able to guess that, or I design the system so that the channel just doesn't allow it to authenticate that way." "You also want to prove that on most inputs there's no change in behavior. Because otherwise it could make it inescapable by saying, well, sandbox just shuts down as soon as it starts." Theorem

MTS

18,080 views • 17 days ago

How do you deploy AI agents for financial institutions without compromising on security, isolation, or scale? Rogo powers complex research, analysis, and deal workflows for leading financial firms, supporting complex tasks across tens of thousands of concurrent users. To meet the diverse needs of financial teams, Rogo relies on both specialist and general-purpose agents that can adapt to a wide range of workflows. With Claude Managed Agents and self-hosted sandboxes, Rogo gets the orchestration and post-training capabilities needed to design these agent systems, while E2B provides the execution layer underneath. Every piece of code generated by an agent runs inside its own E2B sandbox with full auditability and traceability. Each sandbox is powered by an isolated microVM, providing the kernel-level isolation critical for Rogo's customers. The result is a seamless agent experience backed by the security, reliability, and compliance requirements that financial institutions demand.

How do you deploy AI agents for financial institutions without compromising on security, isolation, or scale? Rogo powers complex research, analysis, and deal workflows for leading financial firms, supporting complex tasks across tens of thousands of concurrent users. To meet the diverse needs of financial teams, Rogo relies on both specialist and general-purpose agents that can adapt to a wide range of workflows. With Claude Managed Agents and self-hosted sandboxes, Rogo gets the orchestration and post-training capabilities needed to design these agent systems, while E2B provides the execution layer underneath. Every piece of code generated by an agent runs inside its own E2B sandbox with full auditability and traceability. Each sandbox is powered by an isolated microVM, providing the kernel-level isolation critical for Rogo's customers. The result is a seamless agent experience backed by the security, reliability, and compliance requirements that financial institutions demand.

Vasek Mlejnsky

16,858 views • 3 months ago

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

125,326 views • 9 months ago

In BCGW #213, I talk to CEO Robby Yung ⦿⦿⦿ about how AI reboots The Sandbox 01:10 How Robby Yung sees the past 12 months in blockchain games. 03:30 How adoption of AI changes game development and distribution. 06:48 One problem for The Sandbox was that its original tools were too simple for pro developers. 08:22 How can The Sandbox employ AI to support professional creators? 10:01 Can you maintain The Sandbox's brand if you move away from its voxel art style? 11:21 Adding AI to The Sandbox has been ongoing for around 3 years. 13:05 In the future, game studios will be much smaller because of AI. 14:50 But will indie devs actually use AI tools? Many seem to hate AI. 17:02 The Sandbox's AI tools are designed to give developers absolute control. 20:30 Using AI, game devs will be more creative and publish across multiple platforms. 23:00 Does this level of AI portability undermine The Sandbox as a platform? 25:10 "We view the metaverse as the world and The Sandbox as a city." 28:14 The goal is not to automate game creation but to give creative people better tools. 29:02 Why The Sandbox is running game jams prior to Studio's planned October launch. 31:43 AI is amazing but only when it does what you ask it to do. You need granular control. 33:15 Sandbox Studio is designed for people who are already using Unity and Unreal.

jon jordan

26,489 views • 1 month ago

🚨 Anthropic just dropped its 🦞 OpenClaw🦞 competitor Meet Dispatch. A new research preview in Claude Cowork that completely changes how you interact with AI. Here’s how it works: 1️⃣ Pairs your phone to a persistent Claude session on your desktop 2️⃣ Message tasks on the go, come back to finished work 3️⃣ Executes code in a secure, local sandbox Your files stay 100% local and private, and Claude asks for your approval before touching anything Sure, the desktop needs to stay on, but the flexibility is insane. Rolling out now to Max users (Pro coming soon). Time to pair that phone! 👀

🚨 Anthropic just dropped its 🦞 OpenClaw🦞 competitor Meet Dispatch. A new research preview in Claude Cowork that completely changes how you interact with AI. Here’s how it works: 1️⃣ Pairs your phone to a persistent Claude session on your desktop 2️⃣ Message tasks on the go, come back to finished work 3️⃣ Executes code in a secure, local sandbox Your files stay 100% local and private, and Claude asks for your approval before touching anything Sure, the desktop needs to stay on, but the flexibility is insane. Rolling out now to Max users (Pro coming soon). Time to pair that phone! 👀

Charly Wargnier ♨️

468,586 views • 6 months ago

> Training Grok 4.1 or Claude Opus 4.5 to trade gold futures???? > Everyone talking about clawd bot > What if there was a clawd bot for money... wait that's pigeon > pigeon is an omnipresent ai agent that you can control using sms, discord, telegram, or claude code > can continuously do research and even code and run the code on a secure sandbox > here i attempt to lose $100 by shorting into the greatest gold bull run in history on ostium

> Training Grok 4.1 or Claude Opus 4.5 to trade gold futures???? > Everyone talking about clawd bot > What if there was a clawd bot for money... wait that's pigeon > pigeon is an omnipresent ai agent that you can control using sms, discord, telegram, or claude code > can continuously do research and even code and run the code on a secure sandbox > here i attempt to lose $100 by shorting into the greatest gold bull run in history on ostium

jason kim

10,573 views • 8 months ago

I’ve been using quite heavily over the past few days, alongside Claude Code on its other platforms. The first thing that caught my attention was the “Research preview” label, which likely indicates that this experience is still in an experimental phase. That said, compared to Claude Desktop in Code mode, the web version feels slightly more advanced. You can select branches, and previous sessions display clear status icons, which is a small but very meaningful UX improvement. My impression: I liked it much more than Claude Desktop, especially the use of branches, which is essential when working with agents outside a local environment. What’s missing: The sandbox is very limited. It only allows installing packages from PyPI (maybe npm as well, but I didn’t test it). CLI tools are essential in these environments. I tried installing GitHub CLI (gh), but it failed due to network restrictions. Even though I had all the required domains enabled in Claude’s settings, this execution sandbox clearly does not respect that configuration. Another important issue: environment variables added through the UI are not automatically picked up by the sandbox runtime. I had to restart the session for it to recognize the GitHub token I had just added. I also tried installing the Vercel CLI, without success. In the end, Claude usually finds a workaround, but it burns a lot of tokens trying different installation strategies or alternative external calls. What I would add: In the development environment settings, it should be possible to: Configure the sandbox’s network access and define which CLI tools and packages come preinstalled I don’t want to waste tokens installing gh, vercel, wrangler, or supabase CLIs over and over again. These are relatively simple changes that would dramatically improve execution quality and efficiency on the web. If you’re interested in trying I hope this feedback is useful. It’s definitely a tool worth paying attention to, especially since it syncs with Claude Mobile, allowing you to start a task on your phone and continue it later on your computer. Hope this feedback helps Boris Cherny Thariq Anthony Morris ツ

I’ve been using quite heavily over the past few days, alongside Claude Code on its other platforms. The first thing that caught my attention was the “Research preview” label, which likely indicates that this experience is still in an experimental phase. That said, compared to Claude Desktop in Code mode, the web version feels slightly more advanced. You can select branches, and previous sessions display clear status icons, which is a small but very meaningful UX improvement. My impression: I liked it much more than Claude Desktop, especially the use of branches, which is essential when working with agents outside a local environment. What’s missing: The sandbox is very limited. It only allows installing packages from PyPI (maybe npm as well, but I didn’t test it). CLI tools are essential in these environments. I tried installing GitHub CLI (gh), but it failed due to network restrictions. Even though I had all the required domains enabled in Claude’s settings, this execution sandbox clearly does not respect that configuration. Another important issue: environment variables added through the UI are not automatically picked up by the sandbox runtime. I had to restart the session for it to recognize the GitHub token I had just added. I also tried installing the Vercel CLI, without success. In the end, Claude usually finds a workaround, but it burns a lot of tokens trying different installation strategies or alternative external calls. What I would add: In the development environment settings, it should be possible to: Configure the sandbox’s network access and define which CLI tools and packages come preinstalled I don’t want to waste tokens installing gh, vercel, wrangler, or supabase CLIs over and over again. These are relatively simple changes that would dramatically improve execution quality and efficiency on the web. If you’re interested in trying I hope this feedback is useful. It’s definitely a tool worth paying attention to, especially since it syncs with Claude Mobile, allowing you to start a task on your phone and continue it later on your computer. Hope this feedback helps Boris Cherny Thariq Anthony Morris ツ

Daniel San

11,626 views • 8 months ago

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here:

Cursor for Design? This Claude Code UI workflow is insane And many vibe coders not aware of it: 1. Claude Code can assign parallel tasks to sub agents 2. Integrate with git worktree to create sandbox env This means you can get Claude Code generate 10 design at the same time, fork & iterate 🔁 Design is an explorative process, by leveraging sub agent + parallel task capabilities, many interesting product UX can be built; Also turned this workflow into an open-source IDE extension here:

Jason Zhou

40,635 views • 1 year ago

introducing t-rex with t-rex enabled, greptile doesn't just review your PR, it runs your branch in a sandbox to find bugs. it mocks api calls, clicks around the UI, and writes + runs unit tests in our benchmarks, it caught ~20% more bugs than base greptile. most of the new bugs caught could not have been caught with more inference, they required code execution. t-rex is available in beta to all greptile users

introducing t-rex with t-rex enabled, greptile doesn't just review your PR, it runs your branch in a sandbox to find bugs. it mocks api calls, clicks around the UI, and writes + runs unit tests in our benchmarks, it caught ~20% more bugs than base greptile. most of the new bugs caught could not have been caught with more inference, they required code execution. t-rex is available in beta to all greptile users

Daksh Gupta

108,279 views • 3 months ago

The pace at which Gemini 2.5 Pro is improving in code is wild! I generally leaned towards using Claude for code, but now I rely more on Gemini 2.5 Pro. It's just that good! Watch me use Gemini-2.5-Pro-05-06 to go from a YT video to an interactive slide deck app in minutes!

The pace at which Gemini 2.5 Pro is improving in code is wild! I generally leaned towards using Claude for code, but now I rely more on Gemini 2.5 Pro. It's just that good! Watch me use Gemini-2.5-Pro-05-06 to go from a YT video to an interactive slide deck app in minutes!

elvis

81,882 views • 1 year ago

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!

Claude finally killed the need for OpenClaw They launched "Claude Channels" which allows you to control Claude Code from your Telegram / Discord I show you how to set it up in ~6 minutes in mainly 3 steps Step 1: Create bot with BotFather Step 2: Install the Claude plugin Step 3: Pair with a code Now I can code, research, manage files from my phone using Claude Code If you don't watch this tutorial now I highly suggest you bookmark for later!

Chris ☕️

70,433 views • 6 months ago

Claude Code is now included in the Claude Pro plan which means Pro plan subscribers can use their rate limits for Claude apps and Claude Code! To celebrate, here's a conversation with Claude Code's founding engineer, Boris Cherny, on: - how we use Claude Code at Anthropic - underrated tips for using it effectively - the future of coding tools - and more!

Claude Code is now included in the Claude Pro plan which means Pro plan subscribers can use their rate limits for Claude apps and Claude Code! To celebrate, here's a conversation with Claude Code's founding engineer, Boris Cherny, on: - how we use Claude Code at Anthropic - underrated tips for using it effectively - the future of coding tools - and more!

Alex Albert

123,756 views • 1 year ago