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 the Tasklet sandbox VM. Every agent now gets its own Linux environment with Python, ffmpeg, imagemagick, and a persistent filesystem. Create, process & transfer files, use code to analyze data, make network requests, install packages & more.

Tasklet

3,136 subscribers

24,459 views • 8 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude can use code to analyze data, create files, and visualize insights in the files & formats you use. Now available to all paid plans in preview. We've also made the Claude for Chrome extension available to everyone who joined the waitlist last month.

Claude can use code to analyze data, create files, and visualize insights in the files & formats you use. Now available to all paid plans in preview. We've also made the Claude for Chrome extension available to everyone who joined the waitlist last month.

Claude

129,306 views • 11 months ago

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

Anicet

35,735 views • 8 months ago

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

What if you can build an Agent with it own computer in a single api call? At my Google I/O talk, I showed how to use Gemini Managed Agents and the new Interactions API to give your AI a secure, hosted Linux sandbox to execute code and manage its own memory.

Philipp Schmid

21,769 views • 3 months ago

Dev updates for AlphaPulse AI March - Can now write and execute code in its own sandbox environment. - Can create and display personalized visualizations, dashboards & reports with real time data on demand. - Integrated MCP tools for analysis including perplexity, perplexity deepsearch, browser use, crypto twitter (Elfa AI, Masa) coingecko, dexscreener, pumpfun, github and more. - Integrated Heurist's Mesh MCP, an extensive agent framework, unlocking seamless access to 30+ crypto native agents.

Dev updates for AlphaPulse AI March - Can now write and execute code in its own sandbox environment. - Can create and display personalized visualizations, dashboards & reports with real time data on demand. - Integrated MCP tools for analysis including perplexity, perplexity deepsearch, browser use, crypto twitter (Elfa AI, Masa) coingecko, dexscreener, pumpfun, github and more. - Integrated Heurist's Mesh MCP, an extensive agent framework, unlocking seamless access to 30+ crypto native agents.

Aiccelerate

53,923 views • 1 year ago

🚀 The team at Google just released the Agents API, a service for building and running custom agents inside a sandboxed Linux environment, and we built a template that gives these agents access to LlamaParse / LiteParse, enabling them to process unstructured documents automatically 📄⚡ Here’s how it works: 🔹 Configure a Git repository where data and outputs will be stored 🔹 Clone the repository into the agent sandbox 🔹 Install the LiteParse CLI, the LlamaParse SDK, and agent skills to use both 🔹 Prompt the agent with a task and watch it process documents autonomously 🤖 The result? An agent that can work directly with messy, real-world documents using LlamaParse and LiteParse within Google’s new agent runtime. Check out the GitHub repository: Get started with LlamaParse:

🚀 The team at Google just released the Agents API, a service for building and running custom agents inside a sandboxed Linux environment, and we built a template that gives these agents access to LlamaParse / LiteParse, enabling them to process unstructured documents automatically 📄⚡ Here’s how it works: 🔹 Configure a Git repository where data and outputs will be stored 🔹 Clone the repository into the agent sandbox 🔹 Install the LiteParse CLI, the LlamaParse SDK, and agent skills to use both 🔹 Prompt the agent with a task and watch it process documents autonomously 🤖 The result? An agent that can work directly with messy, real-world documents using LlamaParse and LiteParse within Google’s new agent runtime. Check out the GitHub repository: Get started with LlamaParse:

LlamaIndex 🦙

21,975 views • 3 months ago

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or agentically create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Jerry Liu

77,373 views • 11 months ago

Pair programming with ChatGPT with access to my file system that can: - edit files on its own - run ANY bash command - write, run, debug Python & JS code - create & run Git commands I didn't even know has been the most exhilarating experience since I started coding 11 years ago

Pair programming with ChatGPT with access to my file system that can: - edit files on its own - run ANY bash command - write, run, debug Python & JS code - create & run Git commands I didn't even know has been the most exhilarating experience since I started coding 11 years ago

YK aka CS Dojo 📺🐦

234,683 views • 3 years ago

Gave Prime Intellect's new self-improving agent an E2B sandbox and told it to play Factorio. Factorio is a long-horizon test of world models: the agent has to learn a new system, predict the effects of its actions, and adapt when its assumptions are wrong. That requires a persistent sandbox like E2B that can keep the game running and retain its state while the agent works. Spin up a lot of sandboxes and benchmark prime agent or run your own evals with E2B. Try it yourself: e2b sbx create prime

Gave Prime Intellect's new self-improving agent an E2B sandbox and told it to play Factorio. Factorio is a long-horizon test of world models: the agent has to learn a new system, predict the effects of its actions, and adapt when its assumptions are wrong. That requires a persistent sandbox like E2B that can keep the game running and retain its state while the agent works. Spin up a lot of sandboxes and benchmark prime agent or run your own evals with E2B. Try it yourself: e2b sbx create prime

Vasek Mlejnsky

22,994 views • 1 month ago

Introducing the Orca Mobile Emulator. AI agents can now use mobile apps inside Orca ADE. Each worktree gets its own emulator — so you and your agents can build, test, debug, and validate mobile flows right where the code lives. Works with Codex, Claude Code, OpenCode, or any agent.

Introducing the Orca Mobile Emulator. AI agents can now use mobile apps inside Orca ADE. Each worktree gets its own emulator — so you and your agents can build, test, debug, and validate mobile flows right where the code lives. Works with Codex, Claude Code, OpenCode, or any agent.

Orca ADE

31,191 views • 3 months 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:

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

20,810 views • 3 months ago

Lots of people asked how I used Fable to edit its own launch video so I made a video about that! TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it. I didn't touch a video editor.

Lots of people asked how I used Fable to edit its own launch video so I made a video about that! TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it. I didn't touch a video editor.

Thariq is on vacation

1,076,269 views • 2 months ago

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel by the agent, clonable to your heart's desire

Grace Li

169,041 views • 11 months ago

We tried OWL with 𝐆𝐞𝐦𝐢𝐧𝐢 𝟐.𝟓 𝐏𝐫𝐨 (the results were seriously impressive) We gave the agent a task: "Research Gemini 2.5 Pro, get its benchmark scores, write Python code to plot them, and run it." It did everything on its own: ✔️ Collected benchmark data ✔️ Wrote clean python code ✔️ Saved both the chart + code locally No manual steps. Just full-on autonomous execution. This is how agent workflows should feel in 2025. You can try it, check the code, or run your own workflows:

We tried OWL with 𝐆𝐞𝐦𝐢𝐧𝐢 𝟐.𝟓 𝐏𝐫𝐨 (the results were seriously impressive) We gave the agent a task: "Research Gemini 2.5 Pro, get its benchmark scores, write Python code to plot them, and run it." It did everything on its own: ✔️ Collected benchmark data ✔️ Wrote clean python code ✔️ Saved both the chart + code locally No manual steps. Just full-on autonomous execution. This is how agent workflows should feel in 2025. You can try it, check the code, or run your own workflows:

CAMEL-AI.org

20,256 views • 1 year ago

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

Introducing RAGs, a Streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you specify. The app contains three main pages: 🏠 Home Page : Have a “builder agent” build your RAG agent through natural language (you specify the data). ⚙️ RAG Config: Look at configured parameters 🤖 Use your RAG agent! Check out details below 👇 Blog: Repo:

LlamaIndex 🦙

475,732 views • 2 years ago

Every PM should be using Claude Code. So I built a HUGE course for you to learn Claude Code... IN Claude Code! 🔹 Complete guide 🔹 Make PRDs, analyze data, create decks Soon, I'll sell it for $149. For the next 24h: FREE! Follow + RT + comment "CC" & I'll DM it.

Every PM should be using Claude Code. So I built a HUGE course for you to learn Claude Code... IN Claude Code! 🔹 Complete guide 🔹 Make PRDs, analyze data, create decks Soon, I'll sell it for $149. For the next 24h: FREE! Follow + RT + comment "CC" & I'll DM it.

Carl Vellotti 🥞

465,135 views • 10 months ago

you don't have to keep your laptop open for your agents to keep running just type /handoff and send your agent to the cloud with Devin (and close your laptop) from there, your agent gets: - its own Linux VM - shell, IDE, browser - full desktop Computer Use - end-to-end test recordings - ready-to-review PRs - it's own review agent you can continue your session from your phone, computer, or anywhere with an internet connection and you can send as many sessions as you'd like in parallel.

you don't have to keep your laptop open for your agents to keep running just type /handoff and send your agent to the cloud with Devin (and close your laptop) from there, your agent gets: - its own Linux VM - shell, IDE, browser - full desktop Computer Use - end-to-end test recordings - ready-to-review PRs - it's own review agent you can continue your session from your phone, computer, or anywhere with an internet connection and you can send as many sessions as you'd like in parallel.

nader dabit

61,479 views • 4 months ago

pr reviews with Tembo are on another level. this isn't static diff analysis. every pr gets its own vm, runs with any agent you choose, and reviews your code like a real engineer would. fully customizable instructions, plus the ability to pull in sentry or any other context. this is what agentic pr reviews were supposed to be.

pr reviews with Tembo are on another level. this isn't static diff analysis. every pr gets its own vm, runs with any agent you choose, and reviews your code like a real engineer would. fully customizable instructions, plus the ability to pull in sentry or any other context. this is what agentic pr reviews were supposed to be.

benja

13,624 views • 8 months ago

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

deployer

45,638 views • 4 months ago

Announcing Agent Recipes! A site to learn about agent/workflow recipes with code examples that you can easily copy & paste into your own AI apps. I'm gonna make this the go-to resource for devs to learn about agents & how to implement them – more soon.

Announcing Agent Recipes! A site to learn about agent/workflow recipes with code examples that you can easily copy & paste into your own AI apps. I'm gonna make this the go-to resource for devs to learn about agents & how to implement them – more soon.

Hassan

256,250 views • 1 year ago

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

475,005 views • 3 months ago