正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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... show more

Vasek Mlejnsky

8,909 subscribers

21,634 次观看 • 2 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Daniel Liao 的头像

Daniel Liao2 天前

@OpenAI @e2b LETS GO! Big Day for all the devs out there

安叫兽|Bird🕊️ 🔶 BNB 的头像

安叫兽|Bird🕊️ 🔶 BNB2 天前

@OpenAI @e2b 这组合起来终于像能干活的 agent 了

John Rood 的头像

John Rood2 天前

@OpenAI @e2b auto-pause + fork is the important part. the durable primitive isn't a long-running machine. it's replayable task state that can hydrate into a clean machine, branch, and resume.

Vext Labs 的头像

Vext Labs2 天前

@OpenAI @e2b hosted harness, isolated execution — the right split

Michael Waitze 的头像

Michael Waitze2 天前

@OpenAI @e2b The way it handles orchestration and long-running sessions is actually quite impressive.

catman 的头像

catman2 天前

@OpenAI @e2b auto-pausing each sandbox between turns could make long agent sessions much cheaper; how quickly does a resumed machine come back?

gleb 的头像

gleb2 天前

@OpenAI @e2b The isolated filesystem plus preinstalled tools is the part that matters most in practice. Most of my agent failures used to come from environment drift, not the model. Good to see that getting solved at the infra layer instead of every project rebuilding it.

Lawrence Tang 的头像

Lawrence Tang2 天前

@OpenAI @e2b Auto-pause between turns is the product, not a missing automation. A hosted harness that keeps going with no human gate is just a runaway script with better branding. Forks only help if the failed branch can’t write back by default.

Ben Mo 的头像

Ben Mo1 天前

@OpenAI @e2b The fork is the part I'd like to see explored more. A side-by-side view of what each attempt changed would make "try another approach" much easier to judge than scrolling two chat histories.

Shlok Madhekar 的头像

Shlok Madhekar2 天前

@OpenAI @e2b how's your cold start time on spinning up a fresh e2b sandbox per session?

相关视频

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 次观看 • 1 个月前

Cursor x E2B Many of our customers use E2B in their internal development workflows. Some work in regulated industries where code and internal services can’t leave the company. For teams that need control over the execution environment, Cursor’s cloud agents can now use E2B as their machine. With Self-Hosted Machines, Cursor handles the agent loop while E2B runs the code. Teams can give agents bigger machines and start them from custom E2B templates, so their Cursor workloads boot straight into an environment with internal dependencies already in place. Try it:

Cursor x E2B Many of our customers use E2B in their internal development workflows. Some work in regulated industries where code and internal services can’t leave the company. For teams that need control over the execution environment, Cursor’s cloud agents can now use E2B as their machine. With Self-Hosted Machines, Cursor handles the agent loop while E2B runs the code. Teams can give agents bigger machines and start them from custom E2B templates, so their Cursor workloads boot straight into an environment with internal dependencies already in place. Try it:

Vasek Mlejnsky

71,864 次观看 • 10 天前

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

16,666 次观看 • 3 个月前

OPENAI 🔥: As tradition dictates, OpenAI plans to announce a new solution for its agent ecosystem at the upcoming DevDay 2026. This time, we will get Managed Agents 🤖 > Users will be able to create Agents, Environments, and Agent Sessions directly via the OpenAI Platform. > The Codex Plugin will help users build, configure, and deploy agents, lowering the barrier to entry. > OpenAI's Managed Agents could be hosted on the OpenAI platform or self-hosted. Loads of details inside 👀

OPENAI 🔥: As tradition dictates, OpenAI plans to announce a new solution for its agent ecosystem at the upcoming DevDay 2026. This time, we will get Managed Agents 🤖 > Users will be able to create Agents, Environments, and Agent Sessions directly via the OpenAI Platform. > The Codex Plugin will help users build, configure, and deploy agents, lowering the barrier to entry. > OpenAI's Managed Agents could be hosted on the OpenAI platform or self-hosted. Loads of details inside 👀

🚨 AI News | TestingCatalog

113,102 次观看 • 6 天前

Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique. Available in public beta.

Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context management. You focus on what makes your agent unique. Available in public beta.

OpenAI Developers

1,789,112 次观看 • 2 天前

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 次观看 • 3 个月前

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:

Introducing the $COFFEE App & SDK - the versatile on-chain Agent infrastructure that allows anyone to build custom agents. Try it now: Any repo, language, framework, or plugin can now be added to agents. Build plugins, create agents, sell on our marketplace, and chat with Agents that can take on-chain actions. This is just the beginning. The foundation has been built. Together let’s integrate the powerful tools and plugins from the #Solana and #ETH ecosystems into the $COFFEE marketplace. We have some exciting plugins of popular agent repos we will be adding in the coming days and partnerships in the works. Stay tuned! ☕️ SDK and APIs to build custom, enterprise-grade agents:

Coffee - ai/acc ☕️

15,579 次观看 • 1 年前

LFG! Nous Research's Hermes Agent is live on the Umbrel App Store! It's an AI agent that gets smarter the longer it runs, remembers stuff with persistent memory across sessions, learns your workflow, and autonomously creates its own reusable skills from experience. And it's sandboxed like every Umbrel app so it can't touch anything it's not supposed to. 1-click install. Login with ChatGPT, use an OpenRouter/OpenAI/Anthropic API key, or point it to a local Ollama model running on the same Umbrel.

LFG! Nous Research's Hermes Agent is live on the Umbrel App Store! It's an AI agent that gets smarter the longer it runs, remembers stuff with persistent memory across sessions, learns your workflow, and autonomously creates its own reusable skills from experience. And it's sandboxed like every Umbrel app so it can't touch anything it's not supposed to. 1-click install. Login with ChatGPT, use an OpenRouter/OpenAI/Anthropic API key, or point it to a local Ollama model running on the same Umbrel.

Umbrel ☂️

29,882 次观看 • 4 个月前

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Q*bert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Q*bert, but GitLawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

Agent Zero crushed Codex by 2.6× on token efficiency! We gave both agents the same task on the same local model (Qwen3.6 27B): build a retro Qbert arcade game. Each agent wrote and rewrote it across iterations, adding enemies and a HUD. Outputs: • Agent Zero: 239K tokens, 53 min • Codex: 627K tokens, 51 min Both agents built a working Qbert, but GitLawb 's Agent Zero is the cleaner build, with crisper textures and hops that land where they should. Codex refills the context window with its whole history every turn, so the model loses the thread and hallucinates code it never wrote. Agent Zero sends only what's new, so it keeps more of the window open and makes fewer mistakes. Run agents on local AI models in Atomic Chat!

atomic.chat

320,187 次观看 • 1 个月前

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

chetan conikee

469,402 次观看 • 3 个月前

AI agents can now pay for onchain data on their own. No signups, no API keys, no human in the loop. Zerion API supports x402 payments on Base. An agent calls an endpoint, pays $0.01 USDC from its wallet, and gets back portfolio balances, DeFi positions, PnL, token prices. Try it →

AI agents can now pay for onchain data on their own. No signups, no API keys, no human in the loop. Zerion API supports x402 payments on Base. An agent calls an endpoint, pays $0.01 USDC from its wallet, and gets back portfolio balances, DeFi positions, PnL, token prices. Try it →

Zerion

30,430 次观看 • 5 个月前

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Paul Klein IV

1,730,259 次观看 • 5 个月前

🚀 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 次观看 • 3 个月前

Most AI agents stop at chat. Agent Max is built for what comes after. Max tools. Max control and configurability. Max production readiness. Your agent can use: • any tools, APIs, MCP, and workflows • built-in knowledge: docs/website • multi-model: OpenAI, Claude, Gemini... • agent-to-agent handoffs • human-in-the-loop • logs, usage tracking, environments, and RBAC • enterprise controls for SOC2/GDPR/HIPAA/ISO needs • hosted chat UI, API, Skill in agents, Slack, WhatsApp, Teams, Voice, and more Agent Max is live now in BuildShip for everyone. Give it a try, or comment/DM to book a demo if you want help setting up your first agent.

Most AI agents stop at chat. Agent Max is built for what comes after. Max tools. Max control and configurability. Max production readiness. Your agent can use: • any tools, APIs, MCP, and workflows • built-in knowledge: docs/website • multi-model: OpenAI, Claude, Gemini... • agent-to-agent handoffs • human-in-the-loop • logs, usage tracking, environments, and RBAC • enterprise controls for SOC2/GDPR/HIPAA/ISO needs • hosted chat UI, API, Skill in agents, Slack, WhatsApp, Teams, Voice, and more Agent Max is live now in BuildShip for everyone. Give it a try, or comment/DM to book a demo if you want help setting up your first agent.

BuildShip

75,946 次观看 • 2 个月前

elon musk grabbed the source code openai open-sourced by accident, rewrote it in rust over a weekend, and shipped it as a free coding agent that does everything $200/mo chatgpt pro does. why pay $200 to openai and $200 to claude when this runs for $8 the swarm above is one weekend of exactly that: thousands of agents pouring through four endpoints, three paid seats billing $1.80 a task while the free fork bills $0. musk co-founded openai, walked out, and when they left codex on github under a permissive license, he forked it, stamped grok on it, and gave it away what the free version does that the $200 seat charges for: the agent · openai's own engine -> it reads your repo, writes patches, runs your tests, and loops until they pass, exactly like codex -> because under the hood it is codex, just faster and free. you are paying $200 for the paid skin of a tool now sitting on github the license · apache-2.0, un-revocable -> free to use, free to fork, free to ship inside your own product with zero strings -> openai cannot pull it back. musk made sure the license is the kind that never expires the switch · one line, no new tools -> point it at any openai-compatible or claude-compatible endpoint, including an $8 kimi backend -> same terminal, same workflow, gpt-5.6 and opus 5 just quietly lose the seat the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the free agent plus an $8 kimi key does the same daily work -> that is a 98% cut, built out of openai's own source code, handed to you by the guy suing them here is the part they will fight me on: openai did not lose this to a better model, they lost it to their own license and an enemy with a weekend free. the $200 was never the tool, it was the toll, and musk just put openai's own logo on the road around it drop your $400/mo ai stack to $8. the run above is openai's own agent, rewritten free, doing the job it bills $200 a month for. the full breakdown is in the article below

starmex

111,101 次观看 • 17 天前

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

Scrapybara

89,707 次观看 • 1 年前

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 次观看 • 1 年前

New course: Build agents that respond to users with not only plaintext, but custom UIs like charts, forms, and whiteboards, generated on demand and displayed right in the chat. This short course is built in partnership with CopilotKit🪁 and taught by Atai Barkai, co-founder of CopilotKit. You'll learn three approaches: Your agent can pick from custom components you build, like charts and forms. It can compose new layouts from a set of building blocks you provide, like rows, cards, and text. Or it can incorporate existing third-party apps, like a whiteboard or a calendar, right inside the conversation. Skills you’ll gain: - Build agents that render custom components like charts and forms on demand - Build an app where the agent and user collaborate on shared data, beyond just the chat window - Place third-party apps like maps, calendars, and whiteboards right in your interface Join and build agents that give users something to see and act on!

New course: Build agents that respond to users with not only plaintext, but custom UIs like charts, forms, and whiteboards, generated on demand and displayed right in the chat. This short course is built in partnership with CopilotKit🪁 and taught by Atai Barkai, co-founder of CopilotKit. You'll learn three approaches: Your agent can pick from custom components you build, like charts and forms. It can compose new layouts from a set of building blocks you provide, like rows, cards, and text. Or it can incorporate existing third-party apps, like a whiteboard or a calendar, right inside the conversation. Skills you’ll gain: - Build agents that render custom components like charts and forms on demand - Build an app where the agent and user collaborate on shared data, beyond just the chat window - Place third-party apps like maps, calendars, and whiteboards right in your interface Join and build agents that give users something to see and act on!

Andrew Ng

214,564 次观看 • 4 个月前

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Finally, an open-source runtime security layer for your agent harnesses. AI agents can call tools, run shell commands, modify files, and interact with production systems. But when something goes wrong, teams often have to reconstruct what the agent actually did from scattered logs after the fact. Agent Beacon is built to change that. It runs locally and records agent activity as it happens, including: → Tool calls → Shell commands → File changes → Approval decisions → Session and harness context The useful part is that it normalizes all of this into the same event format across 23+ agent harnesses. So instead of writing different detection logic for Claude Code, Codex, or another harness, security teams can reason about the underlying action itself. A command executed is a command executed, regardless of which harness produced it. Beacon also records how confidently an event was captured. An action can be directly observed from the runtime or inferred from indirect evidence. That matters when you start writing security rules against this data. For example, you can detect when an agent reads an environment variable, modifies a sensitive file, executes a suspicious command, or performs an action without the expected approval. And the detection happens while the session is still unfolding, not days later during incident reconstruction. Everything runs locally by default. You can inspect sessions through the dashboard, write your own detection rules, or forward the same normalized events to tools like Splunk, Datadog, Elastic, Sentinel, or CrowdStrike. Beacon GitHub: (don't forget to star 🌟) I also wrote a detailed article on the same, covering how important runtime security is and how to build it for your agent harnesses. The article is quoted below.

Akshay 🚀

26,036 次观看 • 3 天前