# Cloud agent cards for ChatGPT, Claude, Gemini and Jules | CoLateral Source: https://colateralai.com/blog/cloud-agent-cards-chatgpt-claude-gemini-jules [Home](/) [Blog](/blog) [Models and agents](/blog/category/models) # Cloud agent cards for ChatGPT, Claude, Gemini and Jules CoLateral's cloud agent cards, added from 1 October 2026, let you run ChatGPT, Claude Code, Gemini Deep Research and Jules from the Project Canvas, either as the provider's full app in a private Browser Card or as an optional API workflow on a controller card. [Nic Vandewetering](/blog/authors/nic) - October 8, 2026 - 7 min read Covers October 2026 ### On this page 1. [What are cloud agent cards in CoLateral?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#what-are-cloud-agent-cards-in-colateral) 2. [What arrived in the first week of October 2026?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#what-arrived-in-the-first-week-of-october-2026) 3. [How do you run ChatGPT or Claude Code from the canvas without an API token?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#how-do-you-run-chatgpt-or-claude-code-from-the-canvas-without-an) 4. [How do the optional API workflows work?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#how-do-the-optional-api-workflows-work) 5. [Why does an accepted cloud task not mean a finished task?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#why-does-an-accepted-cloud-task-not-mean-a-finished-task) 6. [How do cloud agents differ from local agents on the same canvas?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#how-do-cloud-agents-differ-from-local-agents-on-the-same-canvas) 7. [Can you keep more than one cloud account?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#can-you-keep-more-than-one-cloud-account) 8. [What do you need to bring?](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#what-do-you-need-to-bring) 9. [Frequently asked questions](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules#faq) The agents run on the provider's own infrastructure and on your own accounts, and CoLateral supplies no model credits. This post covers what arrived in the first week of October 2026, how each path works, what its limits are and why the design keeps credentials on your machine. ## Key takeaways - CoLateral added cloud agent cards for ChatGPT Workspace Agents and Claude Code routines, and cloud workflows for Gemini Deep Research and Jules, from 1 October 2026. - CoLateral's default cloud path opens the provider's full app, such as chatgpt.com or claude.ai/code, in a private Browser Card where you sign in yourself, so no API token is needed. - CoLateral's optional API workflows launch hosted tasks through a local relay that keeps your credentials on your computer. An accepted task is not a finished task, and the provider's own transcript remains the record. - Cloud agents opened in CoLateral cannot reach your local canvas tools. The integration does not expose the local canvas MCP server to them. ## What are cloud agent cards in CoLateral? Until October 2026, every agent CoLateral ran was a local command-line tool in a Terminal Card. Cloud agents are different: the work runs on the provider's servers, under the provider's plan, tools and approvals. CoLateral's job is to give you a place for them on the same canvas as your files and your local agents, and to keep what it relays honest about what has and has not happened. Definition - Cloud agent card: A cloud agent card is a Project Canvas card for a hosted AI agent. It either opens the provider's own app inside a private Browser Card, or it launches provider-hosted tasks through an optional API workflow, using your own account or token. For the local half of the story, see [every AI agent CoLateral runs](/blog/ai-agents-in-colateral). Local agents are covered in [running Claude Code and Codex side by side](/blog/run-claude-code-and-codex-side-by-side). ## What arrived in the first week of October 2026? 1. October 1, 2026 - Native ChatGPT and Claude cloud agent cards: Cards for ChatGPT Workspace Agents and for Claude Code routines, the two native subscription cloud agents. 2. October 1, 2026 - Gemini and Jules cloud workflows: Gemini Deep Research and Jules, added with safe action recovery so a lost response is never silently resent. 3. October 1, 2026 - Full provider apps on the canvas: The default Agent, Cloud choice became the provider's full app in a Browser Card, with the API workflows kept as an optional second path. 4. October 3, 2026 - Drafts, continuation and action recovery: Saved cards now keep draft prompts and run references, and a conversation can continue after a card is restored. 5. October 6, 2026 - Multiple app accounts: More than one account for the same provider app, each on its own card, with a switch-account control. ## How do you run ChatGPT or Claude Code from the canvas without an API token? Choose Agent, then Cloud. By default this opens the full provider app: ChatGPT opens chatgpt.com and Claude Code opens claude.ai/code, each in a private Browser Card. You sign in directly in that card and handle multi-factor prompts and site protections yourself. The provider's own conversation, tools, approvals and account limits apply. No API token or published routine is needed. The Browser Card still needs the local browser service, and if that service is unavailable the card shows a recovery message rather than implying the provider opened. Profiles belong to the Browser Card and stay separate from your personal Chrome. Restoring a saved card does not submit a task. Cloud providers do not gain access to local canvas tools just because their website is open on the canvas. The catalogue also includes Claude Chat, Gemini, Grok, Microsoft Copilot, Perplexity, DeepSeek and Jules, and an Another AI website entry that accepts an explicitly entered HTTPS address with no embedded credentials. These open the provider's full app. They are websites in a card, not extra API adapters or local CLI agents. ## How do the optional API workflows work? API workflows have their own controller cards. You connect a provider once through the card's optional setup form, then sending launches a provider-hosted task. Each provider needs its own kind of credential, and they are not interchangeable. The four optional API workflows. Eligibility, plan limits and any charges are the provider's. | Provider | What it runs | What you set up | What the card can do | | --- | --- | --- | --- | | ChatGPT Workspace Agents | A published Workspace Agent with an API trigger channel | A Workspace Agent access token and the channel identifier, which are distinct from OpenAI Platform API keys | Launch a task, refresh its status and continue a conversation that kept a conversation key | | Claude Code routines | A routine with an API trigger | A per-routine bearer token and the routine identifier | Launch a new routine session on each send and link to the hosted session | | Gemini Deep Research | Hosted research through the Interactions API | A Gemini API key with API billing enabled, which is separate from a Gemini app subscription | Run in the background, poll status, retrieve the report and cancel supported active runs | | Jules | Hosted coding sessions | A Jules API key and the repositories you connect | Select a repository and branch per session, show activity, approve a plan and send follow-ups, with no cancellation | Credentials are stored by the local bridge in an owner-only secrets directory, never in the canvas document, and a token is never returned to the interface after you enter it. The store refuses to fall back to an inherited secret if a stored configuration is damaged. Owner-only storage protects against other ordinary accounts on the machine. It is not encryption and it does not protect against the same user or an administrator. ## Why does an accepted cloud task not mean a finished task? Because the providers' interfaces differ, and CoLateral will not pretend otherwise. Claude's routine endpoint returns a hosted session link without streaming output, and its trigger token has no read access, so the transcript stays in the provider's own interface. Stopping the local relay or deleting a credential does not prove that an already-launched cloud run stopped. Cancellation is offered only where a provider documents a supported way to do it: Gemini research can be cancelled, Jules cannot through this integration. Failure handling follows the same principle. Local validation and pairing failures happen before submission, keep your draft and say the task was not sent. Once a request has reached the network, an unreadable response stays uncertain and is never automatically resent. The bridge records an operation identifier so repeating the same operation does not issue another provider action, and an unknown outcome is kept for you to review. Jules plan approval always needs your explicit action. Permissions, confirmation behaviour and usage limits depend on the selected provider, agent and action. Provider plan eligibility, administrator policy, usage limits and any enabled overage still apply. Review a cloud agent's output in the provider's own transcript before you use or share it. ## How do cloud agents differ from local agents on the same canvas? Image: CoLateral canvas with three local agent cards for Claude Code, Codex and Gemini, each above the slideshow, spreadsheet or document it produced Local agent cards, for contrast. A cloud agent card is a Browser Card or a controller card, and its work runs on the provider's servers. - A local agent is a process on your computer, started through the Local Bridge, and it can read the cards you link to it. A cloud agent runs remotely and does not see your canvas. - A local agent's prompts and the material it reads go to its model provider. A cloud agent's prompts and execution go to the provider's hosted agent. Neither is local inference. - Local agents appear in the Command Centre rail and can be managed by the orchestrator. Native cloud conversations stay in their own Browser Cards and are not copied into CoLateral's saved API results. - Switching a cloud app account does not change local terminal accounts, API workflow configuration or the usage bar. See [how the orchestrator manages local agents](/blog/orchestrator-command-centre-chief-of-staff). ## Can you keep more than one cloud account? Yes. Under Cloud, then Full apps, then Accounts and subscriptions, you can list the AI Browser Cards on the current canvas, search and reopen them, and add an account. Each new account is a separate card with its own browser profile, keyed by project and card, and each card has a Switch account control. Labels such as a plan name are descriptions you type. They are not verified identities, entitlements or usage readings, and sign-in cookies are not exported with a labelled card. ## What do you need to bring? Your own accounts and tokens. CoLateral supplies no model credits, and it does not host the inference. A provider's subscription, API charges and usage limits are separate from the CoLateral licence; see [pricing](/pricing) for the licence and the [setup answers](/faq) for installation. Get the desktop app from the [download page](/download), start with an invented project, and read the provider's current terms before you connect a paid account. FAQ ## Frequently asked questions ### Does CoLateral run ChatGPT and Claude Code in the cloud? CoLateral opens the provider's own app, chatgpt.com or claude.ai/code, in a private Browser Card, and it can also launch hosted tasks through optional API workflows. The agent itself runs on the provider's servers under your own account, not on CoLateral's. ### Do I need an API key to use cloud agents in CoLateral? Not for the default path. The full provider apps need only your own sign-in, handled by you in the card. The optional API workflows need each provider's own token or key, and those credentials are distinct from one another. ### Can a cloud agent edit my canvas or my local files? No. Opening a provider's website on the canvas gives it no access to local canvas tools, and the integration does not expose the local canvas MCP server to cloud agents. Local agents in Terminal Cards are the ones that read your linked cards. ### Can I cancel a cloud task from CoLateral? Only where the provider documents it. Gemini Deep Research supports cancelling an active run. Jules cancellation is not supported by this integration, and Claude routines are fire-only, so you review or stop those in the provider's own interface. ### Does Jules work on my repository directly? Jules runs hosted coding sessions against repositories you connect to your own Jules account. You choose the repository and starting branch per session, and plan approval always needs your explicit action in the card. Written by ## [Nic Vandewetering](/blog/authors/nic) Founder and CEO, CoLateral Nic Vandewetering is the founder of CoLateral and builds the workspace in public, often live on YouTube. These posts record what changed and why. [About CoLateral](/about) [YouTube](https://www.youtube.com/@nicvandewetering) [X](https://x.com/nvandewetering) [LinkedIn](https://www.linkedin.com/in/nic-vandewetering-55358a1a5) [Post on X](https://x.com/intent/post?text=Cloud%20agent%20cards%20for%20ChatGPT%2C%20Claude%2C%20Gemini%20and%20Jules&url=https%3A%2F%2Fcolateralai.com%2Fblog%2Fcloud-agent-cards-chatgpt-claude-gemini-jules) [LinkedIn](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fcolateralai.com%2Fblog%2Fcloud-agent-cards-chatgpt-claude-gemini-jules) [Newer post Building CoLateral in Public: Livestreams and Releases](/blog/building-colateral-in-public) [Older post CoLateral Arcade: The Games Module](/blog/colateral-arcade-games-module) ## Keep reading Models and agents ### [Every AI agent CoLateral runs, and how each got there](/blog/ai-agents-in-colateral) CoLateral runs Claude Code, OpenAI Codex, Gemini, Grok Build, Copilot and more on your own accounts. See each agent, when it arrived and what it changed. Oct 8, 2026 - 14 min read Models and agents ### [Run Claude Code and Codex side by side on one canvas](/blog/run-claude-code-and-codex-side-by-side) How CoLateral runs Claude Code and OpenAI Codex side by side as Terminal Cards on your own accounts, how Codex joined in July 2026, and why the design works. Oct 8, 2026 - 6 min read Models and agents ### [The orchestrator, Command Centre and chief of staff](/blog/orchestrator-command-centre-chief-of-staff) How CoLateral's bottom-bar AI orchestrator, Command Centre and chief of staff came together in 2026, what each does, and how they run your own agents. Oct 8, 2026 - 8 min read ## Bring your next project together. CoLateral is a desktop workspace where your files, notes, tools and AI agents share one canvas. Connect your own provider account when an agent needs one, and see how it fits your work. [Get the desktop app](/download) [See pricing](/pricing)