# Every AI agent CoLateral runs, and how each got there | CoLateral

Source: https://colateralai.com/blog/ai-agents-in-colateral

[Home](/)

[Blog](/blog)

[Models and agents](/blog/category/models)

# Every AI agent CoLateral runs, and how each got there

CoLateral runs nine local coding agents (Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, Grok Build, Kiro, Cursor, OpenCode and DeepSeek through Claude Code) plus hosted cloud agents, all on your own provider accounts and all on one Project Canvas.

[Nic Vandewetering](/blog/authors/nic) - October 8, 2026 - 14 min read

Covers July 2026 to October 2026

Image: The CoLateral Project Canvas with three agent cards, one running Codex, one Claude Code and one Gemini, each above the card it produced, and the bottom command bar below

### On this page

1. [Which AI agents does CoLateral run today?](/blog/ai-agents-in-colateral#which-ai-agents-does-colateral-run-today)
2. [What is an agent card, a Terminal Card and an orchestrator?](/blog/ai-agents-in-colateral#what-is-an-agent-card-a-terminal-card-and-an-orchestrator)
3. [How did each agent arrive in CoLateral?](/blog/ai-agents-in-colateral#how-did-each-agent-arrive-in-colateral)
4. [How do local CLI agents, cloud agents and browser agents differ?](/blog/ai-agents-in-colateral#how-do-local-cli-agents-cloud-agents-and-browser-agents-differ)
5. [How do you run Claude Code and Codex side by side on one canvas?](/blog/ai-agents-in-colateral#how-do-you-run-claude-code-and-codex-side-by-side-on-one-canvas)
6. [What did the orchestrator and Command Centre change?](/blog/ai-agents-in-colateral#what-did-the-orchestrator-and-command-centre-change)
7. [How do model releases change the CoLateral interface?](/blog/ai-agents-in-colateral#how-do-model-releases-change-the-colateral-interface)
8. [Can you use more than one account for the same agent?](/blog/ai-agents-in-colateral#can-you-use-more-than-one-account-for-the-same-agent)
9. [How do you see how much of your subscription is spent?](/blog/ai-agents-in-colateral#how-do-you-see-how-much-of-your-subscription-is-spent)
10. [How many agents can run at once?](/blog/ai-agents-in-colateral#how-many-agents-can-run-at-once)
11. [Can you watch this being built?](/blog/ai-agents-in-colateral#can-you-watch-this-being-built)
12. [Do you need your own AI account to use CoLateral?](/blog/ai-agents-in-colateral#do-you-need-your-own-ai-account-to-use-colateral)
13. [What should you check before trusting an agent in CoLateral?](/blog/ai-agents-in-colateral#what-should-you-check-before-trusting-an-agent-in-colateral)
14. [Frequently asked questions](/blog/ai-agents-in-colateral#faq)

The first agents arrived in July 2026 and the rest followed in a run of releases through October 2026. Every one of them changed something visible: the agent card, the Terminal Card, the bottom-bar orchestrator, the Command Centre, the model pickers, the usage bar and the agent limit. This is the formal record of which agents CoLateral supports, when each one arrived, and what its arrival did to the interface.

## Key takeaways

- CoLateral runs nine local coding agents on the Project Canvas: Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, Grok Build, Kiro, Cursor, OpenCode and DeepSeek, which runs through Claude Code.
- CoLateral supplies no model credits. Every agent runs on a provider account you already hold, and provider subscriptions and API charges are separate from the CoLateral licence.
- The first live agents, Claude Code and Codex, arrived as Terminal Cards in July 2026. Seven more local agents followed in August 2026, and cloud agent cards for ChatGPT, Claude Code, Gemini and Jules arrived in October 2026.
- The CoLateral bottom bar became an orchestrator on 30 July 2026. It runs typed requests on whichever signed-in CLI you choose, and it manages the agents in your Terminal Cards.
- Each agent release changed CoLateral's own interface: a shared provider table behind every picker, a model chip on each agent card, a subscription usage bar, per-provider accounts and an agent limit with sleeping cards.

## Which AI agents does CoLateral run today?

CoLateral is a desktop workspace where files, notes, tools, terminals and coding agents share one visual canvas. It does not ship a model of its own. It runs the agents you already use, and it checks each one against an explicit allowlist in its local bridge before it will start a process. The website's list of supported providers is checked against that same allowlist, so the table below is the supported set as of 8 October 2026.

Supported agents in CoLateral on 8 October 2026. CoLateral supplies no model credits; the last column is the month the agent first appeared in the repository history.

| Agent | Provider | How it runs in CoLateral | What you bring | First arrived |
| --- | --- | --- | --- | --- |
| Claude Code | Anthropic | Local CLI in a Terminal Card | Your own Claude account, signed in to Claude Code | July 2026 |
| OpenAI Codex (Codex CLI) | OpenAI | Local CLI in a Terminal Card | Your own ChatGPT account, signed in to Codex | July 2026 |
| GitHub Copilot CLI | GitHub | Local CLI in a Terminal Card | A GitHub Copilot seat you already have | August 2026 |
| Gemini CLI and Antigravity CLI | Google | Local CLI in a Terminal Card | A Google account (Antigravity CLI), or an AI Studio key or Vertex AI (Gemini CLI) | August 2026 |
| Grok Build | xAI | Local CLI in a Terminal Card | A SuperGrok or X Premium subscription | August 2026 |
| Kiro CLI | AWS | Local CLI in a Terminal Card | A Kiro account (AWS Builder ID, Google or GitHub) | August 2026 |
| Cursor CLI | Cursor | Local CLI in a Terminal Card | Your own Cursor subscription | August 2026 |
| OpenCode | Open source | Local CLI in a Terminal Card | Whichever account you sign OpenCode in to | August 2026 |
| DeepSeek | DeepSeek | Claude Code pointed at DeepSeek's Anthropic-compatible endpoint | Your own DeepSeek API key | August 2026 |
| ChatGPT and Claude Code (full apps) | OpenAI, Anthropic | Cloud: the provider's own site in a private Browser Card | Your own account, signed in by you in the card | October 2026 |
| ChatGPT Workspace Agents and Claude Code routines | OpenAI, Anthropic | Cloud: optional API workflows on a controller card | Your own account and the provider's trigger token | October 2026 |
| Gemini Deep Research and Jules | Google | Cloud: hosted research and coding sessions through provider APIs | Your own Google API keys, which are separate from each other | October 2026 |

Provider names and sign-in rules belong to the providers and change. Check each provider's current terms, plan limits and any API charges before you rely on a connection. Permissions and confirmation behaviour depend on the selected agent and action, so read the controls on the card you open.

## What is an agent card, a Terminal Card and an orchestrator?

Four terms carry most of this story. The repository defines them as follows, and the rest of this post uses them in these senses.

Definition - Terminal Card: A Terminal Card is a Project Canvas card that runs one signed-in coding CLI on your own computer through CoLateral's loopback-only Local Bridge, in a real pseudo-terminal, using your own provider account. It can show the raw terminal or a chat thread.

Definition - Agent card: An agent card is a Terminal Card shown in its chat form: a thread of what you asked and what the agent did, a message box, and chips for the folder, the model and what the agent may do without asking. Switching to terminal mode shows the CLI's own screen instead.

Definition - Orchestrator: The orchestrator is the command bar at the bottom of the Project Canvas. Typed requests run your own signed-in CLI headlessly through the Local Bridge, and from there it can see the canvas, run canvas actions, and start and manage the agents in Terminal Cards.

Definition - Command Centre: The Command Centre is a canvas card shaped like a console: a rail listing the chief of staff, every agent on the board and the sections you can read, one pane showing whichever you pick, and one text box to talk to it.

One earlier use of the phrase is worth noting. On 2 July 2026 CoLateral added a different "Agent Card", a workflow card that generated prompts and turned pasted answers into reviewable cards. Once "agent" came to mean a live terminal, that card kind was retired on 3 August 2026, and each saved one was converted into a note in place so no connection or layout was lost. Today's agent card is the live one.

## How did each agent arrive in CoLateral?

The dates below come from the repository's commit history. Where a date is a month, the month is the earliest evidence we hold. The same story, told from the product side, runs through [the history of CoLateral](/blog/history-of-colateral) and [the 2026 release notes](/blog/colateral-release-notes-2026).

1. July 2, 2026 - Live Terminal Cards for Claude Code and Codex: The first commit to put a real CLI session on the canvas. The Local Bridge was loopback-only and token-paired, with a strict command allowlist and no "run anything" path, and the first task was typed in but not submitted, so you read it and pressed Enter.
2. July 28, 2026 - Terminal Cards become first-class: A Terminal button on the canvas dock, a real Windows pty, and a Look panel with themes and layouts.
3. July 29, 2026 - ChatGPT through Codex: A Terminal Card could now run your ChatGPT sign-in through the Codex CLI, with a CLI picker in the card.
4. July 30, 2026 - The bottom bar becomes the orchestrator: The command bar became the application's intelligence layer. It first ran on a realtime speech model on your own API key, and the same day moved typed requests onto your own Claude Code or Codex subscription.
5. August 11, 2026 - The Command Centre reaches the canvas: The Command Centre card arrived, and desktop release 1.0.8 was cut so it shipped to the desktop. It was later rebuilt as a console and given a chief of staff.
6. August 18, 2026 - Copilot, Gemini and Grok Build: Three agents joined on one shared provider table, so every picker, palette entry and card title follows a single list. The same day the agent card was redrawn as a chat instead of a console.
7. August 19, 2026 - Kiro, Cursor and OpenCode: Three more agents through the same table, each checked against the real CLI.
8. August 23, 2026 - DeepSeek and the chief of staff: DeepSeek arrived as a ninth agent card provider, running through Claude Code. The Command Centre gained a chief of staff that writes a short brief from what each agent last did.
9. August 28, 2026 - Antigravity CLI for Google sign-in: Gemini CLI's personal Google sign-in stopped working, so CoLateral launches Antigravity CLI for Google-account sign-in and keeps Gemini CLI for an AI Studio key or Vertex AI. Desktop 1.0.31 carried it.
10. September 1, 2026 - The agent limit: A resource guard limits how many agents run at once and sleeps the rest, so opening a project with many agents does not start them all.
11. September 9, 2026 - The subscription usage bar: A slim strip in the canvas corner shows how much of each supported subscription window has been used and when it resets, where the provider records it.
12. September 12, 2026 - Canvas Browser and browser agents: An interactive Canvas Browser with scoped local agent control, followed on 14 September by the Browser Card's Chrome-style interface and agent-spawned browsers.
13. September 22, 2026 - Model pickers read the installed CLIs: Pickers began reading model names from the installed Claude Code, Codex and Gemini CLIs, so a new model can appear without a CoLateral release. Sonnet 5.5 appeared through the same route on 29 September.
14. October 1, 2026 - Cloud agent cards: Native ChatGPT and Claude cloud agent cards, Gemini and Jules cloud workflows, and full provider apps on the canvas with optional API workflows.
15. October 6, 2026 - Isolated local accounts: Isolated local AI accounts and per-terminal account selection, moved on 7 October into one Settings card per provider.

## How do local CLI agents, cloud agents and browser agents differ?

CoLateral uses three execution paths, and the page you read for one does not apply to the others.

- Local CLI agents run as a process on your own computer, started through the Local Bridge. Your prompts and any material the agent reads go to its model provider, so a local agent is not local inference. This path covers the nine agents in the first part of the table.
- Cloud agents run on the provider's infrastructure. The bridge is a local relay that keeps credentials on your machine while prompts and execution go to the hosted agent. A full provider app opens in a private Browser Card where you sign in yourself; the API workflows are separate controller cards.
- Browser agents are local agents that drive a Browser Card. A canvas arrow means the card exists and is the target, but it does not grant control. You grant a live agent control by connecting it in the card, and you can pause or take control back.

Accepting a task is not completing it. A queued request, a hosted session link or a delivery receipt is not the finished work. The longer account of the hosted path is [cloud agent cards for ChatGPT, Claude, Gemini and Jules](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules).

## How do you run Claude Code and Codex side by side on one canvas?

Open two Terminal Cards, set one to Claude and the other to ChatGPT through Codex, and give each its own task. They are separate sessions with separate folders and separate accounts, and you can draw an arrow from either one to the note, sheet or tool it should read. The Terminal Card gained its CLI picker on 29 July 2026, and the whole design is told in [running Claude Code and Codex side by side](/blog/run-claude-code-and-codex-side-by-side).

Image: A CoLateral agent card for Claude Code with a Launch button, starter prompts, a message box and folder, model and permission chips

An agent card in chat form. The chips under the message box set the folder, the model and what the agent may do without asking.

## What did the orchestrator and Command Centre change?

> It is a Terminal Card without the terminal.

Source: CoLateral docs/orchestrator.md, describing the bottom-bar orchestrator

Before 30 July 2026 you used agents by opening cards. After it, you could ask the bottom bar to open one, brief it and report back, and later releases let it answer an agent's question, stop it without ending its session, and close it. The orchestrator runs on the CLI you choose in Settings, including Claude Code, Codex, Copilot, Gemini, Grok Build, Cursor and OpenCode. The Command Centre then gave the same orchestrator a full-size place to stand, with a chief of staff pinned first on its rail. The chief of staff is not a second agent; the bar and the card are two doors onto one conversation. The full account is in [the orchestrator, the Command Centre and the chief of staff](/blog/orchestrator-command-centre-chief-of-staff).

Voice is a separate choice. Dictate types what you say into the box and sends nothing, and voice mode holds a spoken conversation with the orchestrator, either through a signed-in ChatGPT subscription via Codex or on a realtime model (GPT Realtime 2.1, GPT Realtime 2.1 Mini or Grok Realtime Voice). The realtime route needs an OpenAI key, or a SuperGrok or X Premium sign-in for Grok. The interface says Grok Build whenever it means the coding agent.

## How do model releases change the CoLateral interface?

Each agent card carries a model chip beside the folder and permission chips. It arrived on 22 August 2026, because which model a card ran had been pinned in a settings panel where nobody watching the card could see it. The Claude Code picker later grew to carry the exact names Claude Code's own model menu prints, and today it lists Opus 5.5, Sonnet 5.5, Haiku 4.5 and Fable 5.1 as written-down names, refreshed from the installed CLI when it can read them.

An alias keeps working when the model behind it is replaced, so a card stores the alias and the visible name is read from the installed CLI. For most other agents the list is decided per account or plan, so CoLateral asks the CLI rather than writing models down. [How new model releases change the model picker](/blog/how-model-releases-change-colateral-model-picker) tells that story in order.

## Can you use more than one account for the same agent?

Yes, for the providers that support it. On 6 October 2026 CoLateral added isolated local AI accounts, and a day later moved the control into Settings, where each provider has one account card. Claude Code, Codex, Copilot, Gemini, Grok Build, Cursor, OpenCode and DeepSeek support separate profiles. Kiro keeps your computer default because its credential storage has not been verified for separate profiles.

A new profile starts empty and the next agent you start for that provider opens the provider CLI's own sign-in. The bridge removes inherited authentication from named-profile launches, so one account does not quietly borrow another's sign-in. Account names are labels you type, not evidence of an identity or a plan, and selecting another account changes the next launch only.

## How do you see how much of your subscription is spent?

The subscription usage bar, a slim strip in the bottom-left corner of the canvas, arrived on 9 September 2026. Before it, the first sign that a five-hour window was gone was a CLI refusing halfway through a task, on a surface where a refusal can look like a CoLateral fault. The bar reads figures from the sources the providers expose: Claude Code's own usage endpoint, the rate limits Codex records on disk, and credit usage Grok Build logs locally. It never estimates a percentage.

Where a provider records nothing, the bar says so and names the kind of account. It reports the computer-default account only, not named profiles.

## How many agents can run at once?

The Resources setting under Account and Settings limits how many agents run at once, from one to twelve, with a default of twelve. A card claims a seat before it launches. An agent that starts automatically past the limit opens asleep with a Wake button, and one you ask for at the limit opens a chooser so you decide which session sleeps. Starting, working, waiting and reconnecting agents are protected, and every agent in the current project stays awake. The guard began on 1 September 2026 with a default of four and later moved to twelve. Sleeping cards do not use a seat.

Optional Docker isolation for Terminal Card agents arrived on 26 September 2026. It is off by default and needs Docker.

## Can you watch this being built?

The product history is also a video history. Nic streams the work on YouTube, and the Day 51 stream is titled "BEST MODEL IN THE WORLD". The repository records that title and shows the video first listed on the website on 8 September 2026. It does not record which model the title refers to, so we do not claim one here. More about the streams is in [building CoLateral in public](/blog/building-colateral-in-public).

[Watch on YouTube BEST MODEL IN THE WORLD, Day 51 of the CoLateral build-in-public livestreams](https://www.youtube.com/watch?v=urRM5khGs2E)

A founder livestream from the CoLateral build-in-public series, the Day 51 stream titled BEST MODEL IN THE WORLD.

## Do you need your own AI account to use CoLateral?

Yes, to run an agent. CoLateral supplies no model credits and does not resell model access. Supported agents use your own provider accounts, and provider subscriptions, usage limits and any API charges are separate from the CoLateral licence and from optional modules. The licence is a one-time purchase, and [current pricing](/pricing) lives on its own page because prices change. The [setup answers](/faq) cover installation and sign-in.

You can use the Project Canvas, notes, files and tools without any AI account. An agent only needs the account for the path you choose: a local CLI needs that CLI installed and signed in, a cloud agent needs its provider account or API key, and DeepSeek needs a key. If you want the full picture of how to bring one in, [download the desktop app](/download) and start with a small invented project.

## What should you check before trusting an agent in CoLateral?

Treat agent output as a draft. Permissions and confirmation behaviour depend on the selected agent and action. Some actions in CoLateral stop and show you the exact action first, and others do not, so read the permission chip before you start and review the result afterward. A fluent summary is not evidence that a file was changed correctly. Compare important output with its source. The [guide to AI agents and your files](/resources/ai-agents-on-engineering-files) explains what to check, and the [launch post](/blog/introducing-the-colateral-blog) introduces this blog.

Two more posts complete the picture: [what CoLateral looked like through time](/blog/colateral-visual-history), and [the expansion packs](/blog/colateral-expansion-packs-explained).

FAQ

## Frequently asked questions

### Which AI coding agents does CoLateral support?

CoLateral runs Claude Code, OpenAI Codex, GitHub Copilot CLI, Google Gemini (through Gemini CLI or Antigravity CLI), Grok Build, Kiro CLI, Cursor CLI and OpenCode as local agents, plus DeepSeek through Claude Code. It also opens ChatGPT and Claude Code as full cloud apps and supports Gemini Deep Research and Jules workflows. Each one needs your own provider account.

### Does CoLateral include AI model credits?

No. CoLateral supplies no model credits. Agents run on accounts you already hold, and provider subscriptions, usage limits and API charges are separate from the CoLateral licence. Read the provider's own terms before connecting an account.

### Can Claude Code and Codex run on the same canvas?

Yes. Each is a separate Terminal Card with its own session, folder and account, so you can give them different tasks and link either one to the cards it should read. The Terminal Card picker has offered both Claude and ChatGPT through Codex since 29 July 2026.

### When did CoLateral add each agent?

Claude Code and Codex arrived in July 2026, and Copilot, Gemini, Grok Build, Kiro, Cursor, OpenCode and DeepSeek in August 2026. Cloud agent cards followed on 1 October 2026. The bottom-bar orchestrator dates from 30 July 2026 and the Command Centre from 11 August 2026.

### Does running an agent locally mean my data stays on my computer?

Not necessarily. A local agent runs as a process on your computer, but it can send your prompts and the material it reads to its model provider. Review the connected account's terms and the files you allow an agent to access before using sensitive material.

### Can I use two Claude or ChatGPT accounts in CoLateral?

Yes for supported providers. Settings holds a separate profile list for each, and a new profile starts empty and opens the provider's own sign-in. Cloud app cards can also hold their own account each. Labels are descriptions you type, not verified identities or plans.

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=Every%20AI%20agent%20CoLateral%20runs%2C%20and%20how%20each%20got%20there&url=https%3A%2F%2Fcolateralai.com%2Fblog%2Fai-agents-in-colateral)

[LinkedIn](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fcolateralai.com%2Fblog%2Fai-agents-in-colateral)

[Older post Building CoLateral in Public: Livestreams and Releases](/blog/building-colateral-in-public)

## Keep reading

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

Models and agents

### [Cloud agent cards for ChatGPT, Claude, Gemini and Jules](/blog/cloud-agent-cards-chatgpt-claude-gemini-jules)

In October 2026 CoLateral added cloud agent cards for ChatGPT, Claude Code, Gemini Deep Research and Jules. See how they work, their limits and what you bring.

Oct 8, 2026 - 7 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)