> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/list_workspaces.md).

# Conductor List Workspaces

Lists Conductor workspaces with optional project, state, name, repository, creator and activity filters. Requires your own Conductor API key, created at [app.conductor.build/users/api-keys](https://app.conductor.build/users/api-keys) and added through AutoGPT’s credentials UI. Select that credential for each Conductor block; no server-wide default key is used.

## Conductor List Workspaces

### What it is

List Conductor workspaces, optionally filtered by project, state, name, repository, creator or activity date. When filtering within a project, a page can be empty while has\_more is true; continue with next\_offset until has\_more is false.

### How it works

Without `project_id` the block calls `GET /v0/workspaces` and passes every filter as query parameters (`state` may repeat). With `project_id` it calls `GET /v0/projects/{id}/workspaces`, which only paginates, so the block applies the same filters itself to each returned page: exact `state` and `creator`, case-insensitive `name` and `repo` substrings, `since` against `lastActivityAt`, and archived workspaces hidden unless `include_archived` is set or `archived` is among the requested states. A filtered page can therefore be empty while `has_more` is still true; keep paging with `next_offset`, which always advances by the raw page size. `since` must be an ISO-8601 date or timestamp and is validated before any request. Each workspace is also emitted one at a time on `workspace` for fan-out.

### Inputs

| Input             | Description                                                                        | Type                                                                                                   | Required |
| ----------------- | ---------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ | -------- |
| project\_id       | Only workspaces of this project (repository). Leave empty for all projects.        | str                                                                                                    | No       |
| state             | Only workspaces in these states, e.g. ready, sleeping                              | List\["initializing" \| "ready" \| "sleeping" \| "archived" \| "deleted" \| "updating" \| "unstarted"] | No       |
| name              | Filter by workspace name                                                           | str                                                                                                    | No       |
| repo              | Filter by repository URL                                                           | str                                                                                                    | No       |
| creator           | Filter by creator user ID                                                          | str                                                                                                    | No       |
| since             | Only workspaces whose last activity is on or after this ISO-8601 date or timestamp | str                                                                                                    | No       |
| include\_archived | Include archived workspaces                                                        | bool                                                                                                   | No       |
| limit             | Maximum number of workspaces                                                       | int                                                                                                    | No       |
| offset            | Pagination offset                                                                  | int                                                                                                    | No       |

### Outputs

| Output       | Description                                                                                                            | Type                   |
| ------------ | ---------------------------------------------------------------------------------------------------------------------- | ---------------------- |
| error        | Error message if the operation failed                                                                                  | str                    |
| workspaces   | Workspaces: id, projectId, name, state, repoUrl, deepLink, creatorName, lastActivityAt                                 | List\[Dict\[str, Any]] |
| workspace    | Each workspace, one at a time                                                                                          | Dict\[str, Any]        |
| has\_more    | Whether more pages exist                                                                                               | bool                   |
| next\_offset | Offset to request the next page; with project\_id a page can be filtered down to nothing while has\_more is still true | int                    |

### Possible use case

**Find work in progress**: Filter `state` to `ready` to see which workspaces have a live sandbox before sending prompts.

**Clean-up sweep**: List sleeping workspaces older than a `since` date and feed each `workspace` into Manage Workspace to archive it.

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://agpt.co/docs/integrations/block-integrations/list_workspaces.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.