> ## Documentation Index
> Fetch the complete documentation index at: https://docs.requesty.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenWork

> Connect the OpenWork desktop agent to 600+ Requesty models, with spend limits, routing policies and EU inference

[OpenWork](https://openworklabs.com) is an open source desktop app that runs an AI agent on a folder on your computer. You point it at a workspace, describe a task, and the agent reads and writes the files in that folder. The source lives at [github.com/different-ai/openwork](https://github.com/different-ai/openwork).

OpenWork ships with a built-in **Requesty** provider. Connect it and you get:

* **600+ models** in the OpenWork model picker: Claude, GPT, Gemini, Mistral, DeepSeek and more, all with one API key.
* **Per-task visibility**: every request the agent makes shows up in [Logs](https://app.requesty.ai/logs) and [Analytics](https://app.requesty.ai/analytics) with its model, provider, tokens, cost and latency.
* **Spend limits** on the key OpenWork uses, so a long-running agent can never go past a budget.
* **Routing policies** such as [Fallback](https://docs.requesty.ai/features/fallback-policies.md), and [EU routing](https://docs.requesty.ai/features/eu-routing.md) for teams that need data to stay in the EU.

> [!NOTE]
>
> OpenWork runs its agent on [OpenCode](https://docs.requesty.ai/integrations/opencode.md), so the same `opencode.json` configuration format applies. This guide was tested with OpenWork v0.18.67.

## Prerequisites

* A Requesty account and an API key from the [API Keys page](https://app.requesty.ai/api-keys). We recommend a dedicated key for OpenWork, for example `openwork`, so its usage and limits are separate from your other tools.
* A folder you want OpenWork to work in.

## Install OpenWork

**1. Download the app**

Go to [openworklabs.com/download](https://openworklabs.com/download) and pick the build for your system: macOS (Apple Silicon or Intel), Windows (x64 or ARM64) or Linux (AppImage or tar.gz). Every build is also attached to the [GitHub releases](https://github.com/different-ai/openwork/releases).

![OpenWork download page with macOS, Windows and Linux builds](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-download.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=7429d3ffc0d0fc75716f78309d761f32)

On Linux, make the AppImage executable and start it:

```bash theme={"dark"}
chmod +x openwork-linux-x86_64-*.AppImage
./openwork-linux-x86_64-*.AppImage
```

**2. Add your folder as a workspace**

OpenWork opens on a default **OpenWork Chat** workspace. Click **Add workspace**, choose **Local workspace**, pick your folder in the **Authorize folder** dialog and click **Create Workspace**.

![OpenWork Local workspace dialog with a folder selected and the Create Workspace button](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-local-workspace.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=dda56318194cf84bb786810b5380c16e)

## Connect Requesty

**1. Open AI Providers**

Open the account menu at the bottom left, go to **Settings > AI Providers** and click **Connect a provider**. Search for **Requesty** and click **Connect**.

![OpenWork Connect a provider dialog with Requesty in the search results](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-connect-provider.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=61b43919e04ebb763a034171ce768d5b)

**2. Paste your API key**

Paste your Requesty API key and click **Save key**. Keys added here stay on this device.

![Requesty API key dialog in OpenWork with a masked key and the Save key button](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-requesty-api-key.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=3148a80ce6496569d8416b75f768e27f)

**3. Check the connection**

Requesty now appears under **On this device** in AI Providers, with a **Disconnect** button. Click **Back to app** to return to your workspace.

![OpenWork AI Providers page listing Requesty as connected on this device](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-requesty-connected.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=aa50923ad3f0248ab1033c8067e24796)

**4. Pick a model**

Start a **New session**, click the model name under the task box and search the list. Requesty models are grouped under **Requesty**. Pick one, for example **Claude Sonnet 5.5**.

![OpenWork model picker filtered to sonnet 5.5, listing Claude Sonnet 5.5 and other models from Requesty](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-model-picker.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=ff9809e089e3ead4d0ef55fead0ac7cf)

These models are Requesty [Managed Policies](https://docs.requesty.ai/features/managed-policies.md) such as `claude-sonnet-5-5` and `gemini-3.8-flash`, so Requesty chooses the provider for you. You can switch models per session.

## Run your first task

Describe a task that uses the files in your workspace, then click **Run task**. For example, in a folder of invoice PDFs:

```txt theme={"dark"}
Read every invoice in the invoices folder and create invoice-summary.md with a table of supplier, invoice number, date and total in EUR. Add the grand total and flag any duplicates.
```

The agent reads the files, writes the result back into the folder, and links the new file under its reply. Click the file to open it in the preview panel.

![OpenWork reply with an invoice table, a grand total and a flagged duplicate invoice](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-invoice-result.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=2beaba244b654072b45d9cc7f62d3b9d)

## See every request in Requesty

A single OpenWork task is usually several model requests, as the agent reads files, calls tools and writes output. All of them appear in Requesty.

**1. Filter Logs to your OpenWork key**

Open [Logs](https://app.requesty.ai/logs) and click your OpenWork key in the **API key** column, or use **Add filter > API key**. Each row shows the provider, model, routing type and policy. Use **Columns** to add tokens, cost and latency.

![Requesty Logs filtered to the OpenWork API key, showing Claude Sonnet 5.5, Gemini 3.8 Flash and GPT-6 Luna requests](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-logs-openwork.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=e8d82b68377d0d383c11c7a1fc6b85e1)

**2. Open a request**

Click a row to see first-token latency, input, cached and output tokens, the routing decision and the provider that served it.

![Requesty request detail for claude-sonnet-5-5 served by Bedrock, with latency, token and routing breakdown](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-log-detail.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=0f8e969437191c2c729efdbaa5f511f2)

Agent turns resend much of the same workspace and tool context, so a large share of input is often served from [cache](https://docs.requesty.ai/features/auto-caching.md), as in this request.

**3. Compare models in Analytics**

In [Analytics](https://app.requesty.ai/analytics), filter by your OpenWork key and set **Group** to **Model** to see requests, tokens and cost per model.

![Requesty Analytics model usage table for the OpenWork key with requests, tokens and cost per model](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-analytics-by-model.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=60b53a12cec7b3db3bf8899bf12d52bc)

## Set a spend limit

An agent that works through a large folder can make many requests. Put a monthly limit on the key OpenWork uses so it can never go past your budget.

**1. Open the key's limit**

On the [API Keys page](https://app.requesty.ai/api-keys), click the value in the **Usage** column of your OpenWork key (it reads **No limit** by default) to open **Update API Key Limit**.

**2. Enter the limit**

Enter the **Monthly Limit (USD)** and click **Update Limit**. The smallest limit is \$1.00.

![Update API Key Limit dialog with a monthly limit of \$20](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-key-limit.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=ebb8ba5fb86612fb94de0ee659a1337b)

The Usage column then shows spend against the limit for each key:

![API Keys list showing one key at \$1.08 of a \$1.00 limit and another at \$0.64 of a \$20.00 limit](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-key-usage.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=65e42da230d6cb5e26b1e754f3342f01)

When a key reaches its limit, Requesty blocks new requests and OpenWork shows the error inline as the agent's reply:

```txt theme={"dark"}
This API key, user or group has reached its monthly spend limit. An admin can raise the limit in the Requesty dashboard
```

![OpenWork session where the reply is the Requesty monthly spend limit message](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-spend-limit-error.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=af6aced27611c344f61a50eab2272096)

> [!NOTE]
>
> Requests that are already running when the limit is reached still finish, so usage can end slightly above the limit, as in the $1.08 / $1.00 example above. To continue, raise the limit on the API Keys page.

## Recommended: a routing policy in the EU

A [routing policy](https://docs.requesty.ai/features/fallback-policies.md) gives OpenWork one stable model name while you decide on the Requesty side which models sit behind it. Combined with the [EU endpoint](https://docs.requesty.ai/features/eu-routing.md), you can keep every request in the EU and still fail over to a second model.

**1. Create the policy**

Open [Routing Policies](https://app.requesty.ai/routing-policies), go to the **Custom** tab and click **Create policy**. Give it a name, for example `openwork-reliable`, choose the **Fallback** strategy and use **Add model** to add models in the order they should be tried. To stay in the EU, add EU-pinned models such as `bedrock/claude-sonnet-5-5@eu-west-1` first and `azure/gpt-6.1-sol@swedencentral` as the fallback.

![Requesty routing policy openwork-reliable with the Fallback strategy, Claude Sonnet 5.5 in eu-west-1 first and GPT-6.1 Sol in Sweden Central second](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-routing-policy.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=d87d8af8409cc3ceaf1ee36d876c1326)

After you click **Create policy**, its model ID is shown under the name: `policy/openwork-reliable`.

**2. Store the API key in a file**

Save the Requesty key you want this provider to use in a file that only you can read:

```bash theme={"dark"}
mkdir -p ~/.config
printf '%s' 'YOUR_REQUESTY_API_KEY' > ~/.config/requesty-eu.key
chmod 600 ~/.config/requesty-eu.key
```

> [!WARNING]
>
> In OpenWork v0.18.67, variables saved under **Settings > Environment** were not passed to the agent, so `{env:...}` references to them failed. Use a `{file:...}` reference as shown here.

**3. Add the provider to your workspace**

Create `opencode.jsonc` (or `opencode.json`) in the root of your workspace folder:

```jsonc theme={"dark"}
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "requesty-eu": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Requesty EU",
      "options": {
        "baseURL": "https://router.eu.requesty.ai/v1",
        "apiKey": "{file:~/.config/requesty-eu.key}"
      },
      "models": {
        "policy/openwork-reliable": { "name": "Reliable (Claude, GPT fallback)" }
      }
    }
  }
}
```

![opencode.jsonc in a text editor with the Requesty EU base URL, a file-based API key and the policy model](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-eu-config.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=8af84657c49819466d83364c65ee46d5)

Every policy has to be listed under `models`. OpenWork only offers the models it knows about, so a policy that is not declared here does not appear in the picker.

**4. Pick the policy and run a task**

OpenWork picks the file up without a restart. Start a new session, search the model picker for the name you gave the policy, and select it under **Requesty EU**.

![OpenWork model picker showing Reliable (Claude, GPT fallback) under Requesty EU](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-policy-picker.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=090f94cd0b61845178d1af2a8a619ed8)

Run a task as usual:

![OpenWork answer produced by the Reliable (Claude, GPT fallback) policy](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/openwork-policy-answer.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=b10875d0859ba6963e06b4a57faf47c8)

**5. Confirm the region in Logs**

In [Logs](https://app.requesty.ai/logs), open one of the requests. The detail shows **Policy: fallback**, the policy name, the model that served the request and its region, here `claude-sonnet-5-5@eu-west-1` on Bedrock.

![Requesty request detail showing Policy: fallback, openwork-reliable, claude-sonnet-5-5@eu-west-1 and Bedrock](https://mintcdn.com/requesty/XM2AP-xxwjVKYrMQ/images/openwork/requesty-eu-log-detail.png?fit=max\&auto=format\&n=XM2AP-xxwjVKYrMQ\&q=85\&s=75ecf1c888327a76368af3132cf3079a)

To change models later, edit the policy in Requesty. OpenWork keeps using `policy/openwork-reliable` and the next request follows the new configuration.

If you only need EU routing without a policy, list EU models such as `claude-sonnet-5-5@eu` under `models` instead. To use a policy on the global endpoint, set `baseURL` to `https://router.requesty.ai/v1`.

## Troubleshooting

> [accordion] Requests fail with an invalid API key
>
> Open **Settings > AI Providers**, disconnect Requesty and connect it again with a valid key. For a custom provider in `opencode.jsonc`, check that the key file exists and contains only the key.

> [accordion] My policy or model is not in the picker
>
> Declare it under `models` in `opencode.jsonc` in the workspace root, using the exact ID from [Routing Policies](https://app.requesty.ai/routing-policies) or the [models list](https://docs.requesty.ai/api-reference/endpoint/models-list.md). Also check that the model is enabled in your organization's [Approved Models](https://docs.requesty.ai/features/approved-models.md).

> [accordion] Requesty says the model does not exist
>
> The model or policy ID is not known to Requesty. Check the spelling and the `policy/` prefix against [Routing Policies](https://app.requesty.ai/routing-policies) or the [models list](https://docs.requesty.ai/api-reference/endpoint/models-list.md).

> [accordion] Monthly spend limit reached
>
> The key OpenWork uses is over its limit. Raise or remove the limit on the [API Keys page](https://app.requesty.ai/api-keys). See [Set a spend limit](#set-a-spend-limit).

## References

* [OpenWork download](https://openworklabs.com/download)
* [OpenWork on GitHub](https://github.com/different-ai/openwork)
* [OpenCode integration](https://docs.requesty.ai/integrations/opencode.md)
* [Fallback Policies](https://docs.requesty.ai/features/fallback-policies.md)
* [EU Routing](https://docs.requesty.ai/features/eu-routing.md)
* [Requesty API Keys](https://app.requesty.ai/api-keys)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.