# AI use cases for Claude Unlimited (DevDock-AI/claude-unlimited)

Repo: [DevDock-AI/claude-unlimited](https://github.com/DevDock-AI/claude-unlimited) | Use cases: 4 | Page: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/

Claude Unlimited is a local daemon that pools Claude, ChatGPT/Codex and Anthropic API accounts so a Claude Code session moves to the next account when one hits its usage limit.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Keep a Claude Code session going past a usage limit: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/keep-claude-code-session-running-past-limit/
- Spread a Claude Code session's subagents across accounts: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/spread-subagents-across-accounts/
- Track AI spend by model and project in one dashboard: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/track-ai-spend-by-model-and-project/
- Send your own app's Anthropic API calls through the pool: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/call-pooled-accounts-from-own-app/

## How to keep a Claude Code session going past a usage limit with Claude Unlimited

Repo: [DevDock-AI/claude-unlimited](https://github.com/DevDock-AI/claude-unlimited) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Pool two or more accounts so a long coding session switches accounts instead of stopping.

**Who it is for:** A developer in the middle of a long Claude Code task who keeps hitting the usage limit on one subscription.

**The problem:** When one account runs out, the session stops and the manual workaround means logging out, logging into another account and pasting a handover note.

**The outcome:** The session continues on the next account between requests, with the same context and terminal.

### Steps

1. Install with the one-line command for your system from the README Install section, then open http://127.0.0.1:4317/ to confirm the dashboard runs.
2. Run `claude-unlimited add-account` to log in your first Claude Pro or Max account in the browser.
3. Add a second account, such as a ChatGPT/Codex subscription or an API key, from the dashboard at http://127.0.0.1:4317/.
4. Run `claude-unlimited code` in your project and keep working as normal.
5. Check the dashboard activity log to see when a switch happened.

### Prompt to paste into your agent

```text
Using the DevDock-AI/claude-unlimited repo, install the daemon and add a second account, then start a Claude Code session with `claude-unlimited code` in <project-path>. Expected output: the dashboard at http://127.0.0.1:4317/ lists at least two accounts. Verify that the dashboard shows both accounts and that the session starts without an error.
```

### Caveat

The README says Windows and Linux are best-effort and macOS is the most tested platform.

Risk, account pooling: Pooling several subscriptions into one supply may conflict with the terms of the providers you use, so check those terms before you set it up.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/keep-claude-code-session-running-past-limit/

## How to spread a Claude Code session's subagents across accounts with Claude Unlimited

Repo: [DevDock-AI/claude-unlimited](https://github.com/DevDock-AI/claude-unlimited) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README

Run the main agent and each subagent on different pooled accounts to share the load.

**Who it is for:** A developer running parallel subagents in Claude Code who wants to avoid exhausting a single account.

**The problem:** A single account gets used by every subagent, so one heavy task can drain its usage quickly.

**The outcome:** Each agent stays on its own account, so the load is shared and each prompt cache stays warm.

### Steps

1. Complete the install and add at least two accounts as described in the README.
2. Open the dashboard at http://127.0.0.1:4317/ and confirm each account has a priority and threshold set.
3. Run `cu code --distribute` in your project directory.
4. Start a task that uses subagents and watch which account each one uses in the dashboard.

### Prompt to paste into your agent

```text
Using the DevDock-AI/claude-unlimited repo, start a session with `cu code --distribute` in <project-path> after at least two accounts are in the pool. Expected output: subagents are spread across accounts as shown on the dashboard. Verify that the dashboard lists more than one account in use during the run.
```

### Caveat

The README describes this as balancing across accounts but does not describe how the split is decided, so check the dashboard to confirm the behavior.

Risk, account pooling: Spreading agents across several subscriptions may conflict with the provider terms, so confirm those terms first.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/spread-subagents-across-accounts/

## How to track AI spend by model and project in one dashboard with Claude Unlimited

Repo: [DevDock-AI/claude-unlimited](https://github.com/DevDock-AI/claude-unlimited) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

See cost and token use over time, split by model, project and account, on your own machine.

**Who it is for:** A developer or team lead who needs to know which projects and models are driving AI usage costs.

**The problem:** Usage data is spread across several accounts and providers, so it is hard to see where the spend goes.

**The outcome:** A local dashboard shows spend and tokens over time, broken down by model, project and account.

### Steps

1. Install the daemon and add your accounts as described in the README.
2. Open the dashboard at http://127.0.0.1:4317/.
3. Work in one or more projects with `claude-unlimited code` so requests are recorded.
4. Open the Statistics view to compare spend and tokens by model, project and account.

### Prompt to paste into your agent

```text
Using the DevDock-AI/claude-unlimited repo, run a short session with `claude-unlimited code` in <project-path>, then open http://127.0.0.1:4317/ and open the Statistics view. Expected output: charts of spend and tokens split by model, project and account. Verify that the project you used appears in the per-project breakdown.
```

### Caveat

The README says the cost figures are estimates, so treat them as a guide rather than a bill.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/track-ai-spend-by-model-and-project/

## How to send your own app's Anthropic API calls through the pool with Claude Unlimited

Repo: [DevDock-AI/claude-unlimited](https://github.com/DevDock-AI/claude-unlimited) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Point any Messages API client at the local daemon so its requests use the pooled accounts.

**Who it is for:** A developer building an app or script that calls the Anthropic Messages API and wants requests to survive a usage limit.

**The problem:** A custom app that calls one account directly fails when that account hits its limit.

**The outcome:** The app sends requests to 127.0.0.1 and the daemon picks the account for each request.

### Steps

1. Install the daemon and add your accounts as described in the README.
2. Set the environment variable `ANTHROPIC_BASE_URL=http://127.0.0.1:4317` in the shell that runs your app.
3. Run your app as usual so its Messages API calls go through the daemon.
4. Check the dashboard at http://127.0.0.1:4317/ to confirm the requests are counted.

### Prompt to paste into your agent

```text
Using the DevDock-AI/claude-unlimited repo, set ANTHROPIC_BASE_URL=http://127.0.0.1:4317 and run <app-command> against the Messages API. Expected output: the app gets normal responses. Verify that the request appears in the dashboard activity log at http://127.0.0.1:4317/.
```

### Caveat

The README describes this route for Anthropic-API clients but does not list every client that has been tested, so check your app's behavior first.

Risk, credentials: Your app authenticates to the local daemon with a placeholder token, so keep the daemon's dashboard and config files private to your machine.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/devdock-ai-claude-unlimited/call-pooled-accounts-from-own-app/