DEDUPED Hot AI repos, turned into use cases Get 5 a day

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

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

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

Who it is forA developer running parallel subagents in Claude Code who wants to avoid exhausting a single account.

The problemA single account gets used by every subagent, so one heavy task can drain its usage quickly.

The outcomeEach agent stays on its own account, so the load is shared and each prompt cache stays warm.

What you need first

  • Python 3.10+, git, and the claude CLI on your PATH
  • At least two accounts to pool: Claude Pro or Max, ChatGPT/Codex, or Anthropic API keys
  • A browser to complete the account login
  • macOS is the most tested platform; Windows and Linux are best-effort per the README

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 for your agent

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.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page