What you can do with Underclass

4 use cases

• Point opencode at a pool of coding subscriptions

  Run one local endpoint that spreads opencode requests across several Codex or Copilot accounts.

  • Underclass
  • Software and DevOps
  • Intermediate
  View prompt

  In the underclass repo at <repo path>, start the server with the proxy key and UI token set as environment variables, run `cargo run -- connect`, then run one opencode prompt against the underclass provider. Expected output: a completed response and a usage row in the admin page for <account label>. Verify that the admin page lists the account as healthy after the request.

  Share Save

• Route Claude Code through a pool of Claude subscriptions

  Point the official Claude Code client at a local proxy that rotates across several Claude Code accounts.

  • Underclass
  • Claude Code
  • Software and DevOps
  • Intermediate
  View prompt

  In the underclass repo at <repo path>, start the server, export ANTHROPIC_BASE_URL and CLAUDE_CODE_OAUTH_TOKEN as the README describes, and run one short Claude Code task. Expected output: a completed task and a request row for a Claude Code account in the admin page. Verify that the account's plan and its 5-hour, 7-day, and model-scoped windows are shown.

  Share Save

• Watch pool quota, cooldowns, and plans in real time

  Open a live terminal monitor that shows in-flight requests, account states, and quota windows.

  • Underclass
  • Software and DevOps
  • Intermediate
  View prompt

  In the underclass repo at <repo path>, with the server running, start `underclass top` and capture the account table. Expected output: one row per configured account with a status label and plan. Verify that each cooling account shows a reset time and that the PLAN column is filled or marked unknown.

  Share Save

• Audit token use and stream failures over the last week

  Summarize requests, tokens, and failed streams per model or account from the local database.

  • Underclass
  • Software and DevOps
  • Intermediate
  View prompt

  In the underclass repo at <repo path>, with the server running, run `underclass stats --since 7d --by model` and save the output. Expected output: a UTC table with requests, tokens in and out, and event columns. Verify that the totals match the sum of the per-model rows.

  Share Save

How to use Underclass

1. Check you have what it needs: Rust toolchain with cargo, to run `cargo run -- serve` from the repo; openssl available on the machine, to generate the proxy key and UI token; At least one ChatGPT/Codex, GitHub Copilot, or Claude Code subscription you are entitled to use.
2. Open ghuntley/underclass on GitHub and read the README and license.
3. Clone the repo and, from its root, run UNDERCLASS_PROXY_KEY="$(openssl rand -hex 32)" UNDERCLASS_UI_TOKEN="$(openssl rand -hex 32)" cargo run -- serve and keep the generated values in a password manager. (inferred, check the README)
4. Open http://127.0.0.1:8080/ in a browser, paste the value you set as UNDERCLASS_UI_TOKEN, click Add account, and sign in to each ChatGPT/Codex or Copilot subscription you want in the pool.
5. In a second terminal, run cargo run -- connect to write the provider block into your global opencode config.
6. Run opencode --provider underclass --model underclass/gpt-5.5 and send a prompt.

These steps come from our top use case, Point opencode at a pool of coding subscriptions, which also has a copy-paste agent prompt.

Underclass alternatives · Best AI repos for Software and DevOps

About this repo

• Who it is forDevelopers who already hold several personal AI coding subscriptions and want one local endpoint that their coding clients can use.
• Why it is hot
• LanguageRust
• Sourcegithub.com/ghuntley/underclass · Back to Hot repos

Requirements

• Rust toolchain with cargo, to run `cargo run -- serve` from the repo
• openssl available on the machine, to generate the proxy key and UI token
• At least one ChatGPT/Codex, GitHub Copilot, or Claude Code subscription you are entitled to use
• opencode installed if you want to use the OpenAI-compatible path from that client
• Read each provider's terms before pooling accounts; the README does not address this

Related repos

• #1 this week Harness2 Harness² is a Python framework from Google Research that refines the harness around a fixed model (prompts, tools, memory, skills, orchestration) so it performs better on agent tasks.
• #8 this week iFixAi iFixAi is an open-source Python tool that audits whether an AI agent is doing the job it is supposed to do, using 60 inspections that combine red-teaming with operational checks.
• #9 this week Orca Orca is a desktop app, with a mobile companion, for running several CLI coding agents side by side, each in its own git worktree, and tracking them in one place.