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

How to run Comma locally with a mock model for testing with Comma

Start the backend and Web client without a model key and run the test suites.

Who it is forA developer who wants to explore or contribute to Comma and does not have a model provider key yet.

The problemSetting up a model provider just to see how Comma works slows down development and testing.

The outcomeA local Comma backend and Web client running on a deterministic mock model, with the client and system test suites passing.

What you need first

  • Docker Engine with Compose v2.24 or later for self-hosting
  • A model provider account, or a ChatGPT or Claude plan, for real model calls
  • Enough disk space for the first Docker build, which downloads Lean, Elixir, Go, and Node toolchains
  • A Mac with the Comma Mac app for local file and agent work
  • pnpm and make for local development

Steps

  1. Run pnpm install once in the repository root.
  2. Run make dev to start the local backend and the Web client.
  3. Sign in as [email protected] and read the login code in Mailpit at the address shown in the README development section.
  4. Run make test-clients from the repository root.
  5. Run make test-systems from the repository root.

Prompt for your agent

In the AFK-surf/Comma repository, install dependencies with pnpm, start the local stack with make dev, and run make test-clients and make test-systems. Report which suites pass and which fail, with the failing test names. Verify that the mock model is in use by confirming the README says make dev uses a deterministic mock model.

Caveat. The mock model in make dev is deterministic and does not give real model answers, so use a configured provider to test real 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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