Credentials. The setup asks you to store an OpenRouter API key and Clerk domain in Convex, so keep those values out of shared logs and commits.
Who it is forA developer who wants a private, self-run AI chat app and has the three required accounts ready.
The problemHosted chat apps keep your conversations and configuration on someone else's servers, and you cannot change how they work.
The outcomeA local Whirl instance at localhost:3000 where you can send messages to models through OpenRouter.
What you need first
- Bun installed
- A free Convex account
- A Clerk application
- An OpenRouter API key
- Git and a terminal
Steps
- Run
git clone https://github.com/whirlchat/whirl.gitand thencd whirl. - Run
bun installfrom the repo root. - Run
cd packages/backendthenbunx convex devand finish the first-run project setup. - In another terminal, run
bunx convex env set CLERK_JWT_ISSUER_DOMAIN https://your-instance.clerk.accounts.devandbunx convex env set OPENROUTER_API_KEY sk-or-v1-.... - Run
cd ../../apps/v2, thencp .env.example .env.local, fill in the four required values, then runcd ../..andbun run dev. - Open localhost:3000 in a browser and send a test message.
Prompt for your agent
In the whirlchat/whirl repo, follow the Quick start in the README to run the web app locally using my Convex, Clerk, and OpenRouter values in <placeholder-env-file>. Report the URL the app is serving on and whether a test message to a model returns a reply. Verify that bun run dev starts without errors before reporting success.
Caveat. The README says the self-hosting guide covers the Clerk JWT template Convex needs, so read that guide before assuming the quick start alone is complete.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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