ai
Hack Club's lightweight LLM proxy, listed for adding a Jev forwarding endpoint behind its auth, limits and usage logging.
Overview
Hack Club AI is a lightweight LLM proxy used by Hack Club. It handles Hack Club auth, API keys, chat, embedding and moderation models, global analytics and usage logging, optional Sentry, blocking of coding tools, spending limits and optional Replicate support, typically routing through OpenRouter.
According to the list summary, it includes a Jev forwarding endpoint, so members can call Jev through the same authentication, limits and usage logging as other models. The README excerpt does not describe that endpoint. The proxy is configured with allowlists of language, embedding and image models, routes through OpenRouter by default, can require ID-verified users, and must sit behind a reverse proxy so client IPs cannot be spoofed.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Forwards members' Jev requests; the decisions are whatever callers ask(inferred) | — |
How it works
- Member authenticates with a Hack Club API key
- Request hits the proxy's Jev endpoint
- Proxy enforces limits and logs usage
- Request is forwarded to Jev and the answer returned
Strengths
- Shared auth, limits and usage logging for Jev calls
Caveats
- Jev endpoint not documented in the README excerpt
- Must sit behind a reverse proxy to avoid IP spoofing
At a glance
- Type
- MCP server
- Status
- production
- Language
- TypeScript
- Runtime
- Node service + Postgres
- Has code
- yes
Use cases and integrations
How curated lists describe it
A Jev forwarding endpoint in the Hack Club AI proxy, using its authentication, limits and usage logging.
logicrw/awesome-jev-projects
Frequently asked questions
What does it add for Jev?
A forwarding endpoint that applies the proxy's auth, limits and logging, per the listing.
Who is it for?
Hack Club members using the shared AI proxy.
Does it make decisions itself?
No, it only forwards requests.
Related projects
npm library that rate-limits, spend-caps, caches and redacts every Jev request made in a loop.
LibrarybetaJavaScriptGo gateway that pools multiple TypeSafe accounts behind the native System One API with user keys, quotas and failover.
ServicebetaGoRust CLI for Jev that lints typed question sets offline, then sends them and prints probabilities, labels and scores as JSON.
CLIbetaRustOffline TypeScript token counter and request-cost estimator for Jev 1.13, a port of the reconstructed jevtok encoder.
PluginbetaTypeScriptTask plugin for the new-api LLM gateway that adds a native /v1/systemone endpoint for Jev with auth, routing and token billing.
PluginbetaJavaScriptChinese-documented LLM gateway with virtual model routing, protocol conversion and a transparent Jev System One proxy.
ServicebetaTypeScript