Add Lightning Rod Labs MPP services#780
Open
bartolomej wants to merge 2 commits into
Open
Conversation
|
@bartolomej is attempting to deploy a commit to the Tempo Team on Vercel. A member of the Team first needs to authorize it. |
|
Thanks for submitting a service to the MPP directory! If you want your service included in the curated Required
Recommended
Review criteriaWe prioritize services that are high quality and novel. We may not approve services that duplicate existing functionality or aren't yet production-ready. |
🔀 Changed Services✅ Added
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds LightningRod (Lightning Rod Labs) to the service directory — an AI forecasting API that predicts anything via OpenAI-compatible endpoints, with structured answers (binary, multiple-choice, continuous, free-response), optional web research, and low/medium/high reasoning effort.
Unlike a per-request proxy, LightningRod uses a credit + API-key model: agents pay once over MPP at
POST /v1/mpp/topupto fund a balance and receive an API key, then call the forecasting endpoints with that key. Accepts Stripe and Tempo USDC.e.Endpoints
Only
POST /v1/mpp/topupcarries an MPP payment (charge, dynamic, $1–$10,000, default $5). The forecasting endpoints (/v1/openai/chat/completions,/v1/openai/completions,/v1/openai/models) authenticate with the API key returned by top-up and draw down the prepaid balance — no per-request MPP payment — so they are listed without an amount (rendered as "—", no intent badge) purely to surface the product's API surface. Each description states the balance requirement. A code comment in the entry documents this so the routes aren't mistaken for missing prices.Required checklist
schemas/services.tspnpm check:typespnpm checknode scripts/generate-discovery.ts(LightningRod present indiscovery.json+llms.txt)pnpm build(verified locally; static generation emits LightningRod into the services bundle. Requires anMPP_SECRET_KEY≥ 32 bytes — CI supplies the real secret)Recommended