I built a surf forecast that shows its own arithmetic

Description and use

Swellread turns raw swell, wind and tide data into a clear verdict with transparent arithmetic and interactive tide manipulation.

Problem

Surf forecasts provide raw numbers but no interpretation, leading to half‑right decisions.

Outcome

Swellread delivers actionable surf forecasts with transparent arithmetic, interactive tide manipulation, a playable wave model, and an agent API for planning and proof, all built with open data and client‑side AI.

Workflow

• 1. Pull real swell, wind and tide data from NOAA CO‑OPS and Open‑Meteo.
• 2. Compute six weighted factors (swell power, peel speed, wind quality, tide window, direction match, period cleanliness).
• 3. Apply hard gates (swell <0.35 m → score 0, reef depth <min → clamp 0.08).
• 4. Normalize remaining factors to sum to 1 and renormalize if a factor is missing.
• 5. Render verdict and arithmetic on the UI; allow drag‑tide interaction that POSTs a what‑if to the server.
• 6. Provide a WebGL Gerstner surface for a playable wave model.
• 7. Expose an agent API with JSON‑RPC tools for ranking, freezing plans, logging rides and proving chains.
• 8. Store sessions in a cookie‑scoped, soft‑deleted history with SHA‑384 seals for replayability.

Evidence

A forecast gives you a significant wave height, a period, a direction, a tide table and a wind arrow. That is enough information to know exactly whether a two‑hour drive is worth it.

Source

Swellread turns today's real swell, wind and verified tide predictions into one verdict per break, and then shows every number that produced it.

Source

The app draws the break's actual seabed profile, lets you move the water level, and re‑solves the peel.

Source

Eight typed tools over JSON‑RPC 2.0, four of them mutating, all through the same service layer as the web UI.

Source