DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to fetch personalized recommendations for a user with Gorse

Request the top items for a user from the recommend endpoint and plug them into your app.

Short answer: Make sure the user has feedback in Gorse; then call curl http://127.0.0.1:8088/api/recommend/bob?n=10 with your user ID in place of bob; Render the returned items in your app. All steps.

  • Data and analytics
  • Intermediate
  • 30 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

network-exposure. The quick start exposes the API on port 8088 with no authentication step shown; keep it off public networks.

Who it is forA product engineer adding a recommended for you list.

The problemTeams need a simple API that returns ranked items per user.

The outcomeA list of recommended item IDs for a user that reflects their feedback.

What you need first

  • Docker for the gorse-in-one image
  • curl or any HTTP client for the REST API
  • For production: MySQL (MariaDB), MongoDB or Postgres for storage, with a cache such as Redis

Steps

  1. Make sure the user has feedback in Gorse
  2. Call curl http://127.0.0.1:8088/api/recommend/bob?n=10 with your user ID in place of bob
  3. Render the returned items in your app
  4. For scale, split into master, worker and server nodes as the Architecture section describes

Prompt for your agent

Using gorse-io/gorse, call `curl http://127.0.0.1:8088/api/recommend/bob?n=10` for <user id> before and after posting new feedback, and show how the list changed.

Caveat. Gorse trains on a single node and predicts in a distributed way; production storage needs MySQL, MongoDB or Postgres.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for gorse-io/gorse and "Fetch personalized recommendations for a user"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer