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

How to feed user behavior into recommendations over REST with Gorse

Post star or click feedback for a user and watch it change what Gorse recommends.

Short answer: Start Gorse, for example with the playground image; then build a JSON array of feedback objects with FeedbackType, UserId, ItemId, Value and Timestamp; send it with curl -X POST http://127.0.0.1:8088/api/feedback using the Content-Type header and -d payload shown in the README. All steps.

Who it is forA backend developer wiring product events into a recommender.

The problemRecommendations are only as good as the user signals you can feed in.

The outcomeFeedback records stored in Gorse for a user, ready for training.

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. Start Gorse, for example with the playground image
  2. Build a JSON array of feedback objects with FeedbackType, UserId, ItemId, Value and Timestamp
  3. Send it with curl -X POST http://127.0.0.1:8088/api/feedback using the Content-Type header and -d payload shown in the README
  4. Check the stored feedback in the dashboard

Prompt for your agent

Using gorse-io/gorse, post five star feedback events for user <user id> to the /api/feedback endpoint as the README shows, then confirm they appear in the dashboard.

Caveat.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for gorse-io/gorse and "Feed user behavior into recommendations over REST"

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