gorse-io/gitrec

A recommender system for GitHub repositories based on Gorse provides personalized recommendations and similar repositories

GitRec – A Recommender System for GitHub Repositories

What it is

GitRec is an open‑source service that suggests GitHub repositories to users. It sits on top of Gorse, an open‑source recommendation engine, and provides a ready‑to‑use web UI plus browser extensions that surface recommendations directly inside GitHub.

Why it matters

Finding useful projects on GitHub is a pain point for developers. GitRec automates the discovery process:

  • Personalised suggestions – based on the repos a user has starred.
  • Related‑repo discovery – shows similar projects for any popular repository. The system can be self‑hosted, giving teams full control over data and the recommendation model.

Core components (as described in the README)

Component Role
Gorse engine The underlying recommendation algorithm (collaborative‑filtering, content‑based, etc.). GitRec simply configures and queries it.
Web UI Accessible at http://127.0.0.1:5000/, lets users browse recommendations and manage settings.
Gorse Dashboard Admin UI at http://127.0.0.1:8088/ for monitoring the recommendation service.
Browser extensions Chrome, Edge and Firefox add‑ons that inject recommendation widgets into the GitHub site.
Docker‑Compose stack Spins up the Gorse service, a MySQL database, and the GitRec web server with a single command.
Data import A pre‑built github.sql dump can be loaded into MySQL to give the system a starting catalogue of repositories.

How to get it running (quick‑start steps)

  1. Clone the repo and cd into it.
  2. Create a .env file with credentials for:
    • Gorse dashboard (user, password, API key)
    • GitHub (personal access token, OAuth client ID/secret)
    • Optional S3 bucket for backups
    • Optional OpenAI endpoint (the README mentions an OPENAI_MODEL but does not detail its use).
  3. Start the services with docker-compose up -d.
  4. Load sample data – download github.sql and import it into the MySQL container.
  5. Restart the master node so the imported data is recognised.
  6. Open the UI (http://127.0.0.1:5000/) or install the browser extension to see recommendations.

Who might use it

  • Individual developers who want a personalised “discover” page for GitHub.
  • Teams that want an internal recommendation service without sending data to a third‑party SaaS.
  • Researchers experimenting with recommendation algorithms on open‑source code data.

Limitations & open questions (based on the README)

  • The README references an OpenAI model (gpt-6-luna) but does not explain how it is used – it may be optional or experimental.
  • Running the full stack requires Docker, MySQL, and a GitHub OAuth app, which adds setup overhead.
  • No explicit mention of model training; GitRec appears to rely on Gorse’s built‑in algorithms.

All information above is taken directly from the repository’s README.

Related

  • Project
    Mubelotix/SimRepo

    A browser extension that suggests similar GitHub repositories using a vector database and a model trained on 300 million stars.

  • Project
    gorse-io/gorse

    Gorse is an open‑source, Go‑based recommender‑system server that automatically trains models from user‑item interaction data and serves personalized suggestions via REST APIs or a web dashboard. It supports multiple recommendation algorithms, multimodal item embeddings, and can run on a single node or a distributed cluster.

  • Project
    zamalali/DeepGit

    An agentic research engine for GitHub that uses LLMs and semantic recall to find the best-fitting repositories based on intent and source code analysis rather than just keywords or stars.

  • Project
    hustcer/deepseek-review

    DeepSeek Code Review is a tool (GitHub Action + Nushell CLI) that uses DeepSeek LLMs to automatically review code changes in pull requests, with customizable prompts, model choice, and support for local diff reviews.

  • Project
    AmintaCCCP/GithubStarsManager

    GithubStarsManager is an Electron‑based desktop app that syncs your GitHub stars, enriches each repo with AI‑generated summaries, tags and categories, and lets you search them semantically via Cloudflare Vectorize. It also offers a repository Q&A assistant, release‑tracking timeline, fork and Gist management, a discovery feed, and an optional self‑hosted backend for cross‑device sync. Supports multiple LLM providers, local‑first data storage, and a Model Context Protocol server for AI agents.