valkia/aramgg_client

Windows companion for League of Legends ARAM Mayhem with read-only LCU recommendations, Hextech Augment stats, and in-game OCR overlays.

What it solves

This tool provides real-time strategic advice for the "ARAM" (All Random All Mid) game mode in League of Legends. It helps players make informed decisions during champion selection and provides data-driven recommendations for "Augments" during gameplay, such as win rates and suggested item builds.

How it works

The application runs on Windows and monitors the game in two ways: it uses a read-only connection to the League Client Update (LCU) service to fetch champion and lobby data, and it uses PaddleOCR (optical character recognition) to identify Augment cards directly from your screen during a match. It then overlays this information in a non-intrusive window, ensuring you have access to stats without the software ever performing automated actions like locking in champions or accepting trades.

Who it’s for

It is designed for League of Legends players who want quick access to performance statistics and build recommendations while playing ARAM, without needing to manually search for data or alt-tab out of the game.

Highlights

  • Read-only LCU integration: Safely retrieves game state information without interfering with game controls.
  • Real-time Augment recognition: Uses screen-based OCR to detect Augment choices and display relevant win rates and build paths.
  • Local-first data: Prioritizes locally cached data for fast performance, with background updates for the latest stats.
  • Multi-language support: Seamlessly switches between Simplified Chinese, Traditional Chinese, and English for both the interface and data.
  • Privacy-focused: Designed with security in mind, keeping the renderer isolated from sensitive system processes.

Related

  • Project
    signerless/llm-checker

    An intelligent CLI tool that analyzes your hardware to recommend, rank, and manage local LLMs, featuring hardware-calibrated memory estimation and an integrated MCP server for AI assistants.

  • Project
    ramjke/Translumo

    A real-time screen translator that uses OCR and machine learning to translate text from PC games and applications directly on the screen.

  • Project
    amd/skills

    AMD Skills is a catalog of reusable, agent‑compatible “skills” that encode AMD‑specific AI workflow knowledge (ROCm diagnostics, Quark quantisation, LLM serving on Instinct/EPYC, etc.). Install via the `skills` CLI (`npx skills add amd/skills`) or manually, then invoke the skills through coding assistants like Cursor, Claude Code, Codex or Gemini. Each skill bundles a `SKILL.md` description, optional scripts and references, enabling agents to automatically perform setup, optimisation and debugging steps for AMD hardware.

  • Project
    MaaAssistantArknights/MaaAssistantArknights

    An automation assistant for Arknights that uses image recognition and OCR to automate daily tasks, resource farming, and base management.

  • Dispatch
    Your Game Is a Harness: Engineering AI Harnesses for Game Development

    Kyle Kukshtel's talk-turned-essay "Your Game Is a Harness" argues that LLMs fail at game development because games contain large amounts of non-code state that models cannot read, and that seeded randomness, external data, command-based state changes, and a standalone simulation core make a game legible enough for agents to iterate on it.