OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Trading & Crypto Agents

Riftcoach Agent

Riftcoach Agent is an open-source Python system that analyzes public, completed League of Legends matches and generates coaching reports from deterministic match statistics, retrieved knowledge and model explanations, with independent evaluation gating publication.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Riftcoach Agent — OpenViST project profile in Trading & Crypto Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it for post-game analysis and training guidance when you can work with a locally configured Python project and its Riot API and Zhipu GLM dependencies.

Who it is for

  • League of Legends players or coaches seeking structured reviews of completed matches, when the project is locally configured.
  • Developers studying or extending an agent that combines game-data analysis, retrieval-augmented generation, quality gating and persistent coaching workflows.

Documented uses

  • Review recent completed matches using Riot match and timeline data.
  • Turn calculated performance measures into a Chinese-language coaching report supported by retrieved knowledge.
  • Track player conversations, typed memory, training plans and progress in a PostgreSQL-backed workflow.
  • Provide a constrained lane-meta snapshot through an MCP tool boundary.
Before you choose

Requirements & limits

The public GitHub repository identifies the project as MIT-licensed. Local development requires Python 3.11 or newer and local Riot API and Zhipu GLM configuration.

  • The supported game workflow is specific to League of Legends and public post-game data; adapting it to another game requires new data integration, domain logic and coaching knowledge.
  • The documented coaching report is in Chinese and uses Zhipu GLM.
  • The OP.GG integration supplies a restricted lane-meta snapshot with partial provenance; it does not replace Riot-derived player facts.
  • Formal public authentication and a front-end are not implemented, so the documented setup is developer-oriented.
  • The system evaluates report quality, but repository infrastructure and test evidence do not establish real-world model report quality.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the local development environment

Install the project’s development package and prepare local credentials for its Riot-data and coaching-report workflow.

Before you start

  • Python 3.11 or newer
  • A local Riot API configuration
  • A Zhipu GLM configuration

Steps

  1. Create and activate a Python 3.11 virtual environment.

  2. Install the development package with the command below.

    Documented command
    python -m pip install -e ".[dev]"

  3. Copy .env.example to .env and fill in the local Riot API and Zhipu GLM configuration; do not commit the file.

Expected outcome

A locally configured development environment for the project’s coaching workflow.

Guide limitations

  • This setup guide does not establish that a coaching run or report has been executed.
  • The repository’s full runtime also involves PostgreSQL and separate service components; this recipe covers the documented basic development setup.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
123Cx330Yrx/riftcoach-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction