MetaEditor, Open AI and ChatGPT - page 8

[Sergey Golubev]

From Novice to Expert: Animated News Headline Using MQL5 (IV) — Locally hosted AI model market insights

In the previous discussion, we focused on Indicator Insights. Today, we’ll explore how to harness open‑source AI for algorithmic trading by self‑hosting a quantized language model and integrating it directly into an MQL5 Expert Advisor. In the next section, we’ll begin with a brief primer on the roles of llama.cpp (the lightweight inference engine) and a 4‑bit GGUF model (the compressed “brain”), then walk through downloading and preparing the model, setting up a local Python‑based inference server with FastAPI, and finally wiring it into the News Headline EA to create a dynamic AI Insights lane.

[Sergey Golubev]

From Novice to Expert: Animated News Headline Using MQL5 (VI) — Pending Order Strategy for News Trading

The integration of alerts in the previous version of our Expert Advisor was a significant step forward, transforming it into a valuable tool for manual news traders. However, a key limitation still remains: the EA has yet to automate trade executions. Today, our goal is to address that gap by integrating the CTrade class to enable automatic trading based on news events.

[Sergey Golubev]

Analyzing binary code of prices on the exchange (Part II): Converting to BIP39 and writing GPT model

This article will consider in detail how to implement such a "translator" using modern machine learning tools, and more importantly, how to interpret its "translations". We will see that some words and phrases appear more often than others in certain market situations, as if the market really uses its own vocabulary to describe its conditions.

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

How to Start with MT5, a summary !

Sergey Golubev, 2025.08.28 08:49

Getting Started with MQL5 Algo Forge

The new MQL5 Algo Forge is more than just a list of your projects – it's a full-fledged social network for developers. You can easily track changes, maintain project history, connect with like-minded professionals, and discover new ideas. Here, you can follow interesting authors, form teams, and collaborate on algorithmic trading projects.  

MQL5 Algo Forge is built on Git, the modern version control system. It equips every developer with a powerful toolset for tracking project history, branching, experimenting, and working in teams. But how does it all work? In this article, we'll explain how to get started with MQL5 Algo Forge.

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

How to Start with MT5, a summary !

Sergey Golubev, 2025.09.04 16:55

From "New MetaTrader 5 Platform Build 5260: Enhancements in Algo Forge, extended OpenBLAS support, and new inheritance rules in MQL5" - 

On the service website, we have published comprehensive MQL5 Algo Forge documentation. It clearly demonstrates all the features and advantages of using the Git system for algorithmic traders: how to explore projects, follow interesting publications, collaborate, and clone repositories.

--------------------

Guide to Working with MQL5 Algo Forge

[Sergey Golubev]

Moving to MQL5 Algo Forge (Part 1): Creating the Main Repository

At the time this article is being written, the new repository is already available for use, but MetaEditor integration has not yet been completed. Thus, while MetaEditor remains the main development environment, developers are still limited to MQL Storage based on SVN.

[Sergey Golubev]

Moving to MQL5 Algo Forge (Part 2): Working with Multiple Repositories

In the first article, we began transitioning from the built-in SVN-based MQL5 Storage in MetaEditor to a more flexible and modern solution based on the Git version control system: MQL5 Algo Forge. The main reason for this step was the need to fully leverage repository branches while working on multiple projects or on different functionalities within a single project.

[Sergey Golubev]

Moving to MQL5 Algo Forge (Part 3): Using External Repositories in Your Own Projects

In the second part of our transition to MQL5 Algo Forge, we focused on solving one of the important challenges –working with multiple repositories. Using the combination of the Adwizard library project and the Simple Candles Expert Advisor, we encountered and successfully resolved issues mostly related to file inclusion paths and branch merging. We also tried to use MetaEditor tools (where possible) throughout the entire workflow, from creating a separate branch for fixes to merging it via a Pull Request. However, where MetaEditor functionality was not enough, we switched to the MQL5 Algo Forge web interface, an external Git client in Visual Studio Code, or Git console commands. This clearly demonstrated how even in individual development, you can apply Git best practices to maintain order and a clear history of changes within your project.

In this article, we finally turn to this promising, yet more complex, task: how to practically connect and use libraries from third-party repositories within MQL5 Algo Forge. And not "someday in the future" but right now, without waiting for further development of MetaEditor's repository tools.

[Vladislav Boyko]

😁

[Sergey Golubev]

Moving to MQL5 Algo Forge (Part 4): Working with Versions and Releases

In today's article, we will take a closer look at the stage of publishing the edits made in the repository, a certain set of changes that form a complete solution, whether it's adding new functionality to a project or fixing a discovered issue. This is the process of committing or releasing a new product version. We will see how to organize this process and what capabilities MQL5 Algo Forge provides for it.