-
-
NeuroTrade’s login screen lets users securely access AI insights. Use the demo account or create your own to explore the platform.
-
The FAQ page guides users on setting up OANDA, switching modes, and resolving issues like vector search errors or account token setup.
-
New users can easily create a NeuroTrade account to start exploring AI-powered trading insights with OANDA integration support.
-
The dashboard shows trade summaries, AI insights, risk assessment, and behavioral analysis powered by MongoDB and AI embeddings.
-
The All Trades view displays detailed trade metrics synced from OANDA, including position data, P/L, and direct access to trade insights.
-
The My Accounts page displays synced OANDA account details, including balance, NAV, P/L, trade activity, and a quick link to account view.
-
NeuroTrade delivers instant trade analysis using AI, showing profit/loss, trade behavior, actionable insights from vector search results.
-
The AI Chat interface lets users ask trading questions using Vertex AI or OpenAI, with topic selection, chat history, and demo/live modes.
-
Users can manage integrations with OANDA, MetaTrader 4/5, and TradingView. OANDA is live; others are planned for upcoming releases.
-
Users securely add their OANDA API token, account ID, and select demo or live mode to sync real-time trading data into NeuroTrade.
-
Users can select from multiple AI platforms like Vertex AI, OpenAI, Claude, Gemini, and Grok to power their trading intelligence workflows.
-
The Profile screen allows users to update their email, username, and password securely, ensuring account customization and privacy.
-
Seven GitLab repos for NeuroTrade: main, frontend, backend, OANDA sync, OpenAI, Vertex AI, and candle streaming services.
-
GitLab repo for NeuroTrade AI with README, demo links, features, and system overview for semantic forex trade analysis.
-
Backend for NeuroTrade AI with user, info,alerts APIs, MongoDB, and CI/CD using GitLab. Docker ready, CORS-enabled, and tested.
-
NeuroTrade backend runs GitLab CI/CD with a tagged project runner (neurotrade, production) for automated build and deploy.
-
GitLab repo is mirrored to GitHub, enabling automatic push updates for version control and cross-platform collaboration.
-
CI/CD pipelines in GitLab automatically test, build, and deploy each commit for the NeuroTrade backend service.
-
Frontend built with React and deployed via GitLab CI. Handles user interface for AI-powered semantic forex trading insights.
-
CI/CD enabled for the React frontend using GitLab Runner tagged neurotrade, automating builds and deployments to production.
-
GitLab mirror enabled for the NeuroTrade frontend repo, auto-syncing commits to GitHub every 45 minutes for redundancy.
-
Frontend pipelines in GitLab show successful CI/CD runs for each push, ensuring build, test, and deployment are automated reliably.
-
OANDA service fetches account, trade, and candle data, pushes to RabbitMQ, and is deployed via GitLab CI with Docker support.
-
GitLab runner tagged neurotrade and production is assigned to automate CI/CD for the oanda service deployment pipeline.
-
GitLab project is configured to mirror code from GitHub to keep the neurotrade_oanda_service repo synced automatically.
-
CI/CD pipelines for neurotrade_oanda_service run on a GitLab runner with all stages passing on every push to the main branch.
-
The neurotrade_openai_service handles OpenAI embeddings and queries, with CI/CD integration and Docker-ready deployment for trade analysis.
-
The neurotrade_openai_service is linked to a dedicated GitLab runner with neurotrade and production tags for streamlined CI/CD automation.
-
Mirrored from GitHub to GitLab for automatic syncs, ensuring NeuroTrade OpenAI stays up-to-date with external changes.
-
GitLab CI/CD pipelines in neurotrade_openai_service show consistent green passes, validating deployments and sync tasks.
-
Vertex AI service powers embeddings and chat for NeuroTrade, with endpoints for querying and full Docker + CI/CD support.
-
VertexAI service uses a dedicated GitLab runner with neurotrade and production tags for automated CI/CD pipeline execution.
-
The vertexai service repo is mirrored from GitHub, ensuring GitLab stays in sync with external updates automatically.
-
Recent pipelines on neurotrade_vertexai_service show successful CI/CD runs, syncing Vertex AI service updates with GitLab.
-
The neurotrade_oanda_sync repo organizes currency pairs and sync scripts with versioned updates, CI/CD-ready using GitLab.
-
The neurotrade_oanda_sync project uses a dedicated GitLab runner tagged “neurotrade” for automated CI/CD pipeline execution.
-
The neurotrade_oanda_sync pipeline history shows all stages passing from v2 to v7, confirming stable CI/CD automation via GitLab.
-
GitLab Runner 18.0.3 is installed on a Linux/amd64 system with Go 1.23.6, built on June 11, 2025, confirming runner setup.
-
All NeuroTrade services and RabbitMQ are up and running in Docker, confirming stable deployment across seven containers.
Inspiration
Forex trading produces massive amounts of data: prices, trades, account shifts. Most traders only focus on outcomes not behavior. NeuroTrade AI was born from the need to analyze personal trading patterns semantically using AI.
We wanted to build a platform that helps traders reflect, improve, and act using data they already own. GitLab gave us the control, automation, and visibility needed to move fast and stay organized.
What it does
NeuroTrade connects to OANDA, retrieves real-time and historical trade, candle, and account data, and processes it through multiple microservices powered by OpenAI and Vertex AI.
Users can:
- Ask natural language questions about their trading behavior
- Search for past trades similar to new scenarios
- Get AI-generated behavioral insights (e.g., risk exposure, emotional decisions)
- View semantic trends over time
How we built it
We used a microservice architecture, hosted on an Ubuntu VPS. All services are containerized and deployed through GitLab CI pipelines.
- GitLab CI/CD: Each microservice repo has its own
.gitlab-ci.ymlfile with test, build, and deploy stages. - GitLab Runner: Self-hosted on Contabo, executes Docker jobs per commit.
- OANDA Service: Fetches raw trade data and sends it to RabbitMQ.
- OpenAI & Vertex Services: Embed and analyze data using vector models.
- MongoDB Atlas: Stores raw and embedded data, supports vector search.
- RabbitMQ: Queue management for asynchronous embedding.
Challenges we ran into
- Managing vector indexes across different AI providers
- Embedding consistency for candles vs. trades
- Rate-limiting and batch processing with OpenAI and Vertex AI APIs
- Scaling GitLab Runner and making sure deploys didn’t interrupt containers
Accomplishments that we're proud of
- Successfully used GitLab to orchestrate an end-to-end MLOps pipeline
- Designed reusable GitLab CI templates across services
- Embedded over 20,000 candles and trades into MongoDB with consistent schema
- Delivered vector search and GPT-powered query endpoints on schedule
What we learned
- GitLab makes multi-repo workflows intuitive and highly customizable
- You don’t need Kubernetes, Docker + GitLab Runner is enough for small MLOps
- Semantic search changes how traders interact with their own data
What's next for NeuroTrade AI: GitLab-Driven Semantic Trade Intelligence
- GitLab Issue Boards for user feedback integration
- Auto-scaling services based on RabbitMQ queue load
- GitLab Pages for public dashboards and doc hosting
- Deeper model tuning with GitLab ML Experiments
Built With
- certbot
- docker
- express.js
- gitlab-ci/cd
- gitlab-runner
- mongodb-atlas-(vector-search)
- nginx
- node.js
- oanda-rest-api
- openai-api
- rabbitmq
- react.js
- ubuntu-24.04
- vertex-ai
Log in or sign up for Devpost to join the conversation.