Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Designing end-to-end weekly stock report generation using LSTM and Agentic AI. Deploying on AWS with MLOps practices.
| Date | Stars |
|---|---|
| 2026-07-31 | 297 |
| 2026-08-06 | 298 |
Today
+1 stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# 📈 MLOps Pipeline: End-to-End Weekly Stock Report Generation
[](https://github.com/kmeanskaran/stock-agent-ops/blob/main/LICENSE)
[](https://www.python.org/downloads/)
[](https://docs.docker.com/compose/)
[](https://feast.dev/)
[](https://mlflow.org/)
> **Design an end-to-end automated system for weekly stock market analysis using Transfer Learning (LSTM) and Agentic AI (LangGraph).**
---
## 🏗️ Clone & Local Setup
### 1. Clone the Repository
```bash
git clone https://github.com/kmeanskaran/stock-agent-ops.git
cd stock-agent-ops
```
### 2. Local Environment Setup (Using UV)
We use `uv` for lightning-fast dependency management.
```bash
# Install uv if you haven't
curl -LsSf https://astral.sh/uv/install.sh | sh
# Sync dependencies and create venv
uv sync
```
---
## 🌟 Overview
This project is a production-grade MLOps pipeline that automates the entire lifecycle of stock price prediction and financial reporting. It shifts from traditional monolithic ML scripts to a modular, scalable architecture using modern MLOps tools.
### Key Capabilities:
- **🧠 Transfer Learning**: Uses a Parent-Child architecture (S&P 500 base model) to predict individual stock prices accurately with minimal data.
- **🤖 Agentic AI**: A multi-agent system (LangGraph) that acts as a financial analyst, market expert, and editor to generate Bloomberg-quality reports.
- **📖 Deep Learning & Design**: Explore the [In-depth System Design Guide](./doc/system_design.md) for a technical breakdown.
- **⚡ Real-time Serving**: Low-latency predictions powered by FastAPI and Redis caching (1-day TTL).
- **🍽️ Feature Store**: Consistent data management for training and serving using **Feast**.
- **🔍 Observability**: Full-stack monitoring with Prometheus, Grafana, and Evidently AI for data drift detection.
---
## 🏗️ Technical Architecture
```mermaid
graph TB
subgraph "User Layer"
UI[Streamlit UI]
MON_UI[Monitoring Dashboard]
end
subgraph "Logic Layer"
API[FastAPI Orchestrator]
TRAIN[Training Pipeline]
AGENT[LangGraph Agents]
end
subgraph "Storage & Memory"
REDIS[(Redis Cache)]
QDRANT[(Qdrant Vector DB)]
FEAST[(Feast Feature Store)]
MLFLOW[DagsHub MLflow]
end
UI --> API
API --> TRAIN
API --> AGENT
TRAIN --> FEAST
TRAIN --> MLFLOW
AGENT --> QDRANT
API --> REDIS
```
---
## 🛠️ Tech Stack
| Component | Technology |
| :--- | :--- |
| **Model** | PyTorch (LSTM) |
| **LLM Engine** | Ollama (`gpt-oss:20b-cloud`) |
| **Embeddings** | Ollama (`nomic-embed-text`) |
| **AI Agents** | LangGraph, LangChain |
| **Feature Store**| Feast |
| **Registry** | MLflow (via DagsHub) |
| **Vector DB** | Qdrant (Semantic Caching) |
| **Cache** | Redis Stack |
| **Backend** | FastAPI (Async) |
| **Frontend** | Streamlit |
| **Observability**| Prometheus, Grafana |
---
## 🚀 Quick Start
### 1. Prerequisites
- [Docker & Docker Compose](https://docs.docker.com/get-docker/)
- [Ollama](https://ollama.com/) (Running on host machine)
- [FINHUB](https://finnhub.io/) (Get FinnHub API key)
- [UV](https://docs.astral.sh/uv/guides/install-python/) (UV package manager for Python
#### Install Ollama Models
1. LLM: GPT-oss:20b Cloud - `gpt-oss:20b-cloud`
2. EMBEDDINGS: nomic-embed-text - `ollama pull nomic-embed-text`
### 2. Configure Environment
Create a `.env` file in the root:
```bash
# DagsHub Tracking
# DagsHub Configuration for Remote MLflow Tracking
DAGSHUB_USER_NAME=
DAGSHUB_REPO_NAME=
DAGSHUB_TOKEN=
MLFLOW_TRACKING_URI=
REDIS_HOST=localhost
REDIS_PORT=6379
GOOGLE_API_KEY=
FMI_API_KEY=
```
### 3. Spin up the SExcerpt of 6,526 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:322703adb1c50711, llm:Description: 'Designing end-to-end weekly stock report generation using LSTM and Agentic AI. Deploying on AWS with MLOps practices.' Topics: agentic-ai, aws, devops, machine-learning, mlops, neural-network
matched fp:322703adb1c50711, llm:Description: 'Designing end-to-end weekly stock report generation using LSTM and Agentic AI. Deploying on AWS with MLOps practices.' Topics: agentic-ai, aws, devops, machine-learning, mlops, neural-network
matched fp:322703adb1c50711, llm:Description: 'Designing end-to-end weekly stock report generation using LSTM and Agentic AI. Deploying on AWS with MLOps practices.' Topics: agentic-ai, aws, devops, machine-learning, mlops, neural-network
matched fp:322703adb1c50711, llm:Description: 'Designing end-to-end weekly stock report generation using LSTM and Agentic AI. Deploying on AWS with MLOps practices.' Topics: agentic-ai, aws, devops, machine-learning, mlops, neural-network