slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
RayCodes_Kronos
Kronos Indian Market Advisor is an AI-driven quantitative prediction and interpretation system that combines a small candlestick foundation model (Kronos-base) with a local LLM (Llama 3.2 3B) to generate beginner-friendly forecasts and reports for Indian equities, forex, and commodities.
Stars
6
7-day growth
No data
Forks
7
Open issues
0
License
No data
Last updated
2026-07-28
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It democratizes advanced quantitative forecasting by pairing a compact, open-source foundation model with a local LLM, making sophisticated market analysis accessible and understandable for Indian retail investors without requiring deep financial knowledge.
Who it is for
- Indian retail investors new to technical analysis
- Quantitative finance enthusiasts seeking lightweight, local AI tools
- Developers building beginner-friendly market advisory applications
- Indian traders interested in AI-enhanced swing trading and hedging
Use cases
- Navigating NIFTY 50 trends with plain-language explanations
- Identifying entry and profit targets for high-liquidity Indian blue-chip stocks
- Monitoring Gold ETFs and USD/INR for volatility hedging decisions
- Generating pre-market quantitative screening reports to validate trading hypotheses
Strengths
- Open-source and fully local (privacy, no API costs) with a ~400MB foundation model and Ollama-based LLM
- Beginner-friendly interpretation that converts complex quantitative metrics into intuitive analogies
- Includes an automated backtesting script (proof_test.py) for directional accuracy validation
- Produces aesthetic, interactive HTML reports with dark-mode glassmorphism and export features
Considerations
- Requires manual setup of Ollama and pulling the llama3.2:3b model, which may be a barrier for non-technical users
- The Kronos-base model (102.3M params) may have lower accuracy compared to larger, cloud-based forecasting models
- Currently focused exclusively on Indian markets (NSE, BSE, USD/INR, Gold ETFs), limiting geographic applicability
README quick start
📺 Watch the full tutorial on YouTube
🇮🇳 Kronos Indian Market Advisor
An advanced, AI-driven quantitative prediction and interpretation system designed specifically for Indian financial investors and beginners. Powered by Kronos-base (the ~400MB open-source candlestick foundation model trained on global exchanges) and localized by Llama 3.2 3B via Ollama, this project translates complex K-line sequences into jargon-free, high-value financial insights for equities like NIFTY 50, Reliance Industries, HDFC Bank, Gold ETFs, and USD/INR exchange rates.
🚀 Key Highlights
- Kronos Foundation Model: Utilizes the 102.3M parameter (
~400MB) base model with hierarchical K-line tokenization to predict future OHLCV candlestick paths. - Beginner-Friendly Interpretation: Local Ollama AI analyzes quantitative forecasting metrics and translates them into intuitive analogies tailored to Indian market participants.
- Empirical Proof Testing: Includes an automated quantitative validation script to measure directional accuracy and support/resistance resilience against historical NSE data.
- Responsive HTML Visualizers: Generates aesthetic, interactive reporting templates featuring dark-mode glassmorphism and instant markdown export capabilities.
🛠️ Tech Stack
- Quantitative Forecaster:
NeoQuasar/Kronos-base(Hugging Face Transformers & PyTorch) - Local Explainer AI:
llama3.2:3b(via Ollama, thinking disabled for rapid inference) - Market Data Provider:
yfinance(Live NSE Indian market indices, corporate stocks, and commodities) - Visual Templating:
Jinja2with custom responsive CSS styling - Data & Math Engine:
pandas,numpy,matplotlib,torch
📦 Installation & Setup
All commands below can be executed directly in your Windows Antigravity PowerShell terminal by copy-pasting.
1. Clone & Install Dependencies
First, clone the official Kronos foundation model repository into kronos_lib and install standard Python dependencies:
git clone https://github.com/shiyu-coder/Kronos.git kronos_lib
pip install --upgrade transformers huggingface_hub safetensors pandas einops matplotlib tqdm yfinance jinja2 requests torch
2. Download Local Ollama Model
Ensure Ollama is running, and pull the required 3B instruction model:
ollama run llama3.2:3b
``
Description
Kronos AI: Tiny Model That Beats Expensive Trading Bots - Open-source foundation model for financial candlesticks with Ollama Llama 3.2 Indian market analysis.
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.