Synchronised from GitHub, curated by hand

• Featured

  sentinel-memory

  An incident-response agent whose memory is a transactional database rather than a context window. Retrieval over CockroachDB's distributed vector index surfaces what a proposed action cost during a previous incident, with the incident code, date and damage attached; approval commits four writes in one transaction. 94 tests, none requiring a live cluster.

  From GitHub An AI incident-response agent that uses CockroachDB and Amazon Bedrock to remember consequences and prevent repeated mistakes.

  TypeScript 95% · JavaScript 5% · CSS 1%

  Licence

  MIT

  Last push

  Pushed 16 days ago

  Project: Sentinel Memory Hackathon: CockroachDB × AWS — Build with Agentic Memory Homepage
• Featured Private Not in last sync

  astranova-trading-copilot

  AstraNova — an AI trading copilot for India's options traders, built for the Build with Gemini XPRIZE hackathon. Joins live Angel One market data, AI-scored signals, real broker execution and a Gemini-powered assistant.

  This repository is private on GitHub, so it is listed but not linked.

  Project: AstraNova Hackathon: Build with Gemini XPRIZE
• Featured

  Circular-trade-Fraud-Detection

  Graph-based detection of circular trading rings in iron-dealer invoice data: cycle detection over a multi-graph representation feeds a per-node suspicion score, Node2Vec embeddings, and DBSCAN clustering to isolate dense regions of anomalous trading behaviour.

  From GitHub This project focuses on leveraging multi-graph representation techniques for fraud detection. The dataset given is iron dealers data which contains information about invoices between sellers and buyers and the value of transaction. Each row in the dataset represents one invoice and contains the following information

  Language

  Jupyter Notebook

  Last push

  Pushed 10 months ago

  Project: Circular Trade Fraud Detection with Graph Learning
• Sentimental-Analysis

  Fine-tuning bert-base-uncased on the SMILE annotation dataset for multi-class sentiment classification — a complete PyTorch pipeline from tokenisation through AdamW training with linear warm-up. A learning project rather than a research contribution.

  Language

  Jupyter Notebook

  Last push

  Pushed last year

  Project: Multi-Class Sentiment Analysis with BERT
• To-Do-List-Application

  A small vanilla-JavaScript task list. Early web practice, listed for completeness under coursework and learning labs.

  From GitHub This is a To Do List Application

  • bootrsap
  • css
  • html
  • javascript
  • project
  • to-do-list-app
  JavaScript 52% · CSS 28% · HTML 20%

  Last push

  Pushed last year

  Homepage
• WebPage

  Static HTML/CSS practice page. Listed under coursework and learning labs.

  Language

  HTML

  Last push

  Pushed last year

• ParishruthiGanesh.github.io

  The source of this site: an Astro + TypeScript + Tailwind portfolio with Zod-validated structured content, a GitHub synchronisation pipeline and a `portfolio` CLI for adding papers, projects and hackathons.

  TypeScript 49% · Astro 48% · CSS 3%

  Licence

  MIT

  Last push

  Pushed 15 days ago

No repositories match these filters.

Forks and empty scratch repositories are excluded from this list by default. The exclusion rules live in content/repositories-overrides.yml.