This project is an automatic web scraper that uses the LLM Ollama gpt-oss:20b to parse the body content of a web page. The application is built using Streamlit for the user interface and various Python libraries for web scraping and parsing.

aillm

ollama

pythonstreamlit-webapp

ML-object-detection-project

Repo · 3 stars · Python

▲ 0

YOLOv8s football detection, player tracking and pitch mapping, with a live match viewer.

computer-visionobject-detection

pythonsoccer-analyticsjupyter-notebook

NLP-Cyber-Harm-Detection

Repo · 2 stars · Jupyter Notebook

▲ 0

Nine-class scam detection with word and character features (macro F1 0.948 on an 18,261-record internal test), plus historical BERT and LLM experiments.

bert-fine-tuningcyber-scamsfraud-detectionllmsml

transactional-agent-ledger

Repo · 0 stars · Python

▲ 0

SQLite task ledger with verifier-gated claims and workspace snapshot rollback for tool-using agents.

ai-agentsllmsqlitetransactionsverification

trajectory-replay

Repo · 0 stars · Python

▲ 0

Deterministic tool-call replay and trajectory regression tests for tool-using LLM agents.

ai-agentsdeterministic-replayllmregression-testingtesting

odyssey

Repo · 0 stars · Python

▲ 0

Local-first terminal AI coding agent with 17 tools and Ollama inference.

ai-agentscoding-agentllm

ollamaterminal

About

Rock Wang is an AI developer based in Canberra, Australia, who works independently on software that applies machine learning and large language models. Rock is an IT student at the University of Adelaide, with skills in Python, PyTorch, Scikit-learn and web development. Public GitHub work includes an LLM-based web scraper built with Ollama and Streamlit, a YOLOv8s football tracker, and a nine-class scam detection model.