olama

An Obsidian plugin that keeps track of your novel; where every character is and what they know, chapter by chapter. Bring your own AI.

Autonomous flight simulator for AI agents: co-evolutionary adversarial red-teaming with 3D MAP-Elites quality-diversity. Discovers zero-days in LLM agents before production. MCP-native.

AST-based coding, structured edits instead of raw diffs, sandboxed by default.

FraudSentinel is an AI-powered multi-modal fraud detection platform designed to identify modern cyber threats across emails, credentials, attachments, websites, voice, prompts, and AI agents. It combines machine learning, transformer models, audio analysis, URL and domain forensics, sret scanning, and sandboxed behavioral detection to generate.

Advanced AI Assistant powered by Python (Backend) and React Three Fiber (Frontend). Includes Object Detection (YOLOv8), Lip-Synced 3D Avatar (WebSockets), Neural TTS, and System Automation

Hands-on exploration of prompt injection using Lakera's Gandalf game, plus my own Spring Boot chatbot demonstrating escalating LLM defenses (system prompts, input filters, output filters). Part of my AI Security Engineering learning journey.

I built a GPT which you can customise using a prompt (no code required).

AI Presentation Creator Pro — Generate academic PowerPoint presentations using a local LLM (GGUF) with optional PDF-enhanced RAG for highly accurate slide content. Fully offline and privacy-friendly.

A code-base index example that you can run locally for your interp interpreter.

Микросервисная ИИ-платформа для конфиденциального анализа корпоративных документов и CSV-таблиц на базе Laravel 13, Python (Pandas) и локальной нейросети Qwen 2.5 (Ollama) без интернета.

Contract-first Python utilities for building and testing AI-powered applications across providers

A benchmark of open-source language models (Hugging Face and Ollama) on a CPU-only laptop, built around one business decision.

A portfolio of five standalone AI engineering systems covering agentic workflows, hybrid RAG, MCP-based access control, secure self-hosted LLMs, AI web generation, and native Windows EXE building using FastAPI, Ollama, Docker, and GitHub Actions.

This project demonstrates how to use the local Ollama API to interact with an AI model. It includes instructions to install the necessary tools, download a model, and run a sample chat script.

SuperCore: O seu novo ChatBot de IA local!

Full-stack AI chatbot with conversation memory — FastAPI + Next.js + Ollama

Build a grounded AI chatbot from your TXT and Markdown documents, test it in a dashboard, and embed it on your website.

Playground for LLM deepseek

An app for creating LLM-chatbot via system prompts, RAG resources and external APIs.