Persistent semantic memory for Claude Cowork. Extracts beliefs, insights, and research from every session into a local database Claude queries in real time. Nightly research scouting, automated belief verification, and MCP-based retrieval. Built for Cowork — not Claude Code.
AI Business Analyst app built with Streamlit, Plotly, and Llama3 for smart data analysis and automated visualizations.
Generate graphs of conceptual graphs of your repository using cloud LLMs or Ollama. Available now on VSCode Extension Marketplace
Auto-generated companion guides (book-chapter style markdown) for Karpathy's Neural Networks: Zero to Hero playlist — 19h of source video into 10 guides in 3h on a laptop, fully local, $0 cloud spend.
Windows-first local AI coding toolkit with multi-agent workflows, Ollama automation, and dashboard utilities.
A lightweight, fully‑local AI coding assistant for VS Code, built for small local LLMs and maximum privacy.
Decky Loader plugin to let Ollama run in game-mode.
RAG-based agricultural Q&A system using FastAPI, Qdrant vector database, and Ollama LLM for semantic document retrieval and response generation from PDF knowledge bases.
W.A.R.V.I.S. — Forensic IR agent (Go orchestrator + Python MCP + Gemma 4). SANS FIND EVIL hackathon entry by WoopsFactory.
Telegram-driven multi-agent AI office kernel (Sanitized version)
Normal chat, Rag con pdf y consultas con pgvector
A small experiment with docker, dev containers and a LLM. An experiment, but quiet useful. Ceridwen is a personal assistant that can be run on the GPU.
This project is a Blog Generator web application built using Streamlit and LangChain The app uses the Ollama LLM (Large Language Model) to generate professional, informative blogs based on the user's input.
Add a description, image, and links to the ollama topic page so that developers can more easily learn about it.
To associate your repository with the ollama topic, visit your repo's landing page and select "manage topics."