Detect and redact PII locally with SOTA performance

Extract structured data from local or remote LLM models

Main code chunks used for models in the publication "Exploring the Potential of Adaptive, Local Machine Learning (ML) in Comparison ton the Prediction Performance of Global Models: A Case Study from Bayer's Caco-2 Permeability Database"

LiAgent OS is a local-first AI agent OS for building a private personal assistant with governed autonomy across local models and hybrid cloud services. It brings conversation, tool use, multi-agent orchestration, task scheduling, heartbeat execution, human approval, and auditability into one long-lived loop.

Extracting complete webpage articles from a screen recording using local models

Zero-config Named Entity Recognition for drug discovery, chemistry, and biological sciences.

A streamlined interface for interacting with local Large Language Models (LLMs) using Streamlit. Features interactive chat, configurable model parameters, and more.

A comprehensive learning repository for Model Context Protocol (MCP) - from simple tools to complex agentic workflows using local Ollama models

A modular terminal AI agent capable of autonomous code execution, context propagation, and secure OS sandboxing using Gemini and local Ollama engines.

Vision-based avatar, reads Google News and extracts news by itself using only local models

Build a private AI assistant that runs locally with controlled autonomy, combining task management, tool use, and human oversight in one system.

Terminal-native agentic coding runtime for local & cloud models — Ollama, OpenRouter, Colab tunnels. No subscriptions, no limits.

Experimental macOS AI agent with SwiftUI, FastAPI, Ollama/local models, ChatGPT/Codex Bridge, MCP tools, Skills, diagnostics, and a safe Self Update Lab.

Gradio-Powered Handwriting (TrOCR + OpenVINO) to Video Generation (LTX + OpenVINO GenAI)