David vonThenen

All resources (slides, code, etc) for WeAreDevelopers World Congress EU 2026: From Vector Search to Better Understanding: How Hybrid RAG Improves Answers, Not Just Matches

All resources (slides, code, etc) for WeAreDevelopers World Congress EU 2026: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

All resources (slides, code, etc) for Devoxx Poland 2026: A Practical Guide to Training a Small Language Model: Tokenizers, Training, and Real-World Pitfalls

All resources (slides, code, etc) for 2026 TMLS: Why Your RAG Agent Is Confidently Wrong: Retrieval Choices That Actually Matter

All resources (slides, code, etc) for 2026 ODSC AI East (Tutorial): Less Compute, More Impact: How Model Quantization Fuels the Next Wave of Agentic AI

All resources (slides, code, etc) for WeAreDevelopers World Congress 2025: Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

Open Source Virtual Assistant Framework

All resources (slides, code, etc) for SCaLE 23x: A Practical Guide to Training a Small Language Model: Tokenizers, Training, and Real-World Pitfalls

All resources (slides, code, etc) for 2026 ODSC AI East (Tutorial): Train Your Own Small Language Model: A Hands-On Workshop in Model Design, Distillation, and Deployment

All resources (slides, code, etc) for 2025 ODSC Workshop: Adaptive RAG Systems with Knowledge Graphs: Building Reinforcement-Learning-Driven AI Applications

All resources (slides, code, etc) for Devoxx Greece 2026: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

About About All resources (slides, code, etc) for 2025 KubeCon NA: Your Kubernetes Playbook at Your Fingertips: Advanced Troubleshooting With MCP, RAG, and K8sgpt

About All resources (slides, code, etc) for 2025 ODSC West Workshop: Rethinking RAG: How MCP and Agent2Agent Will Transform the Future of Intelligent Search

All resources (slides, code, etc) for SCaLE 23x: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

All resources (slides, code, etc) for NVIDIA GTC 2025: Crack the AI Black Box: Practical Techniques for Explainable AI

Reference Implementation for a Symbl.ai Enterprise Application

All resources (slides, code, etc) for Devoxx France 2026: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

All resources (slides, code, etc) for Devoxx Greece 2026: Less Compute, More Impact: How Model Quantization Fuels the Next Wave of Agentic AI

Covers Implementation Guidelines and Sample Code for Document RAG Using OpenSearch

All resources (slides, code, etc) for SCaLE 22x: Demystifying Building Natural Language Processing ML Models and How to Leverage Them By Example

All resources (slides, code, etc) for API World 2025: API Security for the AI Era: Detecting and Preventing Adversarial Manipulation

All resources (slides, code, etc) for DevBcn 2025: Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

All resources (slides, code, etc) for Render ATL 2025: The Future of UI/UX: AI-Generated Interfaces Tailored Just-in-Time

All resources (slides, code, etc) for 2024 RTC Conference: Empower Your AI Journey: Hands-on Machine Learning with fastai for Graphics and NLP

All resources (slides, code, etc) for 2024 ODSC Conference: Building Multiple Natural Language Processing Models to Work In Concert Together

Port of Facebook's LLaMA model in C/C++

All resources (slides, code, etc) for ODSC West 2026: Cognitive Memory Architectures: Designing Continuity into Long-Running RAG and Agentic Soluitions

All resources (slides, code, etc) for API World 2026: Vertical APIs for Agentic AI: Routing the Right Context to the Right Expert

Articles for my Blog

All resources (slides, code, etc) for DevBcn 2026: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

All resources (slides, code, etc) for NDC Copenhagen 2026: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

All resources (slides, code, etc) for 2026 AI DevSummit: Less Compute, More Impact: How Model Quantization Fuels the Next Wave of Agentic AI

Covers Implementation Guidelines and Sample Code for Hybrid RAG Using Graph

Covers Implementation Guidelines and Sample Code for Hybrid RAG Using BM25

All resources (slides, code, etc) for RenderATL 2026: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

spaCy pipeline object for negating concepts in text

Spacy Food Name Entity Recognition (NER) model trained on StanfordNLP CRF recipe dataset

About All resources (slides, code, etc) for 2025 Devoxx Morocco: Rethinking RAG: How MCP and Agent2Agent Will Transform the Future of Intelligent Search

All resources (slides, code, etc) for 2026 Warsaw IT Days: Rethinking RAG: How MCP and Agent2Agent Will Transform the Future of Intelligent Search

No description.

KeePass-compatible password manager for iOS

Implementation of 17+ agentic architectures designed for practical use across different stages of AI system development.

All resources (slides, code, etc) for Agent Bounty 2026: Small Models, Big Impact: Practical SLMs for Retrieval, Reasoning, & Cost Control

Entity Type Recognition from Redacted Documents

No description.

Depix is a PoC for a technique to recover plaintext from pixelized screenshots.

A simple tool for reading in poorly redacted documents and reproducing their origional form

No description.

Early Access to NetApp Innovation Software | https://netapp.github.io/Innovation-Labs/

AI agents running research on single-GPU nanochat training automatically

A pytorch quantization backend for optimum

AI Audio Datasets (AI-ADS) 🎵, including Speech, Music, and Sound Effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio applications.

Covers Implementation Guidelines and Sample Implementation for Open Source and Enterprise Deployments

Easily serialize Data Classes to and from JSON

💫 Toolkit to help you get started with Spec-Driven Development

🙌 OpenHands: AI-Driven Development

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code support via MCP protocol. Ranked #1 in agent-based frameworks.

About All resources (slides, code, etc) for 2025 Tbilisi Data Science Meetup: Unlocking RAG's Potential: MCP and Multi-Agent Reinforcement Learning in Action

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

All resources (slides, code, etc) for AI Forward 2025: Trust, But Verify: A Practical Path to the 5% of AI Pilots That Make It To Production

Samples using the Agent2Agent (A2A) Protocol

An open protocol enabling communication and interoperability between opaque agentic applications.

Official Python SDK for the Agent2Agent (A2A) Protocol

All resources (slides, code, etc) for All Things Open 2025: TinyML Meets PyTorch: Deploying AI at the Edge with Python Using ExecuTorch

All resources (slides, code, etc) for CA Technology Summit 2025: Guardians of AI: Equipping Humans to Detect and Prevent Adversarial Manipulation

All resources (slides, code, etc) for Developer Week 2025: Navigating the Edge-Cloud Bridge: Building Resource Optimized IoT/Edge Assistants with LLMs

All resources (slides, code, etc) for Developer Week 2025: The Sound of Innovation: Why Voice Cloning Will Redefine Human-Computer Interaction

All resources (slides, code, etc) for 2024 RTC Conference: Enhancing Real-Time WebRTC Conversation Understanding Using ChatGPT

All resources (slides, code, etc) for 2024 RTC Conference: Edge Devices as Interactive Personal Assistants: Unleashing the Power of Generative AI Agents

All resources (slides, code, etc) for AI_Dev Europe 2025: Sarcastically Speaking: Unlocking Multi-modal Sentiment Analysis with NLP and Facial Expressions

No description.

An OBS plugin for removing background in portrait images (video), making it easy to replace the background when screen recording.

All resources (slides, code, etc) for SCaLE 21x: Voice-Activated AI Collaborators: A Hands-On Guide Using LLMs in IoT & Edge Devices

All resources (slides, code, etc) for 2024 RTC Conference: Training Machine Learning Classification Models for Creating Real-Time Data Points of Medical Conditions

All resources (slides, code, etc) for 2024 RTC Conference: Building Multiple Natural Language Processing Models to Work In Concert Together

No description.

All resources (slides, code, etc) for Devoxx UK 2025: The Rise of Agentic AI: Harnessing Open Source for Dynamic Decision-Making

All resources (slides, code, etc) for All Things Open AI 2025: Leveraging Knowledge Graphs for RAG: A Smarter Approach to Contextual AI Applications

All resources (slides, code, etc) for SCaLE 22x: Training Multi-Modal ML Classification Models for Real-Time Detection of Debilitating Disease

All resources (slides, code, etc) for Devoxx France 2025: Explaining the Unexplainable: Python Tools for AI Transparency using Captum

Multimodal Sarcasm Detection Dataset

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

https://hf.co/hexgrad/Kokoro-82M

TTS with kokoro and onnx runtime

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper

Chat-GPT Proxy and Opinionated Client

An Open-Source Package for Textual Adversarial Attack.

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

scikit-learn: machine learning in Python

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

DataLLM

Python interface to the LinkedIn API

Password manager app for Android

LuLu is the free macOS firewall

KeePassXC is a cross-platform community-driven port of the Windows application “Keepass Password Safe”.

Security, performance, marketing, and design tools — Jetpack is made by WordPress experts to make WP sites safer and faster, and help you grow your traffic.

OBS Studio - Free and open source software for live streaming and screen recording

OBS複数サイト同時配信プラグイン

A collection of corpora for named entity recognition (NER) and entity recognition tasks. These annotated datasets cover a variety of languages, domains and entity types.

Python library for audio and music analysis

A feature-rich command-line audio/video downloader

Visualize streams of multimodal data. Fast, easy to use, and simple to integrate. Built in Rust using egui.

Cross-platform, customizable ML solutions for live and streaming media.

The collection of pre-trained, state-of-the-art AI models for ailia SDK

This code uses the MediaPipe Pose model to detect human poses in a video file and writes the landmark coordinates to a CSV file.

Google Drive CLI Client

Some helpful utilities written in go

Package gorilla/schema fills a struct with form values.

Inference code for LLaMA models

Python bindings for llama.cpp

The official Python library for the OpenAI API

A Commander for modern Go CLI interactions

Examples and learnings for python

Verbose logging for Python's logging module

Read-only mirror of https://gitlab.gnome.org/GNOME/meld

An approximate string matching library for the Go programming language.

Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

No description.

No description.

Informal repo for various golang projects

Code and documentation to train Stanford's Alpaca models, and generate the data.

WebSocket reverse proxy handler for Go

Generic Go package designed to define a common interface to analyze and/or process audio data

Battle tested Wav decoder/encoder

Plugins for the Enterprise Conversation Insight Framework

A fast, well-tested and widely used WebSocket implementation for Go.

Library for RabbitMQ Messaging Manager

JSON pretty print for Golang.

A powerful HTTP router and URL matcher for building Go web servers with 🦍

Go bindings for the libmpg123 MP3 decoding library

♪ A low-level library to play sound on multiple platforms ♪

An MP3 decoder in pure Go

Go bindings for the PortAudio audio I/O library

obs-studio plugin to simulate a directshow webcam

A simple stream wrapper for arecord (Linux (including Raspbian)) and sox (Mac, Windows). Returns a Passthrough stream object so that stream control like pause(), resume(), pipe(), etc. are all available.

A WordPress plugin to allow you writing on GitHub (or Jekyll site).

:fishing_pole_and_fish: Webhook receiver for GitHub, Bitbucket, GitLab, Gogs

vSphere storage Container Storage Interface (CSI) plugin

2019 Hackday at Whitney High in Cerritos

Go library to handle cross platform speak