I created a claude code deep researcher that seems to work better than the current deep research models

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

🛡️ ⚛️ A simple, scalable, and powerful architecture for building production ready React applications.

OpenZFS on Linux and FreeBSD

Allow use of Annotated function arguments in pytest tests for resolving fixtures

A clean, modern, wrapper for pytest.mark.parametrize

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

Elasticsearch gui - desktop app, browser extension, docker, self hosted

✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

Obsidian plugin which integrates your academic reference manager with the Obsidian editor. Search your references from within Obsidian and automatically create and reference literature notes for pa…

Examples from knowledge graphs tutorial paper

Playfair is a general purpose Open Source typeface family

Graph database optimized for fast Read at the cost of slow Writes. Implemented ontop of Neo4j and LevelDB.

A fast top-k completion based on a trie (see http://www.di.unipi.it/~ottavian/files/topk_completion_www13.pdf)

Generalized Language Modeling toolkit

LaTeX source of my bachelor thesis “Fast and Non-Approximative Language Model Prefixqueries for Word Prediction using Top-k Joining Techniques”.

My system configuration.

Incomplete game prototype developed during the 2.5-day “Global Game Jam” hackathon.

Slides and code of my talk “Introduction to Supervised Learning with TensorFlow”.

CLEARumor: ConvoLving ELMo against Rumors

Slides of my talk “Introduction to Advanced Neural Network Architectures for Natural Language Processing”.

Single-node production-ready setup of Elasticsearch and Kibana based on Docker.

Python stub files created during NASTY's development.

Independent useful utilities created during NASTY's development.

TODO

NASTY Advanced Search Tweet Yielder

Simulate StarCraft II army engagements and try to predict them.

A minimal Ubuntu base image modified for Docker-friendliness

Dokumentvorlagen für OpenOffice/Libreoffice ‒ templates for OpenOffice/LibreOffice