Ultra-fast and customizable Python charts

Terminal dashboard for Docker monitoring across multiple hosts with Dozzle integration.

Apple Music ALAC / Dolby Atmos / AAC / MV Downloader

Fast LLM inference in pure C++

Tiered optimizer state allocation for memory-efficient MoE training. Cuts optimizer memory by 97.4%, outperforming AdamW/Muon/Lion while fitting a 6.78B MoE on a single 40GB GPU.

The Museum of Modern Art (MoMA) collection data

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

A LLM trained only on data from certain time periods to reduce modern bias

The National Gallery of Art Open Data Program

AI Design Patterns for Galleries, Libraries, Archives, and Museums

Official Repository of "LLM × DATA" Survey Paper

Replication package for: Automated, Unsupervised, and Auto-parameterized Inference of Data Patterns and Anomaly Detection

Real-time 3D visualisation of SAE feature activations inside GPT-2, token by token

[H] HyperspaceDB is a high-performance, vector database. It features 1-bit quantization, async replication, and native support for hierarchical datasets (Lorentz, Poincaré ball & Hybrid models).

Universal LLM API client — 163 providers, 14 native language bindings, powered by a Rust core

Browser-based audio-reactive visualizer inspired by Winamp and MilkDrop

Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, deduplication, and flexible export.

Automated music downloader and manager integrating Slskd and Beets.

A Subsonic API proxy server that transparently integrates multiple music streaming providers as sources.

Unmanic - Library Optimiser

Koito is a modern, themeable scrobbler that you can use with any program that scrobbles to a custom ListenBrainz URL

Zero-config visual debugging and auto-evaluation for LLM agents. Local-first tracing with a beautiful dashboard for OpenAI, LangChain, CrewAI, and more.

Visualize large time series data with plotly.py

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

data load tool (dlt) is an open source Python library that makes data loading easy 🛠️

[NeurIPS '25] Knowledge Graph Generation from Any Text