-
Infactory
- San Francisco, California
- https://www.valentino.io/
- https://orcid.org/0000-0002-5279-4143
- https://scholar.google.com/citations?user=8UMmNtQAAAAJ&hl=en
Highlights
Stars
A curated collection of papers, code, datasets, and utilities for Video Anomaly Detection, updated every Friday.
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Linux virtual machines, with a focus on running containers
Micro-library of Node stream components with minimal dependencies for creating custom data processors oriented on processing huge CSV files while requiring a minimal memory footprint.
The micro-library of Node.js stream components for creating custom JSON processing pipelines with a minimal memory footprint. It can parse JSON files far exceeding available memory streaming indivi…
Implementation of the Surya Foundation Model and Downstream Tasks for Heliophysics
Git Based Memory Storage for Conversational AI Agent
Markdown to PDF command line app with support for stylesheets
Command line tool for the Mermaid library
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
OpenTofu lets you declaratively manage your cloud infrastructure.
Flink Agents is an Agentic AI framework based on Apache Flink
💾 Self-hosted online file converter. Supports 1000+ formats ⚙️
📷 RAW image processing for Python, a wrapper for libraw
Model Context Protocol (MCP) Server for Yamcs Mission Control System
OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team co…
Muon is an optimizer for hidden layers in neural networks
An open-source AI agent that brings the power of Gemini directly into your terminal.
Clone a voice in 5 seconds to generate arbitrary speech in real-time
us cached road graph, freeways, primary and secondary roads
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?