RecursiveMAS — Extensions and Reflections

Offical Implementation for "Recursive Multi-Agent Systems"

The agent that re-shapes the Space

Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

A cross-platform GUI for webcam-based spectrometers.

Python Thermal Camera Library

⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

Run MCP stdio servers over SSE and SSE over stdio. AI gateway.

Turn any Excel spreadsheet into LLM consumable JSON

Docling with Ollama - RAG on Local Files with Local Models

a unified framework for modeling chemically reactive systems

A Geochemical Reactive Transport Solver for Acidizing: Coupling OpenFOAM and Reaktoro

OpenSceneSense Ollama is a Python library that harnesses AI for advanced local video analysis, offering customizable frame and audio insights for dynamic applications in media, education, and conte…

Python version of the amazing Reaction Mechanism Generator (RMG).

Official implementation of the SIGGRAPH 2024 paper "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets"

Silero Models: pre-trained text-to-speech models made embarrassingly simple

Vane is an AI-powered answering engine.

a bash/yad script to manage proprietary and open source nvidia driver

DSPy program/pipeline inspector widget for Jupyter/VSCode Notebooks.

A machine learning software for extracting information from scholarly documents

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Linux​ based GDDR6/GDDR6X VRAM temperature reader for NVIDIA RTX 3000/4000 series GPUs.

Prometheus exporter for Linux​ based GDDR6/GDDR6X VRAM and GPU Core Hot spot temperature reader for NVIDIA RTX 3000/4000 series GPUs.

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Unified framework for building enterprise RAG pipelines with small, specialized models