🎯
Highlights
- Pro
Lists (1)
Starred repositories
We aim to redefine Data Parallel libraries portabiliy, performance, programability and maintainability, by using C++ standard features, instead of creating new compilers.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…
Scalable data pre processing and curation toolkit for LLMs
library to quickly export and deploy entire inference pipelines
Real news, from elections to climate, explained for kids through friendly cartoon stories that are honest without being scary.
An image-to-world skillset for Claude.
Agent control plane for Physical AI on Nebius: infrastructure setup and management, simulation, robot policy training, synthetic data, and evaluation.
Scrub Data: A Framework for Reproducible Data Curation with AI Coding Agents
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
AI agents running research on 8000 single-GPU nanochat training automatically
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.
robertdvdk / hyperbolic-fully-connected
Forked from ricardo-chavez-torres/hyperbolic-fully-connectedKernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.
[ECCV 2026] Official code for DILLO, "Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models".
[ECCV 2026] Blind to Position, Biased in Language: Probing Mid-Layer Representational Bias in Vision-Language Encoders for Zero-Shot Language-Grounded Spatial Understanding
Probe the fractal convergence landscape of reasoning models
Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
A curated list of reinforcement learning with verifiable rewards (continually updated)
verified skills catalog for NVIDIA MedTech
Skills that guide AI coding agents to help you build product-specific AI evals.
Official implementation of Score-CAM in PyTorch
brevdev / nemoclaw-demos
Forked from slopp/nemoclaw-demosDemos of what to do after "hello world" works with NemoClaw installer.
NVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill. It can gather competition context, study public writeups and notebooks, reprod…