Repository Index

In order to make it easier to use the ComfyUI, I have made some optimizations and integrations to some commonly used nodes.

Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets.

Unsupervised Learning for Image Registration

• image-registration
• image-alignment
• machine-learning
• deep-learning

Free, open source blog writer for Claude Code. Researches current sources, writes answer-first posts for Google and AI answers, has an independent reviewer score each one out of 100 and ships only after five delivery gates. 32 skills, 30 /blog commands, 5 agents. Active development at AI-Marketing-Hub/claude-blog; public releases ship here.

• claude-code
• seo
• claude-code-skill
• ai

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.

• kv-cache
• llm-inference
• local-llm
• quantization

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

Infrastructure for evolutionary AI systems. GPU-accelerated, PyTorch-based optimization with an ecosystem of algorithm libraries, benchmarks, and tools.

• evolutionary-algorithms
• neuroevolution
• gpu-acceleration
• multi-objective-optimization

Python library for portfolio optimization, factor model construction, and risk management built on scikit-learn

• asset-allocation
• portfolio
• portfolio-optimization
• quantitative-finance

A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents

• meta-agents
• meta-optimization
• runtime-supervision
• workflow-automation

TorchCFM: a Conditional Flow Matching library

• continuous-normalizing-flows
• optimal-transport
• pytorch

A PyTorch Library for Multi-Task Learning

• multitask-learning
• multi-task-learning
• pytorch
• python

Details on how to get Binance public data

• binance
• historical-data
• market-data
• public

An object-oriented algebraic modeling language in Python for structured optimization problems.

• python
• optimization
• linear-programming
• mathematical-programming

Unmanic - Library Optimiser

• hacktoberfest

On the Variance of the Adaptive Learning Rate and Beyond

• optimizer
• adam
• adam-optimizer
• warmup

Automatic architecture search and hyperparameter optimization for PyTorch

• automl
• deep-learning
• tabular-data
• pytorch

A Linux program to handle GPU switching on Optimus laptops.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

• llm-agents
• llm-training
• reinforcement-learning
• large-language-models

AI agents running research on single-GPU nanochat training automatically adopted for MacOS

Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

• pytorch-implmention
• pytorch
• pytorch-tutorial
• proximal-policy-optimization