AI & ML

OpenAI's command-line coding assistant that runs locally with ChatGPT integration for terminal use.

MCP server delivering version-specific library documentation to LLMs.

CLI and browser extension that generates summaries from URLs, files, videos, podcasts, and other media sources.

Fast document parser for RAG and AI workflows.

LLM-powered agent automating local software engineering workflows.

Open source implementation of Google's NotebookLM that runs locally with document processing and podcast generation.

Async browser automation extracting web content for LLMs.

System for real-time human pose tracking using WiFi Channel State Information without cameras or wearables.

Fast, memory-efficient LLM inference engine with PagedAttention for production deployments at scale.

LLM-powered coding agent with LSP and MCP integration.

Quantized LLM inference with hardware-accelerated CPU/GPU backends.

Python framework for autonomous multi-agent AI collaboration.

Reference implementations for LLM tool and data integration.

Memory-efficient Python library for accelerated LLM training.

Build Model Context Protocol servers with decorators.

Extensible multi-LLM chat platform with RAG pipeline.

Graph-based retrieval framework for structured RAG reasoning.

Minimal PyTorch implementation for training GPT models.

Modular Python framework for building production AI agents.

Library for training large transformer models with distributed computing and GPU-optimized building blocks.

Modular framework for chaining LLMs with external data.

Self-hosted OCR document archive with ML classification.

High-performance inference engine for LLMs and VLMs.

LLM agent benchmarking framework for autonomous market trading.

Guides, papers, and resources for prompt engineering, RAG, and AI agents.

Open-source Next.js template for AI chatbots with auth, persistence, and multi-provider support.

Go-based CLI for local LLM inference and management.

Web UI for Stable Diffusion enabling AI image generation and editing in browser.

Multilingual OCR toolkit with document structure extraction.

Lightweight C++ port of OpenAI Whisper for cross-platform speech recognition.

PyTorch library for robot imitation learning and sim-to-real transfer.

Open-source diffusion framework for multi-modal video generation.

PyTorch library for YOLO-based real-time computer vision.

Vector database for embedding storage and semantic search.

Speech recognition system supporting multilingual transcription, translation, and language ID.

AI-powered slide generator with multi-model integration and themes.

Unified framework for scaling AI and Python applications from laptops to clusters with distributed runtime.

Graphical package manager for ComfyUI custom nodes.

Web demo showcasing OpenAI's Speech API text-to-speech capabilities with an interactive Next.js interface.

ML-powered video upscaling, frame interpolation, and restoration with multiple backend support.

Multi-backend inference UI manager with embedded dependencies.

Unified API for pre-trained transformer models across frameworks.

Type-safe Python client for OpenAI's REST API.

Python framework for differentiable tensor computation and deep learning.

Connect LLMs to external data via RAG workflows.

AI tool that generates React applications from website clones or user descriptions.

Lazy-evaluated NumPy-like arrays optimized for Apple silicon.

Transformer-based TTS with voice cloning from reference audio.

Fast BPE tokenizer for OpenAI language models.

Self-contained llama.cpp distribution with KoboldAI API for running LLMs on consumer hardware.

CLIP-conditioned latent diffusion model for text-to-image synthesis.

Convert and deploy deep learning models across Intel hardware.

Multi-LLM coding agent with interactive and automated modes.

Python framework for reactive data web applications.

Node-based workflow interface for local Stable Diffusion deployment.

Cross-platform engine for optimized ONNX model execution.

Diffusion transformer models for text and image-to-video generation.

Trillion-parameter MoE model with Muon-optimized training.

LSTM-based OCR engine supporting 100+ languages.

Graph-based framework for streaming media ML pipelines.

Alibaba Cloud's pretrained LLMs supporting Chinese/English with up to 32K context length.

Define-by-run Python framework for automated hyperparameter tuning.

PyTorch toolkit for deep learning text-to-speech synthesis.

Python library wrapping multiple face recognition deep learning models.

Efficient approximate nearest neighbor search for billion-scale vectors.

CUDA C++ templates and Python DSLs for high-performance matrix multiplication on GPUs.

Block-based visual editor for autonomous AI agents.

Curated collection of images and prompts from Google's Gemini-2.5-Flash-Image model with model comparisons.

PyTorch framework for blind super-resolution using GANs.

Domain-specific language and compiler for writing GPU deep learning primitives with higher productivity than CUDA.

Cross-platform C++ library for real-time computer vision algorithms.

PyTorch library for contrastive language-image pretraining.

Multi-object tracker associating low-confidence detections across frames.

Multimodal zero-shot classifier using contrastive vision-language learning.

Transformer-based promptable segmentation with zero-shot generalization.

Code language models (1B-33B parameters) supporting completion and infilling across 80+ languages.

Zero-shot object detection from text prompts.

Foundation model for DNA sequence generation and scoring.

PyTorch OCR library using CRAFT and CRNN models.

10B parameter diffusion model for text-to-video generation using Asymmetric Diffusion Transformer.

PyTorch vision transformers pretrained on 142M unlabeled images.

Efficient PyTorch architecture for image restoration tasks.

Open source implementation of X's recommendation algorithm for timeline and notification ranking.

Gradio-based UI for running LLMs locally with multiple model format and extension support.

PyTorch library for training billion-parameter models efficiently.

ML experiment tracking platform with logging, visualization, and model versioning.

Unified API platform connecting AI agents to 150+ integrations with auth and tool building.

Real-time object detection with cross-platform deployment support.

Memory-efficient PyTorch components for transformer architectures.

Dual-branch architecture for conditional diffusion model control.

PyTorch inference for Meta's Llama language models.

PyTorch anchor-free object detector with scalable model variants.

Multi-person 135-keypoint anatomical detection in C++.

Unified transformer architecture for multi-task image segmentation.

Standard API for reinforcement learning environment interfaces.

Torch implementation for paired image-to-image translation using cGANs.

Modular PyTorch framework for object detection research and deployment.

Transformer-based face restoration using vector-quantized codebook lookup.

PyTorch single-stage detector with bag-of-freebies training optimizations.

Cluster manager for multi-node PyTorch model training.

Google Brain research project using ML to generate music, images, and creative content with TensorFlow.

Research project that fine-tunes LLaMA models to follow instructions using self-generated training data.

Community platform for sharing Stable Diffusion models, embeddings, and AI generation assets.

Official PyTorch package implementing the discrete VAE component for image tokenization used in OpenAI's DALL-E system.

PyTorch framework for blind face restoration using StyleGAN2 priors.

Visual graph-based diffusion model workflow builder.

LLM agent framework automating development in sandboxed containers.

Text-to-image diffusion in compressed latent space.

Parameter-efficient fine-tuning framework for 100+ LLMs.

AI tool that generates charts from natural language text descriptions.

PyTorch implementation for animating portraits by transferring expressions from driving videos.