AI & ML

LLM-powered agent automating local software engineering workflows.

LLM-powered coding agent with LSP and MCP integration.

Graph-based retrieval framework for structured RAG reasoning.

Memory-efficient Python library for accelerated LLM training.

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

Async browser automation extracting web content for LLMs.

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

Minimal PyTorch implementation for training GPT models.

Python framework for autonomous multi-agent AI collaboration.

Extensible multi-LLM chat platform with RAG pipeline.

Reference implementations for LLM tool and data integration.

Multilingual OCR toolkit with document structure extraction.

Visual graph-based diffusion model workflow builder.

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

Self-hosted OCR document archive with ML classification.

LLM agent benchmarking framework for autonomous market trading.

Build Model Context Protocol servers with decorators.

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

Modular framework for chaining LLMs with external data.

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

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

Go-based CLI for local LLM inference and management.

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

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

Modular Python framework for building production AI agents.

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

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

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

LLM agent framework automating development in sandboxed containers.

High-performance inference engine for LLMs and VLMs.

Trillion-parameter MoE model with Muon-optimized training.

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

Multi-backend inference UI manager with embedded dependencies.

PyTorch framework for blind super-resolution using GANs.

Multi-LLM coding agent with interactive and automated modes.

Connect LLMs to external data via RAG workflows.

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

Vector database for embedding storage and semantic search.

Graphical package manager for ComfyUI custom nodes.

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

Unified API for pre-trained transformer models across frameworks.

Graph-based framework for streaming media ML pipelines.

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

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

Python framework for differentiable tensor computation and deep learning.

Fast BPE tokenizer for OpenAI language models.

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

Python framework for reactive data web applications.

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

Convert and deploy deep learning models across Intel hardware.

Cross-platform engine for optimized ONNX model execution.

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

Efficient approximate nearest neighbor search for billion-scale vectors.

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

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

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

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

Transformer-based TTS with voice cloning from reference audio.

LSTM-based OCR engine supporting 100+ languages.

Zero-shot object detection from text prompts.

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

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

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

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

PyTorch library for contrastive language-image pretraining.

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

Python library wrapping multiple face recognition deep learning models.

PyTorch library for training billion-parameter models efficiently.

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

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

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

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

PyTorch vision transformers pretrained on 142M unlabeled images.

PyTorch OCR library using CRAFT and CRNN models.

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

Block-based visual editor for autonomous AI agents.

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

Transformer-based promptable segmentation with zero-shot generalization.

Modular PyTorch framework for object detection research and deployment.

PyTorch anchor-free object detector with scalable model variants.

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

Memory-efficient PyTorch components for transformer architectures.

Node-based workflow interface for local Stable Diffusion deployment.

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

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

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

Dual-branch architecture for conditional diffusion model control.

PyTorch inference for Meta's Llama language models.

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

Foundation model for DNA sequence generation and scoring.

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

Standard API for reinforcement learning environment interfaces.

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

Efficient PyTorch architecture for image restoration tasks.

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

Cluster manager for multi-node PyTorch model training.

Unified transformer architecture for multi-task image segmentation.

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

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

AI tool that generates charts from natural language text descriptions.

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

PyTorch framework for blind face restoration using StyleGAN2 priors.

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

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

Text-to-image diffusion in compressed latent space.

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