AI & ML

Multilingual OCR toolkit with document structure extraction.

Async browser automation extracting web content for LLMs.

Python framework for autonomous multi-agent AI collaboration.

Extensible multi-LLM chat platform with RAG pipeline.

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

High-performance inference engine for LLMs and VLMs.

Video2X enhances video quality using machine learning algorithms for upscaling, frame interpolation, and restoration with multiple backend support.

Reference implementations for LLM tool and data integration.

Graph-based retrieval framework for structured RAG reasoning.

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

Modular framework for chaining LLMs with external data.

AI-assisted Python framework for automated security testing.

Memory-efficient Python library for accelerated LLM training.

Graph-based framework for streaming media ML pipelines.

Build Model Context Protocol servers with decorators.

Modular Python framework for building production AI agents.

LLM agent benchmarking framework for autonomous market trading.

Multi-LLM coding agent with interactive and automated modes.

LLM-powered Python framework for automated penetration testing workflows.

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

Go-based CLI for local LLM inference and management.

Self-hosted OCR document archive with ML classification.

LLM agent framework automating development in sandboxed containers.

Minimal PyTorch implementation for training GPT models.

Lightweight, cross-platform speech recognition engine delivering real-time transcription with minimal dependencies and optimized inference performance.

Graphical package manager for ComfyUI custom nodes.

Unified API for pre-trained transformer models across frameworks.

Multi-backend inference UI manager with embedded dependencies.

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

Python framework for differentiable tensor computation and deep learning.

Cross-platform engine for optimized ONNX model execution.

Visual graph-based diffusion model workflow builder.

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

Feature-rich web UI for Stable Diffusion that enables AI image generation, editing, and enhancement through an intuitive browser interface.

Convert and deploy deep learning models across Intel hardware.

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

Self-contained distribution of llama.cpp with KoboldAI-compatible API server for running large language models locally on consumer hardware.

Block-based visual editor for autonomous AI agents.

PyTorch framework for blind super-resolution using GANs.

Fast BPE tokenizer for OpenAI language models.

Connect LLMs to external data via RAG workflows.

PyTorch vision transformers pretrained on 142M unlabeled images.

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

Transformer-based TTS with voice cloning from reference audio.

Efficient approximate nearest neighbor search for billion-scale vectors.

LSTM-based OCR engine supporting 100+ languages.

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

Foundation model for DNA sequence generation and scoring.

Transformer-based promptable segmentation with zero-shot generalization.

PyTorch library for training billion-parameter models efficiently.

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

Python framework for reactive data web applications.

Trillion-parameter MoE model with Muon-optimized training.

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

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

Python library wrapping multiple face recognition deep learning models.

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

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

Feature-rich Gradio-based UI for running and interacting with LLMs locally, supporting multiple model formats and extensions.

PyTorch library for contrastive language-image pretraining.

LLM-powered browser IDE with integrated WebContainers runtime.

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

Zero-shot object detection from text prompts.

Node-based workflow interface for local Stable Diffusion deployment.

Efficient PyTorch architecture for image restoration tasks.

Memory-efficient PyTorch components for transformer architectures.

PyTorch OCR library using CRAFT and CRNN models.

Unified transformer architecture for multi-task image segmentation.

PyTorch inference for Meta's Llama language models.

Modular PyTorch framework for object detection research and deployment.

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

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

Dual-branch architecture for conditional diffusion model control.

PyTorch framework for blind face restoration using StyleGAN2 priors.

Standard API for reinforcement learning environment interfaces.

PyTorch anchor-free object detector with scalable model variants.

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

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

Cluster manager for multi-node PyTorch model training.

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

Text-to-image diffusion in compressed latent space.