AI & ML

Tool that removes safety alignment from transformer language models using directional ablation without post-training.

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

Graph-based retrieval framework for structured RAG reasoning.

MCP server delivering version-specific library documentation to LLMs.

Transformer-based TTS with voice cloning from reference audio.

Python framework for autonomous multi-agent AI collaboration.

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

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

LLM-powered coding agent with LSP and MCP integration.

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

Modular framework for chaining LLMs with external data.

LLM-powered agent automating local software engineering workflows.

High-performance inference engine for LLMs and VLMs.

Extensible multi-LLM chat platform with RAG pipeline.

Reference implementations for LLM tool and data integration.

Minimal PyTorch implementation for training GPT models.

Fast document parser for RAG and AI workflows.

Visual graph-based diffusion model workflow builder.

Build Model Context Protocol servers with decorators.

Multilingual OCR toolkit with document structure extraction.

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

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

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

Async browser automation extracting web content for LLMs.

Foundation model for DNA sequence generation and scoring.

LLM agent framework automating development in sandboxed containers.

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

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

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

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

Modular Python framework for building production AI agents.

LLM agent benchmarking framework for autonomous market trading.

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

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

Go-based CLI for local LLM inference and management.

Connect LLMs to external data via RAG workflows.

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

Self-hosted OCR document archive with ML classification.

Vector database for embedding storage and semantic search.

Unified API for pre-trained transformer models across frameworks.

Multi-LLM coding agent with interactive and automated modes.

Graphical package manager for ComfyUI custom nodes.

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

Fast BPE tokenizer for OpenAI language models.

Graph-based framework for streaming media ML pipelines.

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

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

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

Python framework for differentiable tensor computation and deep learning.

PyTorch framework for blind super-resolution using GANs.

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

Multi-backend inference UI manager with embedded dependencies.

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

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

Trillion-parameter MoE model with Muon-optimized training.

Open-source AI assistant that builds a knowledge graph from emails and meetings to help with work tasks.

LSTM-based OCR engine supporting 100+ languages.

Convert and deploy deep learning models across Intel hardware.

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

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

Block-based visual editor for autonomous AI agents.

Cross-platform engine for optimized ONNX model execution.

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

PyTorch library for contrastive language-image pretraining.

Zero-shot object detection from text prompts.

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

PyTorch vision transformers pretrained on 142M unlabeled images.

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

Python framework for reactive data web applications.

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

Efficient approximate nearest neighbor search for billion-scale vectors.

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

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

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

Transformer-based promptable segmentation with zero-shot generalization.

PyTorch library for training billion-parameter models efficiently.

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

Python library wrapping multiple face recognition deep learning models.

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

Node-based workflow interface for local Stable Diffusion deployment.

PyTorch OCR library using CRAFT and CRNN models.

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

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

Modular PyTorch framework for object detection research and deployment.

Efficient PyTorch architecture for image restoration tasks.

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

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

Unified transformer architecture for multi-task image segmentation.

PyTorch anchor-free object detector with scalable model variants.

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

Memory-efficient PyTorch components for transformer architectures.

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

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

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

Cluster manager for multi-node PyTorch model training.

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

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

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

Dual-branch architecture for conditional diffusion model control.

PyTorch inference for Meta's Llama language models.

Standard API for reinforcement learning environment interfaces.

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

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

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

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

PyTorch framework for blind face restoration using StyleGAN2 priors.

Text-to-image diffusion in compressed latent space.

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

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

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

AI tool that generates charts from natural language text descriptions.