AI & ML

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

Personal AI assistant that runs on your own devices and connects to messaging platforms like WhatsApp, Telegram, and Slack.

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

Graph-based retrieval framework for structured RAG reasoning.

Memory-efficient Python library for accelerated LLM training.

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

LLM agent benchmarking framework for autonomous market trading.

MCP server delivering version-specific library documentation to LLMs.

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

Self-hosted OCR document archive with ML classification.

Extensible multi-LLM chat platform with RAG pipeline.

Python framework for autonomous multi-agent AI collaboration.

Multilingual OCR toolkit with document structure extraction.

LLM-powered coding agent with LSP and MCP integration.

High-performance inference engine for LLMs and VLMs.

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

Modular framework for chaining LLMs with external data.

Fast document parser for RAG and AI workflows.

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

Reference implementations for LLM tool and data integration.

Async browser automation extracting web content for LLMs.

LLM agent framework automating development in sandboxed containers.

Visual graph-based diffusion model workflow builder.

Transformer-based TTS with voice cloning from reference audio.

Go-based CLI for local LLM inference and management.

Minimal PyTorch implementation for training GPT models.

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

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

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

Build Model Context Protocol servers with decorators.

Vector database for embedding storage and semantic search.

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

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

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

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

Modular Python framework for building production AI agents.

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

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

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

Multi-LLM coding agent with interactive and automated modes.

Connect LLMs to external data via RAG workflows.

Graph-based framework for streaming media ML pipelines.

Multi-backend inference UI manager with embedded dependencies.

Graphical package manager for ComfyUI custom nodes.

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

Unified API for pre-trained transformer models across frameworks.

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

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

Fast BPE tokenizer for OpenAI language models.

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

Python framework for differentiable tensor computation and deep learning.

Cross-platform engine for optimized ONNX model execution.

Convert and deploy deep learning models across Intel hardware.

PyTorch framework for blind super-resolution using GANs.

LSTM-based OCR engine supporting 100+ languages.

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

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

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

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

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

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

Block-based visual editor for autonomous AI agents.

Foundation model for DNA sequence generation and scoring.

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

Efficient approximate nearest neighbor search for billion-scale vectors.

Zero-shot object detection from text prompts.

PyTorch library for contrastive language-image pretraining.

PyTorch vision transformers pretrained on 142M unlabeled images.

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

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

Python framework for reactive data web applications.

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

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

PyTorch library for training billion-parameter models efficiently.

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

Efficient PyTorch architecture for image restoration tasks.

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

PyTorch OCR library using CRAFT and CRNN models.

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

Trillion-parameter MoE model with Muon-optimized training.

Python library wrapping multiple face recognition deep learning models.

Cluster manager for multi-node PyTorch model training.

Transformer-based promptable segmentation with zero-shot generalization.

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

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

Unified transformer architecture for multi-task image segmentation.

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

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

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

Node-based workflow interface for local Stable Diffusion deployment.

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

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

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

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

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

Modular PyTorch framework for object detection research and deployment.

PyTorch inference for Meta's Llama language models.

Memory-efficient PyTorch components for transformer architectures.

PyTorch anchor-free object detector with scalable model variants.

Dual-branch architecture for conditional diffusion model control.

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

Standard API for reinforcement learning environment interfaces.

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

PyTorch framework for blind face restoration using StyleGAN2 priors.

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

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

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

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

Text-to-image diffusion in compressed latent space.

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.