Directory
Published directory entries matching your search.
ImageBind is a PyTorch implementation with pretrained models from FAIR, Meta AI. It learns a joint embedding across six modalities: images, text, audio, depth, thermal, and IMU data. The release includes code and model weights under the CC-BY-NC 4.0 license.
Foundational Models for State-of-the-Art Speech and Text Translation.
fselect is a command-line tool for finding files with SQL-like queries. It supports complex queries, subqueries across directories, aggregate and other functions, searching within archives, and image, EXIF and audio metadata searches. Output can be formatted as CSV, JSON and other formats, and an interactive mode is available.
Garage is a toolkit for developing and evaluating reinforcement learning algorithms, with an accompanying library of implementations built using it. The toolkit offers modular tools including composable neural network models, replay buffers, high-performance samplers, an experiment definition interface, reproducibility tools, logging including TensorBoard, checkpointing and resuming, and environment interfaces.
Research-Digest is a Flask application that scrapes arXiv weekly for newly published papers in fields including computer vision and machine learning, then offers a summarization feature so users can grasp key points. Summarization uses a T5 model finetuned on scientific articles, with weights and tokenizers stored locally.
Pix2pix implementation in keras. The repository provides code to download the facades dataset, install requirements, and start training, and it references the original Image-to-Image Translation with Conditional Adversarial Networks paper.
imutils is a Python package of convenience functions that make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV. It works with Python 2.7 and Python 3 and is pip-installable given NumPy, SciPy, Matplotlib and OpenCV. A find_function method searches function names across modules.
A command-line tool for searching the App Store for iOS, iPadOS, tvOS, watchOS, visionOS and macOS apps and downloading .ipa or macOS .pkg app packages. It requires a supported operating system and an Apple Account already configured to use the App Store, and it runs in interactive mode by default.
Autograd and XLA for high-performance machine learning research.
A project to make it easier to use large external knowledge bases with LLMs.
Jieba is a Chinese text segmentation module for Python. It supports four segmentation modes, including precise, full, search-engine and a paddle mode using PaddlePaddle, and offers keyword extraction based on TF-IDF and TextRank.
LLocalSearch is a fully locally running search aggregator that uses LLM agents to answer user questions. It uses a chain of LLMs to find answers, displays agent progress and final results, and does not require OpenAI or Google API keys to operate.
MLX is an array framework developed for use on Apple silicon hardware. The project includes example code, quickstart guides, installation instructions, and contribution guidelines. It is hosted as an open source repository on GitHub.
Neodisk is a read-only disk space visualizer for macOS and Linux with treemap and sunburst views built on the NeodiskKit scan engine. It is read-only by design and never modifies or deletes files, offering Reveal in Finder, Open and Copy Path as its only file actions. Features include largest-file search, file type statistics, an age heatmap and a duplicate finder.
Numla is a minimal browser-based calculator notepad for quick everyday calculations, including arithmetic, currency conversions, percentages, and unit conversions. It operates entirely locally with no user accounts or tracking, supports offline use, and includes features such as tabbed notes, instant note search, a Time Machine version history tool, focus mode, theme customization, and .txt file export. It is distributed as a progressive web app.
OxiCloud is a self-hosted cloud storage project written in Rust for files, photos, calendars and contacts. It includes built-in WebDAV, CalDAV and CardDAV protocols, plus files, previews, sharing, trash, search, favorites and recent items. Deployment options include Docker Compose, a Helm chart and a Nix module.
Planify is a task manager designed for GNOME with Todoist, Nextcloud and CalDAV support. It offers drag and drop organization, calendar integration, flexible reminders, dark mode and quick search, and can sync with Todoist accounts or self-hosted Nextcloud while working offline.
Ask questions to your documents without an internet connection, using the power of LLMs.
PromptPapers is a public GitHub repository that curates a list of must-read academic papers on prompt-based tuning for pre-trained language models. The list is primarily maintained by Ning Ding and Shengding Hu, and the repository also references the associated open-source prompt-learning toolkit OpenPrompt. It organizes papers into categorized sections and accepts community pull requests to update paper information.
Toolbox of models, callbacks, and datasets for AI/ML researchers.
Dump all your files and chat with it using your generative AI second brain using LLMs & embeddings.
Dump all your files and chat with it using your generative AI second brain using LLMs & embeddings.
Supermemory is a memory and context engine for AI that learns from conversations, extracts facts, builds user profiles, and delivers context. It includes hybrid search combining RAG and memory, connectors, and multi-modal extractors. It can be run fully locally.
TextGen is an open-source desktop app for local LLMs, with text, vision, tool-calling and web search, plus a UI and API. It supports multiple backends including llama.cpp, Transformers, ExLlamaV3 and TensorRT-LLM, and an OpenAI/Anthropic-compatible API. It also offers LoRA training and image generation. Portable builds are provided for Linux, Windows and macOS.
