A super-easy way to record, search and compare 1000s of ML training runs.
Directory
Search the directory
Search published websites, apps and repositories.
Airweave is an open-source context retrieval layer for AI agents. It aims to provide relevant context to support agent functionalities. The project is hosted on GitHub by the airweave-ai organization.
AIToolbox is a toolbox of AI modules written in Swift, covering graphs and trees, support vector machines, neural networks, PCA, K-Means and genetic algorithms. The framework uses the Accelerate library to speed up computations, except the Linux package versions. A Swift Package is available for Mac and Linux, described as a sub-set of the full framework.
albumentations is a fast, flexible open-source image augmentation library. An academic paper describing the library is available. The project is no longer maintained, and AlbumentationsX is presented as its successor.
A curated GitHub list of generative AI companies, sorted by focus area and total fundraised amount. It covers companies with over $5MM raised as of August 2023, split into horizontal application, vertical application and enabling infrastructure categories.
Algebird is an open-source Scala library developed by Twitter that provides abstract algebra functionality for use in Scala software projects. It is hosted and maintained on the GitHub platform for collaborative development.
Alibi is an open-source project that provides algorithms for explaining machine learning models. Developed by SeldonIO and hosted on GitHub, it includes installation and usage documentation for pip and conda.
Alibi Detect is an open-source project that provides algorithms for outlier, adversarial, and drift detection. Developed by SeldonIO and hosted on GitHub, it includes installation and usage documentation for pip and conda.
Code for Data Science at Olin College, Spring 2014.
Alpaca is a project that provides code and documentation to train Stanford's Alpaca instruction-following LLaMA models and generate associated training data. It includes details on the data release, data generation process, and fine-tuning procedures.
alpaca-lora is a repository with code for reproducing the Stanford Alpaca results using low-rank adaptation (LoRA). It provides an Instruct model and training code that can be easily extended to the 13b, 30b and 65b models, along with a script for downloading and inference.
Open-source project that provides conversational AI for questions, tasks, and general assistance.
Open-source project that applies AI to data analysis, extraction, visualization, or business intelligence.
A GitHub repository compiling tools, ideas, prompt engineering resources, Colabs, models and helpers for prompt designers working with AI art and image synthesis. The list covers Dalle2, MidJourney, StableDiffusion and open source tools, and includes sections on commercial and free hosted tools, prompt engineering, post-processing and communities.
Ambrosia is a cross-platform command line tool written in Go for improving text datasets used in machine learning. It offers fast deduplication, filtering, length checking and whitespace trimming, plus an LLM-based filtering option called psort. It ships as a single binary with no dependencies and is pre-1.0 software.
amux is an open-source control plane for AI coding agents, hosted on GitHub by mixpeek. It enables management of parallel AI coding workers including Claude Code, Codex, and Gemini, with features such as a shared task board, atomic task assignment, scheduling, origin-stamped messaging, model switching, self-healing recovery, and access via a dashboard or mobile interface. It is MIT licensed and distributed as a single Rust binary.
ANEE is an experimental dynamic inference wrapper for pretrained Transformer language models, currently GPT-2. It exposes an energy_budget and performs early exit inside the model's forward pass rather than always running all layers. It adds per-token adaptive computation using a profiler and learned controller to skip redundant layers while keeping the KV-cache aligned.
anneal is a machine learning compiler written in Go. It is a from-scratch port of tinygrad, and its features include a graph-rewrite intermediate representation, autodiff implemented as a compiler pass, and a zero-CGO WebGPU backend.
Annoy is a C++ library with Python bindings for approximate nearest neighbor search. It creates large read-only file-based indexes that are mmapped into memory so many processes can share the same data. Supported distances include Euclidean, Manhattan, cosine, Hamming and dot product.
Anthropic's educational courses repository contains five courses covering the Claude SDK, prompt engineering, real world prompting, prompt evaluations and tool use. Suggested order begins with Anthropic API fundamentals. The repository was archived by its owner and is read-only. Courses often favor the lowest-cost model, Claude 3 Haiku, to keep API costs down.
Antigravity Link is a browser-based mobile companion for Google's Antigravity IDE that mirrors active AI chat sessions on a phone over the local network. It also exposes a local HTTP API and an MCP server so agents and external tools can drive Antigravity sessions programmatically.
Platform to programmatically author, schedule, and monitor workflows.
Apache MXNet is a deep learning framework mixing symbolic and imperative programming. It includes a dynamic dependency scheduler that parallelizes symbolic and imperative operations, with a graph optimization layer for symbolic execution. The repository was archived on Nov 17, 2023, and is read-only.
PyTorch Implementation of No Token Left Behind: Explainability-Aided Image Classification and Generation.