#machine-learning

Опис репозиторію не опубліковано.

Training API and CLI

TonY is a framework to natively run deep learning frameworks on Apache Hadoop.

Visual storytelling for deep learning training runs.

Production-grade Python toolkit for credit risk modeling — scorecards, LR, LightGBM/XGBoost, WOE/IV, PSI, KS, SHAP. Source-protected wheels via Cython.

High performance gradient boosting for Ruby

High-performance, multi-provider LLM SDK for Go. Unified access to OpenAI, Anthropic, Gemini, Ollama, OpenRouter with adaptive rate limiting and concurrency control.

Impress your boss with interactive Decision Tree visualization

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

Simple python interface for the OpenProtein.AI REST API.

Python tools for text to speech (TTS), speech to text (STT), and speech to speech (STS) powered by MLX

A framework for giving any AI agent persistent, browser-trainable SSM memory — Mamba models, swappable LLM bridges, and online distillation. The hippocampus behind BuilderForce.ai.

High performance gradient boosting for Ruby

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

A Spring Boot web app that buys and sells cryptocurrencies from API data sources. Its quick trading and other features allow users to leverage computer power to outperform the market.

Predicting time-consuming CQL queries in language corpora

AI-native tensor format (.ptt) for protein-structure ML. Convert a structure or sequence once; load backbone, MSA, ESM embeddings, sparse pair features, and ligands with zero parsing. Feeds AlphaFold/Boltz (Boltz-2 verified). Zarr-backed, lossless, PyTorch/JAX-ready, streams from S3/GCS.

Fetch The Gradient AI research publication posts and listings from the terminal

A command-line tool to extract plain text from Wikipedia dumps with category and section filtering

Save pytrees efficiently in hdf5 files.

Parallel Barnes-Hut t-SNE implementation written in Rust.

Crystallize is a lightweight Python framework for rigorous, reproducible data science experiments. Define modular pipelines, apply treatments as experimental variations, and verify hypotheses with statistical tests, all with built-in caching, immutability, and parallelism for trustworthy, efficient results.

Elixir bindings for 🤗 Tokenizers

Google Gemini MCP - Use Google's visual, video and chat capabilities in your AI Assistant. Uses MCP Apps to preview created images, landing pages, SVGs and video

A nvImageCodec library of GPU- and CPU- accelerated codecs featuring a unified interface

Ruby wrapper for the Weaviate vector search database API

High-performance interpretable ML classifier using High Utility Gain patterns (IEEE Access 2024). C++ accelerated, scikit-learn compatible, with EBM-style explanations, adaptive binning, pattern pruning, and deployment tooling for regulated domains.

Neugo is a Neural network framework developed in and for go