Evidently An open-source framework to evaluate, test and monitor ML and LLM-powered systems. Documentation Evidently is an open-source Python library to evaluate, test, and monitor ML and LLM systems—from experiments to production.

AI-programmable CMS for enterprises hosting on AWS Open-source content platform. Built as a TypeScript framework you extend with code, not a closed product you configure through a UI.

⚠️ Warning: Not Actively Maintained This repository is no longer actively maintained. For a more up-to-date alternative, please visit the LitGPT project: https://github.com/Lightning-AI/litgpt , which serves as the successor to this repository.

Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy.

DoubleEntry is an accounting system based on the principles of a Double-entry Bookkeeping system. While this gem acts like a double-entry bookkeeping system, as it creates two entries in the database for each transfer, it does not enforce accounting rules, other than optionally ensuring a balance is positive, and through an allowlist of approved transfers.

If you are a musician looking to use Surge XT, please download the appropriate binary from our website. Surge Synth Team makes regular releases for all supported platforms.

A Rust, Python and gRPC server for text generation inference. Used in production at Hugging Face to power Hugging Chat, the Inference API and Inference Endpoints.

Welcome to the Cleaned Alpaca Dataset repository! This repository hosts a cleaned and curated version of a dataset used to train the Alpaca LLM (Large Language Model).

General-purpose browser automation as a Claude Skill A Claude Skill that enables Claude to write and execute any Playwright automation on-the-fly - from simple page tests to complex multi-step flows. Packaged as a Claude Code Plugin for easy installation and distribution.

![Platform][platformimage] [![License][licenseimage]][licenselink] [![versionicon]][versionlink] ![QQ Group][qqgroupimage] Translations: 简体中文 Sketch is an image loading library specially designed for Compose Multiplatform and Android View. It has the following features: compose resource, android asset/content/resource, etc.

In a nutshell, we aim to generate polyphonic music of multiple tracks (instruments). The proposed models are able to generate music either from scratch, or by accompanying a track given a priori by the user.

The WatermarkLogitsProcessor is designed to be readily compatible with any model that supports the generate API. Any model that can be constructed using the AutoModelForCausalLM or AutoModelForSeq2SeqLM factories should be compatible.

By Nikhil Mittal Founder of Altered Security - Hands-on red team and enterprise security training! Import all the scripts in the current PowerShell session (PowerShell v3 onwards).

Naive linter for English prose for developers who can't write good and wanna learn to do other stuff good too. Important: Do not use this tool to be a jerk to other people about their writing.

AI-powered penetration testing assistant using local LLM on linux (Parrot OS) --- Metatron is a CLI-based AI penetration testing assistant that runs entirely on your local machine — no cloud, no API keys, no subscriptions. It runs real recon tools (nmap, whois, whatweb, curl, dig, nikto), feeds all results to a locally running AI model, and the AI analyzes the target, identifies vulnerabilities, suggests exploits, and recommends fixes.

Getting Started • Documentation • Example Apps • Issues ObjectBox Java is a lightweight yet powerful on-device database & vector database designed specifically for Java and Kotlin applications. Store and manage data effortlessly in your Android or JVM Linux, macOS or Windows app with ObjectBox.

LBRYcrd uses a blockchain similar to bitcoin's to implement an index and payment system for content on the LBRY network. In addition to the libraries used by bitcoin, LBRYcrd also uses icu4c.

|--------------| |-------------|--------| |-------|-------------| Create a .env file in the project root: Start Redis locally (install if not already installed): 1. Start Flower dashboard for monitoring (optional, in a new terminal): 1.

This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference.

Prompt with an image/video → Get runnable vision code → Build Visual AI App in minutes Discord · Architecture · YouTube VisionAgent is the Visual AI pilot from LandingAI. Give it a prompt and an image, and it automatically picks the right vision models and outputs ready‑to‑run code—letting you build vision‑enabled apps in minutes.