OpenEvolve is an open-source evolutionary coding agent that uses large language models (LLMs) to iteratively improve programs. It implements a MAP-Elites quality-diversity algorithm with island-based evolution, supporting multiple LLM backends (OpenAI, Claude Code, etc.) and a cascade evaluation pattern. The system accepts a user-provided initial program and an evaluator script, then repeatedly mutates the program via LLM-generated SEARCH/REPLACE diffs or full rewrites, evaluates the fitness, and maintains a diverse population across feature dimensions. The core architecture is a library with a CLI entry point (`openevolve-run`), a high-level API (`run_evolution`, `evolve_function`, `evolve_code`), and a controller that orchestrates the evolution loop, prompt sampling, LLM inference, parallel evaluation, and database storage. The repository includes 20+ diverse examples ranging from algorithm optimization (AlgoTune, TSP, circle packing) to mathematical discovery (Heilbronn, kissing number) and hardware-specific kernel tuning (MLX Metal, MLIR). The codebase is well-structured with extensive unit and integration tests, typed configuration, and a modular design that separates concerns (evaluator, LLM, database, prompt templates). It is actively maintained with frequent commits and responsive issue triage.
This repository is a sample application for the Google Home Local SDK, demonstrating how to create a local fulfillment for a smart light device. It consists of three main parts: the local home app (in the `app` directory) that discovers and controls the device using various network protocols (UDP, mDNS, UPnP for discovery; UDP, TCP, HTTP for control); a virtual device (in the `device` directory) that simulates a smart light using the Open Pixel Control (OPC) protocol and supports the same discovery and control protocols for testing; and a Cloud Function (in the `functions` directory) that acts as a placeholder for the cloud-to-cloud backend, handling account linking and returning placeholder responses for SYNC and QUERY intents (while deferring EXECUTE and QUERY to the local fulfillment). The local home app uses a strategy pattern to delegate discovery and execution handling to protocol-specific implementations. The virtual device encapsulates the OPC protocol logic in a reusable component that is independent of the underlying transport mechanism.
The iced-rs/awesome-iced repository is a curated list of projects, widgets, integrations, and resources related to the Iced GUI library for Rust. It serves as a discovery tool for the Iced ecosystem, helping users find examples of applications built with Iced, custom widgets, and integration libraries. The main artifact is the README.md file, which contains a structured list organized into sections such as "Projects Using Iced", "Custom Widgets", "Integrations", and "Resources". The repository includes a helper script, collect.py, which assists maintainers in adding new entries to the list. This script interacts with the user to gather information about a new project (such as its URL, description, and the Iced version it uses) and updates the README accordingly by inserting the new entry into the appropriate section. The script relies on specific HTML-style markers (<!-- CONTENT --> and <!-- END CONTENT -->) to identify the editable portion of the README and processes the content to maintain section-based organization. While the repository is primarily a documentation project, the collect.py script provides a lightweight CLI tool for maintenance. The codebase demonstrates basic markdown processing and user interaction but lacks modularity and reusable abstractions. The script is tightly coupled to the specific format of this README and includes hardcoded data, limiting its reuse potential without modification. The repository is actively maintained, as evidenced by recent commits and a continuous integration workflow that lints the README using awesome-lint and awesome_bot. Technically, the codebase shows low drift, with dependencies that are reasonably current (though the specified Node.js version is slightly outdated) and no apparent use of deprecated APIs. The project follows standard open-source practices, including a Contributor Covenant Code of Conduct and contribution guidelines.