Search

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

Library to systematically track and evaluate LLM based applications.

A Python library for creating interactive web maps, optimized for LLM-assisted development.

abstract_ai is a Python module that serves as a bridge between your application and the OpenAI GPT-3 API. It provides a convenient interface for sending requests, managing responses, and controlling the behavior of the API calls. This module is highly customizable, allowing you to establish prompts, instructions, and response handling logic.

SkillViz - Visualize Claude Code skills as a graph

Suite of XFEL single particle imaging tools

AI-powered PR description generator using Claude

Lightweight LLM wrapper with usage tracking and label support

A Python library for inference-time scaling LLMs

A lightweight, provider-agnostic LLM client library

Interact with OpenAI's models from the comfort of your terminal.

Package for embedded storage systems

Local Strava analytics CLI with native support for LLM operations

A collection of CLI tools leveraging language models

Local Claude Code alternative powered by Ollama - zero API costs