How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
Promptify is a suite of tools designed for model evaluation, prompt management, token cost tracking, structured extraction, and unified API gateway access. It provides a standardized interface to manage requests and responses across multiple large language model providers. The project features a prompt management platform for engineering and versioning prompts with structured output validation. It includes a dedicated evaluation framework to measure model performance using precision, recall, and f1 scores against labeled datasets, alongside a token cost tracker to monitor the financial expens
Rivet is a visual LLM workflow designer and AI agent orchestration engine. It serves as a development environment for building retrieval augmented generation pipelines and a TypeScript library for embedding visual AI graphs and prompt logic into JavaScript applications. The system differentiates itself through a node-based editor that maps data flow between language models, vector databases, and external APIs. It provides specialized tools for prompt engineering, including interfaces for iterative prompt refinement and A/B testing to improve model response quality. The platform covers a broa
This repository catalogs the system prompts used by Claude Code, organizing them into browsable categories with token-count estimates for each prompt. It functions as both a prompt library browser and a revision tracker, surfacing the size and complexity of individual prompts to support auditing and prompt engineering decisions. The project records prompt revisions by parsing git diffs between versions, capturing additions, removals, and token-count changes in a structured changelog. Token counts are approximated from character length using a fixed heuristic ratio, avoiding the need for API c
This project is a comprehensive technical interview study resource designed to help developers prepare for engineering job assessments. It functions as a structured guide that curates essential computer science fundamentals, web development standards, and programming language concepts into a format optimized for professional evaluation. The repository distinguishes itself by providing strategic guidance on architectural decision-making and professional communication. Beyond simple question-and-answer pairs, it offers frameworks for articulating experience during interviews and suggests profes
Toolkit for creating, sharing and using natural language prompts.
The main features of bigscience-workshop/promptsource are: Annotation and Evaluation, Instruction Tuning, Prompt Engineering Tools, Prompt Optimization Frameworks.
Open-source alternatives to bigscience-workshop/promptsource include: promptslab/promptify — Promptify is a suite of tools designed for model evaluation, prompt management, token cost tracking, structured… ironclad/rivet — Rivet is a visual LLM workflow designer and AI agent orchestration engine. It serves as a development environment for… piebald-ai/claude-code-system-prompts — This repository catalogs the system prompts used by Claude Code, organizing them into browsable categories with… junh0328/prepare_frontend_interview — This project is a comprehensive technical interview study resource designed to help developers prepare for engineering… facebookresearch/metaseq — Metaseq is a transformer sequence modeling toolkit designed for training, fine-tuning, and deploying… bigscience-workshop/xmtf — This repository provides an overview of all components used for the creation of BLOOMZ & mT0 and xP3 introduced in the…