e2e
e2e is a platform for Large Language Model (LLM) evaluations and AI agent testing, facilitating end-to-end test generation and verification workflows.
A professionally curated collection of the most powerful prompt-engineering tools, MCP servers, and SDKs for developers building advanced AI agents. This directory features rigorously tested tools like e2e and backend-zod that streamline the development, testing, and deployment of sophisticated AI capabilities.
e2e is a platform for Large Language Model (LLM) evaluations and AI agent testing, facilitating end-to-end test generation and verification workflows.
Document-Driven Development framework for Claude Code — structured specs, TDD cycles, feedback loops, and skills system
documentation-criteria is a systematic approach to creating documentation with quality gates for AI coding agents, using a test-first workflow with tools like Cursor, Codex, and Gemini CLI.
Agentic coding framework powered by AGENTS.md — systematic, test-first workflows with quality gates for Cursor, Codex, Gemini CLI, and AI coding agents.
Systematic workflows for AI-assisted development - Task-oriented framework with quality gates
typescript-sdk is an open-source library for debugging, evaluating, and monitoring LLM applications. It features a non-blocking, layered architecture that asynchronously buffers and flushes trace data to a backend, requiring Node.js >= 18 and providing both ESM and CJS builds.
local-dev is a debugging and monitoring tool for LLM applications, RAG systems, and agentic workflows, providing features like automated evaluations and tracing.
widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.
a.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.