Provider-agnostic TypeScript library for Zod-validated, fully-typed structured output from any LLM
Structured LLM metadata standard for Node.js packages — llm.package.json and llm.package.txt
A simple workflow showing how to work with structured LLM output in Loopstack.
Compact JSON Schema prompts and validate structured LLM outputs with zero dependencies.
Extract structured, LLM-readable data from Roblox .rbxl/.rbxlx place files
Composable middleware for structured LLM calls with TypeScript
TypeScript structured LLM outputs: JSON extraction, Zod/JSON Schema adapters, validation, retries. OpenAI (JSON mode & structured outputs), Anthropic, Google Gemini, Ollama, custom providers.
JSX interface for structured LLM calls — tools, messages, and prompts as composable components
Schema DSL for structured LLM Markdown output
LangDiff is a TypeScript library that solves the hard problems of streaming structured LLM outputs to frontends.
MCP server for prompt-to-JSON contracts, JSON Schema validation, and structured LLM/agent outputs.
Type-safe AI for TypeScript — structured LLM outputs, agents, tools, and multi-provider support in one library
Structured LLM workflows for verification, exploration, architecture, feasibility, risk, synthesis, and documentation — with interactive installer for 11 AI tools
Tiny schema validator for structured LLM responses.
Agentic orchestration and semantic enforcement for structured LLM output, with native JSON repair and deterministic retries.
Analyzes Git branches and outputs structured, LLM-ready context with intelligent risk analysis
Multi-language library for parsing labeled/structured LLM output
JS framework for typesafe and structured LLM inference.
Telegram bot channel engine — grammy transport, SQLite message mirror, FTS5 full-text search, markdown rendering, and a structured LLM tool facade. Node 24+, built-in node:sqlite.
JavaScript library for parsing labeled/structured LLM output
A structuredClone polyfill
Type definitions for tool2agent: a protocol for structured LLM tool feedback
Automatically convert schemas like Zod to prompts for AI SDK generate, OpenAI function calling, and structured LLM outputs
Lattice runtime for Node.js - A statically-typed language for structured LLM interactions
Simple and powerful way to work with LLM structured outputs in Rails. Supports OpenAI and Anthropic with automatic validation, caching, and Rails integration.
Explore the power of LLM structured extraction in Ruby with the Instructor gem.
Generate BAML style prompts from dry-schema that can get and check structured responses from LLMs
ActiveImagination facilitates using LLMs to generate ActiveRecord content
Ollama DSL provides an easy-to-use Ruby interface to communicate with Ollama local or remote language models. It supports building prompts with system/user roles, handling streaming responses, and chaining prompts seamlessly.
The Firecrawl gem implements a lightweight interface to the Firecrawl.dev API. Firecrawl can take a URL, scrape the page contents and return the whole page or principal content as html, markdown, or structured data. In addition, Firecrawl can crawl an entire site returning the pages it encounters or just the map of the pages, which can be used for subsequent scraping.
Validates and coerces unstructured LLM responses directly into rich, schema-validated Ruby objects with automatic self-correction loops.
Use one CLI for multiple LLM providers with aliases, fallback routing, and structured output options
CV Parser is a Ruby gem that extracts structured information from CVs and resumes in various formats using LLMs.
Leva is a Ruby on Rails framework for evaluating Language Models (LLMs) using ActiveRecord datasets. It provides a flexible structure for creating experiments, managing datasets, and implementing various evaluation logic.
Lluminary is a framework for building applications that leverage Large Language Models. It provides a structured way to define tasks, manage prompts, and handle LLM interactions.
The Ruby framework for programming with large language models. DSPy.rb brings structured LLM programming to Ruby developers. Instead of wrestling with prompt strings and parsing responses, you define typed signatures using idiomatic Ruby to compose and decompose AI Worklows and AI Agents.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.