TypeScript types for ShapeShyft API - LLM structured output platform

Parse arrow-format LLM structured output

Parses TSON (Token-Structured Object Notation) responses back into MongoDB documents, filters, update pipelines, and BSON types. Optimized for LLM structured output parsing & AI database writes.

Validate, repair, retry LLM structured output (JSON / YAML / TOML / Python literal) — 15-strategy two-pass repair chain with Zod adapter.

TypeScript types for ShapeRouter API - LLM structured output platform

Convert string-schema syntax to Zod schemas for LLM structured output

Implementation of Structured Field Values for HTTP (RFC9651, RFC8941)

A structuredClone polyfill

Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.

A debug logger package for other Google libraries

An env-agnostic serializer and deserializer with recursion ability and types beyond JSON, based on the HTML structured clone algorithm.

TypeScript bridge for recursive-llm: Recursive Language Models for unbounded context processing with structured outputs

A gateway package for LLM services.

A powerful TypeScript library for building AI agents with multi-threaded conversations, tool execution, and event handling capabilities

Shared LLM generation policy for DeepSeek Harness session-title providers

Expo module implementation of a parser based on https://httpwg.org/specs/rfc8941.html

Provider-neutral LLM service interface for the DeepSeek Harness

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

A Vitest reporter optimized for LLM parsing with structured, concise output

Utilities for managing multi-shot conversations and structured data handling in LLM applications