Standardized JSON response format for LLM consumption with sensitive field filtering - NestJS + Prisma plugin
Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware encoding of JSON for LLM prompts
Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.
Fetch web pages and return structured text, HTML, or JSON for LLM consumption.
[llm-ui](https://llm-ui.com) JSON blocks for building custom components.
Hardware accelerated language model chats on browsers
Parse partial JSON generated by LLM
Superfast runtime validators with only one line
The official JSON schema converter for Valibot
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
A library for working with LLMs in Grafana plugins
Typescript bindings for langchain
Parse incomplete json text in best-effort manner
micromark extension to support math (`$C_L$`, `\(C_L\)`)
Superfast runtime validators with only one line
LLM eval & testing toolkit
Model Context Protocol implementation for TypeScript
A TypeScript SDK to extract and correct JSON from LLM outputs
JSON for Humans
Detox driver for Wix Pilot usage
JSON Schema validation and specifications
Display language model outputs in your React project.
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 local development tool for debugging and inspecting AI SDK applications. View LLM requests, responses, tool calls, and multi-step interactions in a web-based UI.
Define schemas using a clean DSL and get both JSON Schema documents and runtime validations. Perfect for API request/response validation, LLM function definitions (OpenAI, Anthropic), and structured data modeling. Features Sorbet-style types, schema composition, pluggable validation adapters, and multiple error output formats (JSON:API, RFC 7807).
TOON is a compact, human-readable format designed for passing structured data to Large Language Models with significantly reduced token usage.
Ask LLMs for JSON responses and validate their shape.
Compact serialization format optimized for LLM contexts with 30-60% token reduction compared to JSON
Pipeline: URL → ContentFetcher (Markdown) → LlmClient (JSON). Supports Jina/Firecrawl fetchers and OpenAI-compatible/Anthropic LLM providers.
A Ruby gem for converting between JSON and TOON format. TOON is a compact serialization format designed for LLMs that reduces token usage by 30-60% compared to JSON. Supports bidirectional conversion, tabular arrays, nested structures, and lossless roundtrips.
CTON provides a JSON-compatible, token-efficient text representation optimized for LLM prompts.
Agents that write and execute Ruby code. Inspired by smolagents. LLMs write executable code, not JSON blobs.
LLMs::Tool provides a simple DSL for defining tools that can be serialized to the correct JSON schema to be used with LLM systems
Lightweight Ruby library for converting JSON data to TOON format, achieving 30-60% token reduction for LLM applications
JsonMend is a robust Ruby gem designed to repair broken or malformed JSON strings. It is specifically optimized to handle common errors found in JSON generated by Large Language Models (LLMs), such as missing quotes, trailing commas, unescaped characters, and stray comments
Register JSON-schema tools and let an LLM handle intent, slot-filling, and tool calls safely.