Declarative workflow orchestration for LLM agents — schemas, routers, sub-workflow composition, full audit
CifRail BIS Domains
RoadRailUnits BIS Domains
A highly optimized pure JS implementation of Range Slider for React Native
Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js
Lightweight, zero-dependency LLM API cost & token usage tracker for OpenAI, Anthropic, Gemini, Mistral, Groq, and DeepSeek
Typescript bindings for langchain
Display language model outputs in your React project.
[llm-ui](https://llm-ui.com) markdown block.
Hardware accelerated language model chats on browsers
[llm-ui](https://llm-ui.com) code block.
LLM eval & testing toolkit
[llm-ui](https://llm-ui.com) JSON blocks for building custom components.
CLI wallet for one-shell-command agent payments across x402 (Base) and MPP (Tempo, Solana)
General-purpose agent with transport abstraction, state management, and attachment support
node module that can be used to upload test execution log to test rail using test rail-api
Angular Material Navigation Rail component - Material Design 3 compliant
Detox driver for Wix Pilot usage
micromark extension to support math (`$C_L$`, `\(C_L\)`)
A2A (Agent-to-Agent) protocol wrapper for OpenCode. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports any agent persona, MCP tool servers, SSE streaming with polling fallback, context building, and multi-turn conversations.
A library for working with LLMs in Grafana plugins
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
Sticky reading rail with table-of-contents, scroll progress, and active heading state. Vanilla, ESM, zero dependencies.
Package to connect and trace LLM calls.
LLM evaluation engine for Rails.
A Rails engine providing comprehensive observability for LLM-powered applications. Features include session tracking, trace analysis, prompt management, cost monitoring, and optional chat/agent testing UI (with RubyLLM integration).
Logs every call your Rails app makes to OpenAI, Anthropic, Gemini, RubyLLM, or an OpenAI-compatible API: tokens, cost, latency, tags. Calls go straight to the provider — no proxy. Includes price sync, budget guardrails, and a mountable dashboard.
Easily create and manage LLM prompt templates in your rails app.
A flexible Ruby gem for building LLM-based classifiers. Define categories, system prompts, and domain knowledge using a clean DSL. Supports multiple LLM backends (ruby_llm, OpenAI, Anthropic) and integrates seamlessly with Rails.
A modular and extendable Rails engine that provides an Agent model and LLM client integration for building AI-powered applications.
llm_meta_client provides a Rails Engine with scaffold and authentication generators for building LLM-powered chat applications. Supports OpenAI, Anthropic, Google, and Ollama providers.
ActionPrompt is a Rails plugin for managing templated LLM prompts
Mountable Rails engine that provides hierarchical LLM call tracing and versioned prompt management with Mustache templates.
A Ruby port of Google's A2UI (Agent-to-User Interface) for Rails. Uses DSPy.rb to generate typed UI descriptions from natural language, rendered as ViewComponents via Turbo Streams.
A simple gem that provides a Rails command or Rake tasks to export .rb, .erb, .js, and .yml files into .txt or .md for LLM ingestion.
PromptNavigator is a Rails engine that provides a visual history stack UI for tracking LLM prompt executions. It includes a self-referencing PromptExecution model for building conversation trees, Stimulus-powered SVG arrow visualization between parent-child history cards, and automatic asset pipeline integration.
No description provided.
No description provided.