AI Skill Package Manager + Runtime Adapter System
babel's modular runtime helpers
Runtime for Regenerator-compiled generator and async functions.
Externalise references to helpers and builtins, automatically polyfilling your code without polluting globals
AIS 的中性 integration runtime 内核。
GEOGATE-geojson handles AIS/NMEA encoding/decoding for GEOgate GPS/AIS/GTS framework
Runtime agnostic JS utils
👷 workerd for Linux 64-bit, Cloudflare's JavaScript/Wasm Runtime
👷 workerd, Cloudflare's JavaScript/Wasm Runtime
Module federation runtime package collection. You can just install it instead of installing all the packages separately.
babel's modular runtime helpers with core-js@3 polyfilling
- Can be combined with the build plug-in to share basic dependencies according to policies to reduce the number of module downloads and improve the loading speed of modules. - Only consume part of the export of the remote module and will not fully downloa
Plugin to convert NMEA2000 AIS to NMEA 0183
- Can be combined with the build plug-in to share basic dependencies according to policies to reduce the number of module downloads and improve the loading speed of modules. - Only consume part of the export of the remote module and will not fully downloa
A sdk for support module federation
hast utility to transform to preact, react, solid, svelte, vue, etc
LDM OS: identity, memory, and sovereignty infrastructure for AI agents
The runtime components for the pug templating language
Runtime for React Compiler
Module Federation Runtime for webpack
Get the Node ABI for a given target and runtime, and vice versa.
Functions for converting Expo SDK versions to EAS runtime versions
Runtime to be use with the Flow Enums transform.
Tools for making advanced Metro bundler features work
Official AWS Ruby gem for Amazon Augmented AI Runtime. This gem is part of the AWS SDK for Ruby.
n/a
llm.rb is Ruby's most capable AI runtime. It runs on Ruby's standard library by default. loads optional pieces only when needed, and offers a single runtime for providers, agents, tools, skills, MCP, A2A (Agent2Agent), RAG (vector stores & embeddings), streaming, files, and persisted state. As a bonus, llm.rb is also available for mruby. It supports OpenAI, OpenAI-compatible endpoints, Anthropic, Google Gemini, DeepSeek, xAI, Z.ai, AWS Bedrock, Ollama, and llama.cpp. It also includes built-in ActiveRecord and Sequel support, plus concurrent tool execution through threads, tasks (via async gem), fibers, ractors, and fork (via xchan.rb gem).
Solid Agent stores agent runs in its own database and dispatches staged workflow tasks to the RubyLLM runtime with a built-in Rails UI.
Monitor every action, enforce policies, and automatically roll back damage from AI agents.
A production-ready AI agent platform: multi-provider (Ollama, OpenAI, Anthropic), typed tool system with permissions, three-tier memory, structured observability, loop detection, plugin architecture, interactive REPL, and project indexing. Works out of the box with local Ollama models; drop in OpenAI or Anthropic keys to upgrade.
The CrowdStrike for AI Agents — Real-time security monitoring, threat detection, and runtime protection for LLM-powered agents.
RLM.rb is a Ruby runtime spine for Recursive Language Models. It runs bounded, typed, auditable AI jobs over files, records, and application context. RLM.rb includes RubyLLM provider access, a dspy.rb signature adapter, the recursive prompt loop, file/context mounting, recursive sub-LM calls, typed final output, budget controls, trace events, and a best-effort trace_store hook.
Ruby SDK for MUXI AI platform - manage AI agent formations and interact with their runtime APIs
Sinatra-free core for running Opal-compiled Ruby on Cloudflare Workers: Rack handler, D1/KV/R2/AI/Queue/Durable Object adapters, multipart/streaming, and Opal corelib patches. Use with the `opal` gem and a Module Worker (`runtime/worker.mjs` in this gem).
Ask questions in IRB and get AI-powered answers based on your runtime context. Access local variables, exception info, and Rails model data while debugging. Requires an LLM provider gem (e.g., girb-ruby_llm) or custom provider implementation.
Self-hosted error observability and LLM tracing. Captures errors, deduplicates via fingerprinting, and traces AI/LLM calls (token usage, costs, latency). Zero external runtime dependencies.