Electric agent runtime — behavioral stack for agent entities over durable streams
Shared agents runtime hooks, connection logic, and lifecycle types.
Runtime for Reactive Agents — ExecutionEngine, ReactiveAgentBuilder, and createRuntime
AriaFlow plugin for LiveKit Agents — runtime adapter, transport foundation, Gemini STT/TTS
MCP server for Nerve — gives AI agents runtime access to iOS apps
MCP server that gives AI coding agents runtime visibility into React Native/Expo apps on iOS Simulator
TypeScript SDK for the Lucid Agents Runtime API (auto-generated from OpenAPI)
Cross-runtime adapter — unified API for Bun and Node.js fast paths
The **[Google Vertex provider](https://ai-sdk.dev/providers/ai-sdk-providers/google-vertex)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [Google Vertex AI](https://cloud.google.com/vertex-ai) APIs.
Runtime agnostic JS utils
Hud's Node SDK
Agent 365 Runtime SDK for AI agents built with TypeScript/Node.js
Anginel 是一个 multi-agents runtime 框架，用于快速构建高可扩展的 agents 系统。
provides utilities to route requests through a configurable proxy
Security middleware for OpenClaw agents - Runtime interception with human-in-the-loop approval
Process-global proxy routing for Node.js.
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
babel's modular runtime helpers
Runtime for Regenerator-compiled generator and async functions.
Anthropic Sandbox Runtime (ASRT) - A general-purpose tool for wrapping security boundaries around arbitrary processes
Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line
OpenClaw ACP runtime backend with plugin-owned session and transport management.
Maps proxy protocols to `http.Agent` implementations
No description provided.
Async runtime orchestration for Rust deep agents.
High-performance Rust SDK for composing reusable AI agents with custom tools, sub-agents, and prompts
AWS integrations for the Rust deep agents SDK.
Core traits, data models, and prompt primitives for building deep agents.
Reusable tools and utilities for Rust deep agents.
Runtime agent and builder for AI Agents framework
Official AWS Ruby gem for Agents for Amazon Bedrock Runtime. This gem is part of the AWS SDK for Ruby.
Ruby version of the [Threat Stack](https://www.threatstack.com) agent which helps identify security vulnerabilities at runtime. Refer detailed instructions on how to install the Threat Stack agent [here](https://threatstack.zendesk.com/hc/en-us/articles/360039993431). All components of this product are - Copyright (c) 2021 Threatstack, Inc. All rights reserved.Certain inventions disclosed in this file may be claimed within patents owned or patent applications filed by Threatstack, Inc. or third parties. The Threatstack Ruby agent also uses code from the following open source projects under the following licenses: libinjection http://opensource.org/licenses/BSD-3-Clause
SmartBrain provides commit_turn and compose_context APIs for agent memory, retrieval planning, evidence fusion, and context assembly.
A Ruby CLI agent runtime with streaming provider adapters.
Embeds a FOSM-aware MCP server and ACP agent into your Rails development environment, giving coding agents (Claude Code, Codex, Copilot) runtime intelligence: database queries, logs, code evaluation, and deep introspection of FOSM lifecycle definitions, state machines, transitions, guards, and audit trails. Built on the FOSM (Finite Object State Machine) paradigm — declarative lifecycles for business objects where AI agents operate within bounded, auditable state machines.
AgentRuntime provides a reusable control plane for building tool-using LLM agents with explicit state, policy enforcement, and auditability.
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.
The CrowdStrike for AI Agents — Real-time security monitoring, threat detection, and runtime protection for LLM-powered agents.
Real-time exception monitoring with AI-powered analysis for Ruby applications. Captures exceptions, stack traces, and local variables with zero performance impact.
JSON-RPC message models, method constants, protocol version handling, and side-aware decode helpers for ACP. Community implementation.
Ruby SDK for ARCP: envelope and message model, fiber-based runtime, client, WebSocket / stdio / in-memory transports, SQLite-backed resume log, capability negotiation, leases with budget and expiration, streamed results, and OpenTelemetry trace propagation. Built on socketry/async.
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.