基于多智能体协作的通用工作流框架
Multi-agent workflow framework for automated feature development
Multi-agent workflow framework for Claude Code. 5 agents + 22 commands + MCP-backed evidence research + optional brainstorm + RTK-lite hooks.
Composable AI agent workflow framework — execution, state, orchestration, runtimes, UI
Initialize AI agent workflow framework in any project
TypeScript contract types for the 16 standardized interfaces of Miadi-A2A v2, modeled on the HAWK hierarchical agent workflow framework (Cheng et al. 2025, arXiv:2507.04067). Functional stub: types only, zero runtime dependencies.
LangGraph
Structured AI agent workflow framework with Stories, Activities, and Steps
Allure Agent Plugin – AI-friendly markdown report generator
Get a user agent string across all JavaScript Runtime Environments
Scaffold an AI agent workflow framework into any project — subagents, commands, skills, and conventions for Claude Code and OpenCode
A lightweight AI agent workflow framework
New Relic agent
The Serverless Framework's new infrastructure provisioning technology — Build, compose, & deploy serverless apps in seconds...
New Relic Security Agent for Node.js
No description provided.
The official, opinionated, batteries-included toolset for efficient Redux development
Shared builder infrastructure for Workflow SDK
AI DevOps Framework - AI-assisted development workflows, code quality, and deployment automation
Turn a function into an `http.Agent` instance
better fetch for Node.js. Works on any JavaScript runtime!
Maps proxy protocols to `http.Agent` implementations
Skillflag producer CLI reference implementation.
An HTTP(s) proxy `http.Agent` implementation for HTTPS
Agent framework for triglav, data-driven workflow tool.
Phronomy provides composable building blocks — Agents, Workflows, Tools, Guardrails, and Tracing — for building AI agents in Ruby. Powered by RubyLLM for LLM abstraction.
Ruby port of LangGraph - build stateful, multi-actor applications with LLMs using a graph-based workflow engine with Pregel execution model
Bristow provides a flexible framework for creating and managing systems of agents that can work together, hand off tasks between each other, and execute functions. Perfect for building complex AI systems and automation workflows.
RailsOrchestrator provides a structured framework for building AI agents in Ruby on Rails applications. It includes tool support, memory management, and orchestration capabilities for composing complex agent workflows.
Build and manage AI agents with ease using ActAsAgent. This gem provides a robust framework for creating, configuring, and deploying intelligent agents that can perform tasks autonomously. Whether you're looking to automate workflows, enhance user interactions, or develop complex AI systems, ActAsAgent offers the tools and flexibility you need to bring your ideas to life.
MongoAgent is a framework for creating distributed pipelines across many different servers. It is extensible, and flexible. It does not specify what goals should be processed. It simply provides the foundation for using a MongoDB as a messaging queue between many different agents processing tasks defined in the same queue. It is designed from the beginning to support the creation of simple human-computational workflows.
Rubagent is a lightweight Ruby framework for building modular, composable AI agents that can interact with LLMs (like OpenAI), tools, and external APIs. It provides a flexible architecture for defining agents, managing prompts, and orchestrating multi-step workflows using functional patterns. Features: - Streamed LLM responses (OpenAI, etc.) - Plug-and-play agent design - Shared context and memory flow - Support for custom tools and HTTP integrations - Built-in dry-rb and Zeitwerk compatibility
Boma Gem for building AI agents, workflows, and service integrations. Boma provides a framework for creating intelligent agents that can perform complex tasks by integrating with various services and APIs. It allows developers to build AI-powered applications with ease, enabling them to automate workflows, make decisions, and interact with users in a natural way.
RCrewAI is a powerful Ruby framework for creating autonomous AI agent crews that collaborate to solve complex tasks. Build intelligent workflows with reasoning agents, tool usage, memory systems, and human oversight. Key Features: • Multi-Agent Orchestration: Create crews of specialized AI agents that work together • Multi-LLM Support: OpenAI GPT-4, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama • Rich Tool Ecosystem: Web search, file operations, SQL databases, email, code execution, PDF processing • Agent Memory: Short-term and long-term memory for learning from past executions • Human-in-the-Loop: Interactive approval workflows and collaborative decision making • Advanced Task Management: Dependencies, retries, async execution, and context sharing • Hierarchical Teams: Manager agents that coordinate and delegate to specialist agents • Production Ready: Security controls, error handling, comprehensive logging, and monitoring • Ruby-First Design: Built specifically for Ruby developers with idiomatic patterns • CLI Tools: Command-line interface for creating and managing AI crews
FlowNodes is a Ruby port of PocketFlow, the Python framework created by The Pocket. It brings the power and simplicity of PocketFlow's graph-based architecture to the Ruby ecosystem. Build powerful LLM applications like Agents, Workflows, and RAG systems with minimal code and maximum expressiveness.
SpreadsheetAgent is a framework for creating distributed pipelines across many different servers. It is extensible, and flexible. It does not specify what goals any pipeline should be working towards, or which goals are prerequisites for other goals, but it does provide logic for easily defining these relationships based on your own needs. It does this by providing a subsumption architecture, whereby many small, highly focused agents are written to perform specific goals, and also know what prerequisites and resources they require to perform them. In addition, it is designed from the beginning to support the creation of simple human-computational workflows.
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.