🔄

Workflow

Agent workflow orchestration tools — LangGraph, Dify, n8n, Flowise and more. Define multi-step agent pipelines visually or in code with state machines, DAGs, conditional branching, and human-in-the-loop steps.

154 projects

n8n

200.9k · TypeScript
Active A+

n8n is a powerful workflow automation platform with native AI agent nodes, enabling multi-step agent workflow orchestration and hundreds of external service integrations.

workflowautomationai-agent +2
  • · 400+ integration nodes - Connect to databases, APIs, SaaS services, and major external systems out of the box
  • · Native AI agent support - LangChain-based AI nodes for orchestrating multi-step agent workflows
  • · Code flexibility with no-code speed - Visual drag-and-drop editor with JavaScript/Python custom code support

Langflow

153.3k · Python
Active A+

Langflow is a visual AI agent and workflow builder platform with drag-and-drop design, multi-LLM integration, and tool composition to simplify agent development.

agent-frameworkworkflowvisual-editor +2
  • · Visual drag-and-drop builder - Graphical interface to build AI agents and workflows by dragging components
  • · Multi-agent orchestration - Complex flow design with multi-agent collaboration, conversation management, and retrieval
  • · API and MCP server deployment - Deploy any workflow as a REST API or MCP tool server with one click

Dify

152.6k · TypeScript
Active A+

Dify is an open-source LLM application development platform with a visual agent orchestration interface, supporting workflows, knowledge bases, and multiple models.

platformworkflowrag +1
  • · Visual workflow orchestration — Drag-and-drop canvas for building AI workflows with branching, loops, and parallel nodes
  • · Multi-model integration — Seamless support for hundreds of LLMs (GPT, Llama, Mistral, etc.) including OpenAI-compatible APIs
  • · RAG pipeline — End-to-end document ingestion (PDF/PPT), vector storage, and retrieval-augmented generation

Spec Kit

129.6k · Python
Active A+

GitHub's official open-source Spec-Driven Development toolkit that flips traditional software development — specifications become executable artifacts that directly generate working implementations, integrating with Copilot, Claude Code, Cursor, and other AI coding agents.

spec-drivencopilotworkflow +3
  • · Spec-Driven Development — specifications become executable artifacts that directly generate implementations
  • · Specify CLI — initialize projects and establish principles with a single command
  • · Multi-agent integrations — supports GitHub Copilot, Claude Code, Cursor, and other AI coding agents

ComfyUI

128.0k · Python
Active A

ComfyUI is a modular AI content-creation engine using a node-graph interface for Stable Diffusion workflows. Generate images, videos, 3D models, and audio without code. Supports local and cloud deployment.

image-generationvideo-generationstable-diffusion +3
  • · Node-graph interface — Visually wire nodes to build complex AI workflows without writing a single line of code
  • · Multimodal generation — Natively supports image, video, 3D model, audio, and more generation tasks
  • · Smart caching — Only re-executes changed parts of the workflow between runs for fast iteration

Odysseus

85.5k · Python
Active A+

odysseus is a macOS-native AI browser automation agent that drives Chrome with natural language to complete everyday workflows.

browserautomationai-agent +2
  • · macOS-native integration — deep hookup with system clipboard, shortcuts and notifications
  • · Chrome automation — drives Chrome via CDP following least-privilege principles
  • · Natural-language tasks — describe tasks and the agent decomposes and executes them

AppFlowy

75.6k · Dart
Active A+

AppFlowy is an open-source Notion alternative with AI workflows, knowledge base, kanban and multi-device sync, usable as agent long-term memory.

note-takingproject-managementai +2
  • · Self-hostable — full data ownership, deploys locally or on a private server
  • · AI assistant — built-in AI for writing, summarizing, translating and table generation
  • · Knowledge base — nested pages, databases, linked views for structured notes

Ansible

70.3k · Python
Active A+

Ansible is an agentless automation platform that orchestrates servers, cloud and network using YAML playbooks; serves as the stable execution layer for agent tools.

automationconfiguration-managementagent +2
  • · Agentless — executes over SSH/WinRM, no agent required on target machines
  • · YAML playbooks — declarative YAML describes desired system state
  • · Idempotent — repeat runs produce the same state, ideal for agent toolchains

Get Shit Done

64.7k · JavaScript
Normal A

A light-weight and powerful meta-prompting, context engineering, and spec-driven development system for AI coding agents like Claude Code.

codingagenttools +1
  • · Context engineering framework - Fresh-context subagents solve context rot (quality degradation as context window fills)
  • · Five-phase development loop - Disciplined Discuss → Plan → Execute → Verify → Ship iteration cycle
  • · Multi-runtime compatible - Supports Claude Code, OpenCode, Gemini CLI, Codex, Cursor, Windsurf and other AI coding tools

TrendRadar

61.5k · Python
Active A+

AI-driven public opinion and trend monitor with multi-platform aggregation, RSS subscriptions, smart keyword filtering, AI-powered news analysis and briefings, supporting MCP integration and push notifications via WeChat, Feishu, DingTalk, Telegram and more.

automationllmpython +3
  • · Multi-platform trend aggregation — real-time scraping from 30+ sources covering tech, finance, social media
  • · AI-powered smart filtering — LLM-driven news summarization and intelligent filtering to auto-exclude irrelevant content
  • · Multi-channel push notifications — supports WeChat Work, personal WeChat, Telegram, DingTalk, Feishu, Slack and 10+ channels

LiteLLM

56.5k · Python
Active A

LiteLLM provides a unified interface and proxy gateway for LLM calls, simplifying multi-model switching, routing, and cost control.

llmgatewayproxy +1
  • · Unified LLM interface — OpenAI-format calls across 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, etc.)
  • · AI Gateway proxy server — Self-hosted proxy with virtual keys, spend tracking, load balancing, and admin dashboard
  • · Python SDK — Switch LLM providers in code via the completion() function

Flowise

55.4k · TypeScript
Active A

Flowise is a low-code builder for LLM apps that lets you create agent workflows and RAG applications with drag-and-drop interfaces.

low-codeworkflowrag +1
  • · Visual drag-and-drop builder — build LLM apps and agent workflows through graphical interface without coding
  • · Multi-module architecture — server (API backend), ui (React frontend), and components (third-party integrations)
  • · Rich node integrations — supports LLM, vector stores, document loaders, tools and many third-party component nodes

OpenMontage

48.4k · Python
Active A+

World's first open-source, agentic video production system with 12 pipelines, 52 tools, and 500+ agent skills. Turn your AI coding assistant into a full video production studio.

multi-agentautomationagent +2
  • · 12 production pipelines, 52 tools, and 500+ agent skills for video creation
  • · Real video production — retrieves actual motion footage, not just still image animation
  • · AI-powered scripting, narration, asset generation, editing, and final composition

JeecgBoot

47.4k · Java
Active A+

An AI-driven low-code platform with zero-code and code-generation modes, featuring built-in AI chat, knowledge base, workflow orchestration and MCP plugin system.

workflowjavaagent +2
  • · AI Skills natural language programming — Generate complete system code, forms, workflows, reports, and dashboards from a single sentence
  • · Zero-code + low-code dual mode — Business users build systems with zero-code, developers accelerate with low-code on the same platform
  • · AI application platform — Dify-like AIGC platform with built-in knowledge base Q&A, workflow orchestration, MCP plugins, and model management

gRPC

45.3k · C++
Active A

Google's open-source high-performance RPC framework supporting cross-language service communication as the core infrastructure of microservice architectures.

rpcprotocol-buffershttp2 +3
  • · HTTP/2 multiplexing — Low-latency bidirectional streaming via HTTP/2 protocol
  • · Protocol Buffers IDL — Define service interfaces in .proto files, auto-generate multi-language client and server code
  • · 10+ language SDKs — Official bindings for C++, Python, Java, Go, Node.js, Ruby and more

Hyperframes

41.2k · TypeScript
Active A+

Write HTML. Render video. Built for agents. An open-source tool from HeyGen that turns HTML templates into video content.

typescriptagentautomation +2
  • · HTML to video rendering — deterministically renders HTML/CSS/JS templates into MP4 videos
  • · AI Agent integration — provides Skills for Claude Code, Cursor and other coding agents to generate videos directly
  • · Searchable animation support — integrates GSAP, CSS, Lottie, Three.js, Anime.js, WAAPI animation libraries

ToolJet

40.0k · JavaScript
Active A

Open-source low-code platform for building internal tools, dashboards, business applications, workflows and AI agents with visual drag-and-drop development.

workflowjavascriptagent +2
  • · Visual drag-and-drop builder — 45+ built-in responsive components (tables, charts, lists, forms, progress bars) for complex frontends in minutes
  • · 50+ data source integrations — Connect PostgreSQL, MongoDB, Elasticsearch, Stripe, Slack, Google Sheets, Airtable, Notion and more
  • · Built-in no-code database — ToolJet Database provides ready-to-use data storage without external database setup

DSPy

37.3k · Python
Active A+

DSPy is a declarative LLM programming framework focused on optimizable prompts and program structure, suitable for complex agent workflows.

llmoptimizationagent +1
  • · Declarative LLM programming — Define LM call logic in Python code instead of prompts for modular AI system construction
  • · Automatic prompt optimization — DSPy Compiler automatically optimizes prompts and few-shot examples without manual tuning
  • · Modular pipeline composition — Freely combine ChainOfThought, ReAct, multi-hop and other modules for complex reasoning chains

1Panel

36.5k · Go
Active A+

A modern open-source VPS control panel with native AI agent support, enabling Ollama model deployment, AI agent management and full server stack control.

devopsgoagent +2
  • · AI agent runtime — Built-in Ollama LLM and OpenClaw agent deployment with GPU monitoring
  • · One-click website deployment — Auto domain binding, SSL provisioning, and Nginx config with zero manual setup
  • · App marketplace — 165+ trusted open-source apps (Nextcloud, Bitwarden, etc.) installed with one click

AI Website Cloner

32.2k · JavaScript
Active A+

Clone any website with one command using AI coding agents. Built with Next.js, React, and shadcn-ui with web scraping and automated code generation.

typescriptagentcoding +3
  • · Clone any website with one command — auto-screenshots, extracts design tokens, generates component specs, and builds a Next.js codebase
  • · Multi-phase pipeline: Recon → Foundation → Component Specs → Parallel Build → Assembly & QA for structured engineering workflow
  • · Supports 13 AI coding agents including Claude Code, Codex CLI, Cursor, Copilot, and more

Conductor

32.1k · Java
Active A+

An event-driven agentic orchestration platform providing a durable and highly resilient execution engine for applications and AI agents.

orchestrationworkflow-enginedistributed-systems +2
  • · Durable Execution — Every step persisted; survives crashes, restarts, and network failures with configurable retries
  • · Dynamic Workflows — Runtime-resolved dynamic forks, tasks, and sub-workflows; LLMs generate JSON workflow definitions
  • · AI Agent Orchestration — 14+ native LLM providers, MCP tool calling, function calling, and human-in-the-loop approval

(24 / 154)

Related Articles

AI Agent工作流编排DAG

Agent Workflow Orchestration in Practice: Production Patterns from DAG to State Machines

Most agent workflows fail at the orchestration layer, not the model. A practical comparison of DAG, state machine, and visual builder approaches with production-ready code for error handling, human approval gates, and conditional branching.

AI Agent框架对比LangChain

Best AI Agent Frameworks in 2026: LangGraph vs CrewAI vs OpenAI Agents SDK vs Google ADK Compared

A practical 2026 comparison of the top AI agent frameworks — LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Google ADK, Microsoft Agent Framework, Mastra, and Claude Agent SDK. Covers architecture philosophy, production maturity, multi-language support, observability, and team fit, with a selection decision tree.

deep-researchagent-architectureiterative-retrieval

Deep Research Agents in Practice: From Single-Shot Search to Iterative Reasoning

Decomposes five open-source deep-research projects across three sub-stages with reusable query-rewriting code.

DifyAgent 工作流RAG

Dify in Practice: Full-Stack Low-Code Platform from RAG to Agent Workflows

Dify (145k Stars, $30M Pre-A) is the benchmark for open-source LLM app platforms. From Docker deployment to RAG pipelines, agent orchestration and MCP integration — this article takes you end-to-end.

GraphRAG知识图谱LightRAG

GraphRAG in Practice: Giving Agents Relational Understanding with Knowledge Graphs

Traditional vector RAG only finds "similar chunks." GraphRAG extracts entities and relationships into a knowledge graph, letting agents understand "who, where, when, and how things connect." Compare Microsoft GraphRAG vs LightRAG approaches.

GraphRAGLightRAGRAG

GraphRAG vs LightRAG: Deep Comparison of Two Engineering Routes for Graph-Enhanced RAG

Systematic comparison of Microsoft GraphRAG (community detection + global summarization) and HKUDS LightRAG (dual-layer graph + incremental update) across index construction, retrieval paradigm, cost structure, query quality, and use cases. Includes a decision tree by data scale, query type, and ops budget.