Awesome AI Agents › Low-Code/No-Code Platforms
FLUJO is an open-source, locally hosted application for building and running private AI agents without writing code. It combines three layers. The first is model setup: connections to OpenAI, Azure OpenAI, Anthropic, Google Gemini, xAI, OpenRouter, Codex and local models through Ollama, organised into folders and reusable across agents, with secrets encrypted at rest and never exposed to the browser, plus global variables so a key is defined once and bound wherever it is needed. The second is connected apps over the Model Context Protocol, where servers can be installed from the official MCP registry, a curated list, a GitHub repository or a local command through a guided three-step form with a connection test; the full protocol surface is supported, covering tools, resources, prompts, roots and sampling, and each server gets a detail view for browsing and calling its tools. FLUJO can also act as an MCP proxy, re-exposing any configured server to other clients such as Claude Desktop, Cursor or Cline. The third layer is the agent builder, offered as a simple recipe mode where steps are written in plain language and an expert visual mode where Start, AI, connected-app, subflow and Finish nodes are wired in a graph. Branching lets a model hand off to another node or agent based on the conversation, subflows call another flow as an isolated reusable step, and tools and prompt fragments can be scoped per node. Finished agents are reachable through chat, automation triggers and OpenAI-compatible or MCP endpoints, so other software can call them. A built-in debugger shows every run. FLUJO is built on the PocketFlow framework, MIT licensed, and installed through a Windows setup binary, a shell installer or npx.
https://github.com/mario-andreschak/FLUJO
AnythingLLM is an all-in-one AI application that enables intelligent chat interactions with documents using various large language models, supporting multi-user management, no-code AI agent building, and multi-modal capabilities in both desktop and Docker environments.
NocoBase is an open-source AI + no-code platform that accelerates business system development by combining AI agents with a WYSIWYG no-code interface for speed and reliability.
Maxun is an open-source no-code platform that enables users to create custom robots for automated web data extraction, turning websites into APIs and spreadsheets without coding.
Databerry is a no-code platform that enables users to build custom Large Language Model agents without programming skills, making AI development accessible and user-friendly.
LLMStack is a no-code multi-agent framework for building generative AI agents, workflows, and applications that integrate with your data and business processes, deployable on cloud or on-premise with multi-tenant support and API access.
Source-available agent platform that pairs a drag-and-drop visual builder with a TypeScript SDK kept in two-way sync, plus a configuration API, CLI, chat UI library and OpenTelemetry tracing.
Next.js template for building an AI workflow automation platform, with a React Flow drag-and-drop canvas, prebuilt integrations, execution logs and conversion of workflows into TypeScript code.
Heym is a source-available, self-hosted workflow automation platform where LLMs and agents are the execution model, combining a drag-and-drop canvas with RAG, MCP, human-in-the-loop steps, evals and cost tracking.