Awesome AI Agents › Low-Code/No-Code Platforms
Flow-Like is a platform for building complete use cases in one runtime instead of assembling an automation tool, an app builder, an AI framework and separate data infrastructure. Workflows are composed visually from a library of more than fifteen hundred nodes, and the same workflow can be inspected through three views: a process view for business stakeholders, a data view for analysts and an execution view for engineers. The execution engine is written in Rust and is fully typed, so input and output contracts are checked before deployment, and the maintainers publish throughput and latency figures that they contrast with typical Node and Python engines. Every run records complete lineage of inputs, transformations and outputs, which allows any execution to be replayed. A native data layer is part of the platform rather than an external dependency: files, tables and hybrid keyword plus vector search sit directly on the canvas, and the documentation states that terabytes of data can be held in-platform with no fixed payload size limits. AI capability is local-first as well. Language models, embeddings, vision object detection, speech-to-text and text-to-speech can all run on the device, or in the cloud when that is preferred, and every model call is logged with its inputs, outputs, model version and reasoning trace, with approval gates and guardrails available on each step. Model Context Protocol is supported on both the client and server side. Typical applications described by the project include a private retrieval assistant over local documents, large data pipelines exposed as applications, agentic automations that act across APIs and messaging services on a schedule or webhook, and internal or customer-facing apps. It runs on laptops, servers, phones and edge hardware, is offered as a desktop download or hosted trial, and is licensed under BSL 1.1.
https://github.com/TM9657/flow-like
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.