tinyflow-ai/tinyflow

Tinyflow is a lightweight AI agent solution.

What it solves

Tinyflow is a development component rather than a standalone product, designed to give traditional applications the ability to orchestrate AI agents. It allows developers to integrate AI agent orchestration capabilities directly into their existing software.

How it works

Tinyflow provides a framework consisting of a frontend UI component and backend execution engines. The frontend is built using Web Components, making it compatible with any JavaScript framework (React, Vue, Angular, Svelte) or plain HTML/CSS/JS. The backend supports multiple languages, including Java (currently available), with Node.js and Python support in development.

Who it’s for

Developers who want to add AI agent orchestration to their existing applications without building the orchestration layer from scratch.

Highlights

  • Framework Agnostic: Frontend based on Web Components for universal compatibility.
  • Multi-language Backend: Supports Java, with Python and Node.js coming soon.
  • Integrated Data Providers: Supports configurations for Large Language Models (LLMs) and knowledge bases.
  • Easy Integration: Simple installation via npm for the UI and Maven for the Java core.

Related

  • Project
    frontman-ai/frontman

    An open-source AI coding agent that lets users edit frontend source code directly from the browser by clicking elements and describing changes in plain English.

  • Project
    open-gitagent/gitagent

    A git-native AI agent framework where identity, memory, and tools are stored as version-controlled files, allowing agents to be branched and diffed like code.

  • Project
    vybestack/llxprt-code

    A provider-agnostic CLI AI coding assistant that lets developers use any LLM provider, including local models and existing subscriptions, to edit codebases and automate workflows.

  • Project
    CosmosMind-ai/RSI-Harness

    A configuration layer for the Pi coding agent that bundles system prompts, tools, and settings into shareable "Genomes," including an engine to automatically generate them from usage history.