AndersonBY/vector-vein

No-code AI workflow. Drag and drop workflow nodes and use your workflow with your AI agents.

What it solves

VectorVein provides a no-code environment for users to build intelligent automation workflows. It eliminates the need for programming by allowing users to combine large language models (LLMs) with their own knowledge bases to automate daily tasks, such as document translation, summarizing web articles into mind maps, or classifying customer complaints.

How it works

Users create workflows using a drag-and-drop editor where they connect various functional nodes with wires on a canvas. The system supports a wide range of configurations:

  • LLM Integration: Connects to OpenAI-compatible interfaces, including local services like Ollama, LM-Studio, and vLLM.
  • Knowledge Integration: Supports embedding backends for vector searches using personal data.
  • Execution: Workflows can be run through a dedicated user interface, a command-line interface (CLI), or programmatically via a local FastAPI REST server.
  • Data Handling: Supports structured data inputs/outputs, including XLSX, DOCX, and PNG charts, with JSON Schema validation for LLM nodes to ensure reliable execution.

Who it’s for

It is designed for non-experts and non-programmers who want to leverage the power of AI agents and LLMs to automate repetitive tasks without writing code.

Highlights

  • No-Code Interface: Visual drag-and-drop workflow builder.
  • Local AI Support: Compatible with local LLM and embedding providers (Ollama, vLLM, etc.).
  • Programmatic Access: Local API server for integrating workflows into other applications.
  • ** uma Structured Output**: Ability to generate typed XLSX, DOCX reports, and automatic charts.
  • Multi-modal Capabilities: Includes speech recognition and Stable Diffusion API support.

Related

  • Project
    SamurAIGPT/Vibe-Workflow

    Vibe Workflow is an open‑source, MIT‑licensed node‑based visual editor for building generative image and video pipelines. It consists of a Next.js front‑end, a FastAPI back‑end that calls MuAPI’s generative models, and a reusable workflow‑builder UI library. You can self‑host it (Docker or manual) or use the hosted SaaS version, and you can extend it with custom nodes to call any AI model or external API.

  • Project
    katipally/openlive

    An open-source desktop app that gives AI agents real-time voice and vision, running the entire speech pipeline locally on-device. Works with any LLM provider or coding agent (Claude Code, Codex, etc.), with three modes: Chat (voice calls), Flow (system-wide voice assistant that can drive your computer), and Dictate (voice typing). Privacy-focused: audio never leaves the machine.

  • Project
    OpenBMB/ChatDev

    ChatDev 2.0 (DevAll) is an open‑source, zero‑code platform that lets you design and run multi‑LLM‑agent workflows via a visual web console or a tiny Python SDK. Define agents and their connections in YAML, launch from the browser or code, and use built‑in templates for data viz, 3‑D generation, game dev, research, etc. The backend is FastAPI, the frontend Vue 3, and the project ships Docker/Makefile support, extensible Python tools, and research‑grade orchestrators (Puppeteer, MacNet).

  • Project
    sceneview/sceneview

    SceneView is an open‑source, Apache‑2.0 SDK that provides declarative 3‑D rendering and AR across Android (Jetpack Compose), iOS/macOS/visionOS (SwiftUI), the web, Flutter, React Native, and Kotlin‑Multiplatform. It wraps Filament, RealityKit, and Filament.js behind composable APIs (e.g., SceneView, ModelNode, ARSceneView) and includes a rich node library, physics, gestures, and post‑processing. The project is “AI‑first”: a plain‑text API reference (llms.txt) and a tiny MCP server let LLM assistants generate and validate code automatically. Packages are published on Maven Central, Swift Package Registry, npm, and pub.dev, with demos, CI, Discord community, and an Open Collective for funding.

  • Project
    OpenDCAI/DataFlow

    DataFlow is an open‑source Python framework that lets you build, run, and share low‑code pipelines for generating, cleaning, and evaluating LLM training data. It provides a library of reusable operators, a visual WebUI, an AI‑assistant for auto‑creating pipelines, and a Ray‑based distributed execution layer.