miurla/morphic

An AI-powered search engine with a generative UI

What it solves

Morphic is an AI-powered search engine that moves beyond simple text responses. It solves the problem of static, plain-text AI search results by providing grounded, cited answers with a "generative UI" that renders rich, interactive components like images and grids live from a streamed JSON specification.

How it works

The system integrates multiple AI model providers (such as OpenAI, Anthropic, Google, and Ollama) and search providers (Tavily, SearXNG, Brave, and Exa) to retrieve and synthesize information. It uses a streamed JSON spec to render dynamic UI components inline, allowing the search engine to present information in a more structured and structured way than standard markdown.

Who it’s for

It is designed for users who want a more visual and interactive AI search experience, as well as developers who want to self-host a private AI search engine with support for various LLM and search providers.

Highlights

  • Generative UI: Renders rich inline components (grids, images, headings) instead of just plain markdown.
  • Flexible Provider Support: Supports a wide range of AI models (OpenAI, Anthropic, Google, Ollama) and search engines (Tavily, SearXNG, Brave, Exa).
  • Full-Featured Search: Includes search modes (Quick and Adaptive), file upload support, and the ability to share results via unique URLs.
  • Self-Hostable: Ready for Docker deployment, including a built-in SearXNG instance for search capabilities.

Related

  • Project
    morphik-org/morphik-core

    A multimodal retrieval engine that enables AI applications to search and understand visually rich documents, such as PDFs and charts, without losing spatial or visual context.

  • Project
    thesysdev/openui

    OpenUI is a framework‑agnostic, streaming‑first UI library that lets LLMs generate UI components using a compact language (OpenUI Lang). It provides parsers, prompt generators, and runtime bindings for React, Vue, Svelte, Angular, plus a CLI for scaffolding apps. The language reduces token usage by ~50 % versus JSON, enabling progressive rendering of model‑generated interfaces.

  • Project
    vercel-labs/json-render

    json-render is a generative UI framework that lets AI create interfaces from prompts while staying safe and predictable. It works by constraining AI output to a catalog of defined components and actions, which are then rendered across many platforms.

  • Project
    Comfy-Org/ComfyUI

    ComfyUI is a modular, node-graph based engine that lets visual creators build and run AI workflows for images, video, audio, 3D, and text, with broad support for state-of-the-art open-source models and efficient local execution on consumer hardware.

  • Project
    oxylabs/perplexity-scraper

    A scraper for Perplexity AI that allows developers to send prompts and collect AI-generated responses and structured metadata in formats like JSON and Markdown.