# Morphic

> Open source AI search engine with cited answers and a generated interface

Steal this: Search answers built from components (images, grids, headings) out of a streamed JSON spec.

- Category: Agents & dev (`agents`)
- Tags: `open-source`
- Official: https://chat.morphic.sh
- GitHub: https://github.com/miurla/morphic
- Wunderlust: https://wunderlust.xyz/r/morphic
- Image: https://wunderlust.xyz/media/morphic-poster.jpg
- Video preview: https://wunderlust.xyz/media/morphic.webm
- Added: 2026-11-10

## What it is

An AI search engine that answers with cited sources and builds the answer from rich components such as credited images, grids and headings. It supports many model and search providers and runs with Docker.

## What it’s for

For running your own AI search engine with the model and search backend you choose.

## Benefits

- Answers with cited sources
- Many model providers, including local Ollama
- Docker setup includes SearXNG, so no extra search key

## Caveats

- Needs at least one AI provider key
- Apache-2.0 license

## Similar on Wunderlust

- [Moonshine Voice](https://wunderlust.xyz/r/moonshine-voice.md): Open source on-device speech to text and text to speech
- [Ternary Bonsai 2](https://wunderlust.xyz/r/ternary-bonsai-2.md): Family of 2B, 4B and 9B ternary language models for local use
- [Ollama](https://wunderlust.xyz/r/ollama.md): Runtime for running language models on your own machine
- [LitServe](https://wunderlust.xyz/r/litserve.md): Python framework for serving AI models as APIs with batching and scaling
- [Postiz](https://wunderlust.xyz/r/postiz.md): Open-source agentic scheduling tool for social media posts
- [Open Notebook](https://wunderlust.xyz/r/open-notebook.md): An open source, self-hosted alternative to NotebookLM