Morphic

An open-source AI search engine you can self-host with Docker, with cited answers, Ollama support, and quick or multi-step web research.

Morphic is a self-hosted AI search engine for people who want answers backed by web sources and control over the search interface they use. It combines web searches and URL reading with AI-generated responses, so you can examine the sources behind an answer. It's open source under Apache 2.0, and you can run your own instance with Docker or use the hosted website.

Quick mode handles fast lookups. Adaptive mode performs deeper, multi-step research. Answers can include source-credited images, grids and headings alongside text, with the interface rendering these elements as the response arrives. That makes its answer format a useful distinction for readers who want visual results alongside citations.

Morphic supports Ollama for local models, plus OpenAI, Anthropic, Google, Vercel AI Gateway and OpenAI-compatible providers. The interface includes a model selector. Self-hosting the application doesn't make every request local: cloud model providers process requests externally, and web research needs network access. Search backends include Tavily, SearXNG, Brave and Exa.

For ongoing research, Morphic supports file uploads, stores chat history in PostgreSQL and lets you share results through unique URLs. It supports accounts through Supabase Auth, while guest mode allows anonymous use.

AI Search and Deep Research Docker Web Multi-user access Ollama integration OpenAI-compatible API RAG Source citations Web search

Are you the owner or maker of Morphic?

Claim this page with an email at morphic.sh. Morphic gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.

Want more people to find Morphic?Promote it

Something wrong or outdated on this page?

Similar to Morphic

View all tools

DocsGPT

Self-hosted AI document search and agents with source citations. Run local models through Ollama, vLLM or llama.cpp, including fully offline deployments.

18.3KUpdated 24 hours agoMIT

macOS · Windows · Linux · Docker · Web#Human approval#Hybrid search#llama.cpp backend

DocsGPT is an MIT-licensed, open-source platform for teams that want AI search, assistants and agents over their own documents. It can run on your servers with local models, including fully air-gapped deployments where documents and questions stay inside your network. Answers include the source title and page number so readers can check the evidence.

Agent FrameworksAI Search and Deep ResearchAI Workflow AutomationChat With Your DocumentsRAG Frameworks and Pipelines

GPT Researcher

A self-hosted AI research agent that combines web sources and local documents into cited reports. Supports Ollama and uses the Apache 2.0 license.

29.8KUpdated 4 days agoApache-2.0

Docker · Web#MCP#Multi-agent workflows#Ollama integration

Local Deep Research

3 videos

Self-hosted AI research assistant for web, papers and private documents. Runs on Windows, macOS and Linux with Ollama or cloud models. MIT licensed.

9.1KUpdated 21 hours agoMIT

macOS · Windows · Linux · Docker · Web#llama.cpp backend#MCP#Multi-user access

Onyx

1 video

Self-hosted AI search across company apps, with local-model options and source-permission sync in the Enterprise Edition.

32.3KUpdated 24 hours ago

Docker · Web · Browser Extension#MCP#Multi-user access#Ollama integration

Vane (formerly Perplexica)

2 videos

A self-hosted AI answer engine that cites web sources and works with Ollama, local model servers, or cloud models.

36.9KUpdated 4 weeks agoMIT

Docker · Web#Multimodal input#Ollama integration#OpenAI-compatible API

Farfalle

An open-source AI search engine you can self-host with Docker, using Ollama for local models or OpenAI, Groq and LiteLLM for other backends.

3.5KUpdated 2 years agoApache-2.0

Docker · Web#Ollama integration#Web search

Farfalle is a self-hosted AI search engine for people who want a Perplexity-style search app with a choice of local or cloud models. It combines web search with model-generated answers and includes an agent that plans and carries out searches. The code is open source under Apache 2.0.