Logo
Deploy Now

SaaS Alternative

Perplexity You.com Bing Copilot Google Gemini

Categories

Productivity Developer Tools Privacy AI LLM Research Search Answer Engine

Stars

8977

Forks

2340

Watchers

63

Developer links

Last Updated: 07-15-2026 04:11 PM (UTC)

Morphic

Perplexity's answer-engine experience, self-hostable and open-source: Morphic searches the web and writes cited answers. Instead of returning a list of links, it searches the web, reads the sources, and generates a complete answer with inline numbered citations. The generative UI streams rich components, source cards with thumbnails, image grids, syntax-highlighted code, and LaTeX math, rather than plain markdown. Quick mode answers fast; Adaptive mode runs deeper multi-step research. Search backends are pluggable: the Docker Compose bundle ships with a private SearXNG instance so no search API key is required, and Tavily, Brave, and Exa are supported alternatives. LLM providers include OpenAI, Anthropic, Google, Ollama, and any OpenAI-compatible endpoint, with per-mode model mapping - fast, cheap models for quick searches, stronger models for adaptive research, tuning the cost-quality trade-off per query type. An inspector panel exposes tool execution during multi-step research, and AI-suggested follow-up questions keep an investigation moving. Chat history persists in PostgreSQL, results are shareable by URL, file uploads feed context into queries, and optional Supabase authentication adds multi-user or guest access. Because the default search path is your private SearXNG instance, research topics never hit a commercial search API - and with local Ollama models the marginal cost of a query approaches zero. Built with Next.js, TypeScript, and the Vercel AI SDK under Apache 2.0.

Morphic

Benefits

  • Perplexity Without the Subscription
  • A self-hosted instance replaces a per-seat AI search subscription with flat hosting plus your own API keys, or near-zero marginal cost with local Ollama models.
  • Private Search Out of the Box
  • The bundled SearXNG metasearch engine means queries never hit a commercial search API by default; your research topics stay on your infrastructure.
  • Answers You Can Verify
  • Every claim carries an inline numbered citation linking to its source, so answers are checkable instead of being an opaque model output.
  • Model Choice Per Task
  • Map fast, cheap models to quick searches and stronger models to adaptive research mode, tuning the cost and quality trade-off per query type.

Features

  • Cited Generative Answers
  • The engine searches, reads 10-20 sources, and synthesizes a comprehensive answer with inline citations and AI-suggested follow-up questions.
  • Generative UI
  • Answers stream as rich components from a JSON spec: source cards with thumbnails, image grids, code blocks, and LaTeX rendering.
  • Quick and Adaptive Search Modes
  • Quick mode for fast single-pass answers; Adaptive mode plans and executes multi-step research for deeper questions, with an inspector panel exposing tool execution.
  • Pluggable Search Backends
  • Bundled SearXNG requires no API key; Tavily, Brave, and Exa are supported alternatives, with URL-specific search and content extraction via Tavily or Jina.
  • Multi-Provider LLM Support
  • OpenAI, Anthropic, Google, Ollama, Vercel AI Gateway, and OpenAI-compatible endpoints, with a dynamic model selector and per-mode model configuration.
  • History, Sharing, and Auth
  • PostgreSQL-backed chat history, shareable result URLs, file uploads, and optional Supabase authentication with guest mode.