#1
A free, privacy-respecting metasearch engine that aggregates results from many search services without tracking or profiling users, designed for self-hosting.
- GitHub stars
- 39k
- Last commit
- yesterday
- Licence
- AGPL-3.0
- Self-hosted
- Yes
docs.searxng.org
SearXNG is a free internet metasearch engine. It sends your query to many search services and databases, merges the results into one page, and does so without tracking or profiling the people who use it. Topics list engines such as Google, Bing, Brave, DuckDuckGo, Qwant and Startpage among the sources it can combine.
The documentation is organized for both users and administrators. Users get search syntax, a list of configured engines and an explanation of why a private instance matters. Administrators get settings in settings.yml, engine configuration, plugins, a bot-protection limiter, optional Redis or Valkey storage, and installation guides covering containers, an installation script and step-by-step setups with Granian or uWSGI behind NGINX or Apache. A long catalog of engines extends beyond web search to sources such as arXiv, Crossref, GitHub and Mastodon.
SearXNG is written in Python under the AGPL-3.0 license. Because it is meant to be self-hosted, you can run your own instance for yourself or a group; many volunteers also publicly host instances. It appeals to people who want to reduce reliance on any one search engine and keep their queries private.
Key features
- Aggregates results from many search engines
- No user tracking or profiling
- Configurable engines and plugins
- Container and script-based installation
- Optional Redis or Valkey integration
- Bot protection limiter
Pricing: Free and open source under the AGPL-3.0 license.
#2
An autonomous research agent that searches the web and local documents using any LLM provider and writes detailed, cited research reports.
- GitHub stars
- 31k
- Last commit
- today
- Latest release
- v3.8.0
- Licence
- Apache-2.0
- Self-hosted
- Yes
gptr.dev
GPT Researcher is an open-source autonomous agent that performs deep research on a given task and writes up a report with citations. It can work from web sources and from local documents, and it works with any LLM provider, aiming for factual, unbiased output rather than a quick chatbot answer.
The project positions itself against several limits of manual and LLM-only research: manual work can take weeks, models trained on old data may hallucinate, token limits make long reports hard, and a narrow source set leads to shallow or wrong conclusions. Drawing on Plan-and-Solve and RAG ideas, it splits research into planning and parallelized agent work to increase speed and keep behavior stable. Customization options let you tailor domain-specific research agents, and topics note MCP server support.
GPT Researcher is written in Python and Apache-2.0 licensed, with documentation in several languages and a website at gptr.dev. You run it yourself with your own model API keys, and it suits analysts, students and developers who want automated, source-backed reports on a topic.
Key features
- Autonomous deep research on any topic
- Reports with source citations
- Web and local document research
- Works with any LLM provider
- Parallelized agent work for speed
- MCP server support
Pricing: GPT Researcher is free under the MIT license with no SaaS subscription; you pay only your own LLM and search providers. Managed deployments are arranged by contacting the maintainer.
#3
An open-source, Chromium-based browser built for AI agents, letting tools like Claude Code and Codex run web tasks in parallel with your logged-in accounts on your own machine.
- GitHub stars
- 14k
- Last commit
- today
- Latest release
- browserclaw/v0.52.0
- Licence
- AGPL-3.0
- Self-hosted
- Yes
browseros.com
BrowserOS is an open-source browser designed to be used by AI agents. It is positioned as a secondary browser that sits alongside Chrome rather than replacing it, giving agents a place to carry out web tasks while you keep browsing normally. The project presents itself as an alternative to AI browsers such as ChatGPT Atlas, Perplexity Comet and Dia.
You can import logins, bookmarks and extensions from Chrome in one click so agents work with your real accounts, then connect agents such as Claude Code, Codex, Cursor or VS Code, which BrowserOS detects on your machine. Agents run in parallel in their own tabs. A live dashboard on the new tab page shows which site each agent is on, and every session is saved as a replayable video with a step-by-step action timeline.
Everything runs locally on your machine and the project is free under the AGPL-3.0 licence. Its topics point to local model tooling such as Ollama and LM Studio and it exposes tools through the Model Context Protocol. Typical tasks include posting to social media, clearing an inbox, updating a CRM or filing expenses. An enterprise offering is linked from the repository.
Key features
- Chromium-based browser for AI agents
- One-click import of Chrome logins and extensions
- Auto-connects to Claude Code, Codex and Cursor
- Parallel agents in separate tabs
- Live dashboard of running agent tasks
- Replayable session recordings with action timeline
- Runs locally with MCP tools
Pricing: Free and open source under AGPL-3.0; the project also links to an Enterprise offering.
#4
Morphic is an open-source AI search engine that returns cited answers and renders them as rich, generated interface components instead of plain text.
- GitHub stars
- 9.3k
- Last commit
- yesterday
- Latest release
- v1.10.0
- Licence
- Apache-2.0
- Self-hosted
- Yes
- Hosted version
- Available
chat.morphic.sh
Morphic is an AI-powered search engine with a generative user interface. It answers questions with sources attached, and instead of returning plain markdown it renders richer inline components such as source-credited images, grids and headings built from a streamed specification.
It supports Quick and Adaptive search modes and lets you pick from several model providers, including OpenAI, Anthropic, Google and Ollama, as well as OpenAI-compatible endpoints. Search can run through Tavily, SearXNG, Brave or Exa. Chat history is stored in PostgreSQL, results can be shared through unique URLs, files can be uploaded, and Supabase Auth handles sign-in, with a guest mode for anonymous use.
Morphic is built with Next.js, React, TypeScript and Tailwind CSS under the Apache-2.0 licence. A Docker Compose setup starts PostgreSQL, Redis, SearXNG and the app together, so no separate search API key is required, although at least one AI provider key must be configured. It can also be deployed to Vercel.
Key features
- Cited AI answers grounded in search results
- Generative UI with rich inline components
- Quick and Adaptive search modes
- Selectable model providers including Ollama
- Shareable search results by unique URL
- Docker Compose deployment with bundled SearXNG
Pricing: Free and open source under Apache-2.0; self-hosting requires your own API key for at least one AI model provider.
#5
A self-hostable personal AI app that chats with local or cloud LLMs, answers from the web and your documents, builds custom agents and automates research.
- GitHub stars
- 38k
- Last commit
- 3 mo ago
- Latest release
- 2.0.0-beta.28
- Licence
- AGPL-3.0
- Self-hosted
- Yes
- Hosted version
- Available
khoj.dev
Khoj is a personal AI app that you can run on your own machine or scale up to an enterprise cloud deployment. You can chat with local or online models, such as Llama, Qwen, Gemma, Mistral, GPT, Claude, Gemini and DeepSeek, and get answers drawn from the internet and from your own documents, including images, PDFs, Markdown, org-mode files, Word documents and Notion pages.
It can be reached from a browser, Obsidian, Emacs, a desktop app, a phone or WhatsApp. Users create agents with their own knowledge, persona, chat model and tools, set up automations that deliver personal newsletters and smart notifications by email, and use advanced semantic search to find relevant documents. It can also generate images and speak responses aloud. The README highlights benchmark results for retrieval and reasoning and introduces Pipali, a separate open-source AI coworker for your own computer.
Khoj is written in Python and licensed under AGPL-3.0. You can self-host it, with offline models via llama.cpp, or use the hosted app. It suits individuals and teams who want an AI assistant grounded in their notes and files while keeping a choice of model.
Key features
- Chat with local or online LLMs
- Answers from the web and your documents
- Access from Obsidian, Emacs, WhatsApp and browser
- Custom agents with their own knowledge and tools
- Scheduled automations and newsletters
- Semantic search over personal documents
#6
Experimental search engine and crawler focused on text-oriented, small, and independent websites, which can run on modest hardware or as a white-label engine.
- GitHub stars
- 2.2k
- Last commit
- yesterday
- Latest release
- v24.10.0
- Self-hosted
- Yes
- Hosted version
- Available
marginalia-search.com
Marginalia Search is the source code of an independent internet search engine that indexes the small, old, and unusual parts of the web. The project describes itself as an experimental workshop as much as a public service, developing alternative ways to discover content and elevating the more human, non-commercial side of the Internet. It is written in Java, and the input lists its license only as other.
A side goal is to run the operation on affordable hardware with minimal operational overhead instead of datacenters. The system can run as a copy of Marginalia itself or as a white-label search engine over your own data, whether crawled or side-loaded, though its logic is not yet very configurable and reflects the project's goals. Setup uses run/setup.sh to download supplementary model data, and a local test environment is described in the repository.
The long-term plan is to be funded through grants, donations, and commercial API licenses, while non-commercial share-alike use remains free. Documentation is at docs.marginalia.nu and a public instance runs at marginalia-search.com. It suits people who value the small web and developers curious about building a search engine.
Key features
- Search index of small, text-focused websites
- Custom crawler and indexer
- Runs on affordable hardware
- White-label mode for your own data
- Public instance at marginalia-search.com
- Open documentation and setup scripts
Pricing: The public search is free to use; the project plans grants, donations, and commercial API licenses, with non-commercial share-alike use free.
#7
Scira is an open-source AI search and research tool that plans, retrieves and cites sources, accepting questions, PDFs and URLs.
- GitHub stars
- 12k
- Last commit
- 3 mo ago
- Licence
- AGPL-3.0
- Self-hosted
- Yes
- Hosted version
- Available
scira.ai
Scira, formerly called MiniPerplx, is a minimalistic AI search tool that finds information online and cites where it came from. The project describes it as an agentic research platform that plans, retrieves and cites, and it is available as a hosted site at scira.ai.
You can start by asking a question, uploading a PDF or pasting a link. Behind it, the README credits the Vercel AI SDK for model integration and streaming, Exa AI for web search and content retrieval, and Upstash for serverless Redis and rate limiting. It is written in TypeScript as a web app you can run yourself with your own provider keys.
Scira is licensed under AGPL-3.0, so modified versions offered over a network must share their source. It suits developers who want a reference AI search app to run or adapt, and individuals who want a cited, minimalistic alternative to conventional search.
Key features
- AI search with cited sources
- Agentic research that plans and retrieves
- PDF upload and URL input
- Built on the Vercel AI SDK
- Web search through Exa
- Self-hostable TypeScript app
Pricing: Free plan allows 3 searches a day. Pro costs $15 per month ($9 with a student email) and Max $60 per month for higher model limits and image generation.
#8
Browser Operator is an open-source, privacy-focused AI browser with a multi-agent platform that automates web research and tasks using cloud or local models.
- GitHub stars
- 513
- Last commit
- 2 days ago
- Latest release
- v0.6.0
- Licence
- BSD-3-Clause
browseroperator.io
Browser Operator is an open-source AI browser that runs agents on the web on your behalf. It is a desktop application for macOS and Windows built to support research, analysis and automation, with processing done locally on your machine. The project describes itself as an open alternative to AI browsers such as ChatGPT Atlas, Perplexity Comet, Dia and the Microsoft Copilot Edge browser.
Its multi-agent platform uses specialized agents that work together on complex web tasks. You choose an AI provider in the settings, including OpenRouter, OpenAI, Groq or LiteLLM, and local models through Ollama allow fully offline operation. Through LiteLLM it is compatible with more than 100 models from OpenAI, Claude, Gemini, Llama and others. The repository topics also mention MCP client support and LangGraph.
Listed use cases include literature reviews and market research, shopping comparison and price monitoring, and business automation such as talent sourcing, lead generation and compliance audits. The system requirements list macOS 10.15 or Windows 10 (64-bit), 8 GB of RAM and 2 GB of free disk space. It is released under the BSD-3-Clause license.
Key features
- Multi-agent automation for web tasks
- Privacy-first local processing
- Works with OpenRouter, OpenAI, Groq and LiteLLM
- Offline operation with local Ollama models
- Desktop builds for macOS and Windows
- MCP client support
Pricing: Free and open source under the BSD-3-Clause license; cloud AI providers bill separately, while local models need no provider account.
#9
Farfalle is a free, Apache-licensed, self-hostable AI search engine that answers questions using local or cloud LLMs, positioned as an open alternative to Perplexity.
- GitHub stars
- 3.5k
- Last commit
- 2 yr ago
- Licence
- Apache-2.0
- Self-hosted
- Yes
- Hosted version
- Available
farfalle.dev
Farfalle is an open-source AI-powered search engine, described by its creator as a Perplexity clone, that lets you search the web and get synthesized answers. It is aimed at developers and privacy-minded users who want to self-host this kind of search experience and choose their own model provider rather than depend on a closed commercial service.
It supports local models through Ollama, such as Llama 3, Mistral, Gemma and Phi-3, custom models through LiteLLM, and cloud models including Groq-hosted Llama 3 and OpenAI's GPT-4o. Search results can come from multiple providers, including Tavily, SearXNG, Serper or Bing, and the project supports chat history, an agent mode that plans and executes a search for better results, and expert search.
The stack uses Next.js for the frontend and FastAPI for the backend, with Redis for rate limiting and shadcn/ui components. Running it locally requires Docker and, for local models, Ollama; API keys for search and cloud model providers are optional depending on which features are used. Farfalle is written in TypeScript and released under the Apache-2.0 license, with a cloud-model-only live demo available.
Key features
- AI-generated answers from web search
- Local LLM support via Ollama
- Multiple search providers (Tavily, SearXNG, Serper, Bing)
- Agent mode that plans multi-step searches
- Chat history and expert search modes
- Docker-based self-hosted deployment
Pricing: Free and open source under the Apache-2.0 license; cloud model and search providers used with it are billed separately, while local Ollama models require no provider account.
#10
Open Deep Research is a Next.js web interface for an iterative AI research assistant that searches the web and writes sourced markdown reports.
- GitHub stars
- 878
- Last commit
- 1 yr ago
- Licence
- MIT
- Self-hosted
- Yes
- Hosted version
- Available
anotherwrapper.com
Open Deep Research is an open-source alternative to the deep research features offered by OpenAI and Gemini. It is a web interface built with Next.js and shadcn/ui on top of the original Deep Research command-line project, turning that CLI tool into a visual app for starting and monitoring research tasks.
The system combines search via FireCrawl, web scraping and language models through OpenAI. It researches iteratively and recursively, uses the model to generate targeted search queries and follow-up questions, and runs multiple searches in parallel. Depth and breadth parameters control scope. Output is a detailed markdown report with findings and sources, viewable in a built-in markdown viewer, shown with real-time progress, and downloadable.
API keys for OpenAI and FireCrawl are required and are stored in HTTP-only cookies. You can try a hosted version at anotherwrapper.com with your own keys or host it yourself with Node.js. The project is MIT licensed and sponsored by AnotherWrapper.
Key features
- Iterative, recursive web research
- LLM-generated search queries and follow-ups
- Adjustable research depth and breadth
- Markdown reports with cited sources
- Real-time research progress display
- API keys held in HTTP-only cookies
Pricing: Free and open source under the MIT license; you supply your own OpenAI and FireCrawl API keys.
Perplexity alternatives: questions
- What is the best open-source alternative to Perplexity?
- SearXNG is the top-ranked open-source alternative to Perplexity on Enlisted: A free, privacy-respecting metasearch engine that aggregates results from many search services without tracking or profiling users, designed for self-hosting. Other strong options are GPT Researcher, BrowserOS, Morphic and Khoj.
- What are the best commercial alternatives to Perplexity?
- You.com, Microsoft Copilot, Kagi, Grok and Claude are among the hosted, closed-source alternatives to Perplexity listed on Enlisted, which lists 35 in total. Compare their pricing and features on each tool page.
- Are these Perplexity alternatives free?
- All 10 are open source, so the code is free to use under its licence, and all of them can be self-hosted on your own server or computer. 6 also offer a paid or managed cloud version if you'd rather not host it yourself.
- How is this list of Perplexity alternatives ranked?
- By a score built from GitHub stars, star growth over the last 30 days and how recently the code changed. 6 of these projects shipped code in the last 30 days. Data is refreshed daily, and nobody can pay to move up.