#129 · Primary category： Knowledge Base & RAG
MiniSearch
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space
Project last updated：08/30/26
GitHub Stars
586
Forks
66
Contributors
16
License
Apache-2.0
Why we included this project
MiniSearch is a self-hosted search engine that pairs live web results with an AI assistant, and the assistant can run entirely inside your browser tab on WebGPU or CPU. A basic setup therefore needs no API key and no separate inference server; the bundled SearXNG metasearch instance aggregates results and reranks them locally before they reach you. Privacy-minded teams will like that search history, cached results, and chats stay in the browser, and that you can proxy your own OpenAI-compatible backend without exposing its key. You can also set it as your default search engine or trigger it from Raycast, which makes it easy to fold into daily work. For verifiable answers rather than a black-box chatbot, the cited responses, conversation memory, and on-demand reasoning make this a practical self-hosted alternative to hosted AI search.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience