InternLM/MindSearch

Health v2 · maintenance only

Adoption not part of the score

6918 stars · 693 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

MindSearch is an open-source, LLM-based multi-agent framework that mimics human cognition to perform deep web searches, similar to Perplexity.ai Pro and SearchGPT. It decomposes user queries into parallel sub-questions, searches via pluggable engines (DuckDuckGo, Bing, Brave, Google, Tencent), and serves results through a FastAPI backend with a React frontend.

Use cases

• build a self-hosted Perplexity.ai alternative
• run deep AI-powered web searches that break questions into sub-queries
• create a multi-agent search assistant over my own LLM
• plug different search engine APIs into an LLM search pipeline
• deploy an AI search chat interface with a React frontend
• research multi-agent web search architectures

When to choose

• you want an open-source, self-hosted deep AI search engine
• you need to experiment with multi-agent query decomposition and web search
• you want to swap in your own LLM (InternLM, GPT-4) or search API
• you need both a backend API and a ready-made web UI

When to avoid

• you need a simple single-call search API without agent orchestration
• you cannot access any LLM backend or search engine API keys
• you need a production-grade, heavily maintained enterprise product
• you want a fully managed hosted service with no setup

Facets

framework · maturity active

agent-framework search-engine web-scraping llm-inference rag artificial-intelligence large-language-models web-development python self-hosted multi-agent ai-search-engine perplexity-alternative deep-search fastapi react-frontend search ai-agents nodejs web-server docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="InternLM/MindSearch")