# InternLM/MindSearch

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

Repository: https://github.com/InternLM/MindSearch
Canonical: https://ross.abutalabs.com/products/mindsearch
Language: JavaScript
License: Apache-2.0
License Family: permissive
Topics: gpt, llm, llms, search, transformer, ai-search-engine, multi-agent-systems, web-search, perplexity-ai, searchgpt
Last push: 2025-07-04T10:06:45+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 30, release rhythm 8, longevity 54
- inputs: {"age_days": 766, "days_push": 425, "days_rel": 666, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6918, forks 693 (observed 2026-08-28T04:09:51.394182+00:00)

## What it is
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
- artifact type: framework
- maturity: active
- function: agent-framework, search-engine, web-scraping, llm-inference, rag
- domain: artificial-intelligence, large-language-models, web-development
- platform: python, self-hosted
- tags: multi-agent, ai-search-engine, perplexity-alternative, deep-search, fastapi, react-frontend, search, ai-agents, nodejs, web-server, docker

## Member repositories
- InternLM/MindSearch (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.394182+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:41:26.354562+00:00, confidence not recorded.
  - readme: https://github.com/InternLM/MindSearch (fetched 2026-08-28T04:09:51.394182+00:00, sha b6f2571a988d)
- Data as of 2026-08-30T08:39:29.467469+00:00.