# internlm/mindsearch

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/internlm-mindsearch).**

6,877 stars · 689 forks · JavaScript · Apache-2.0

## Links

- GitHub: https://github.com/InternLM/MindSearch
- awesome-repositories: https://awesome-repositories.com/repository/internlm-mindsearch.md

## Topics

`ai-search-engine` `gpt` `llm` `llms` `multi-agent-systems` `perplexity-ai` `search` `searchgpt` `transformer` `web-search`

## Description

MindSearch is an LLM-based multi-agent search engine that decomposes complex user questions into targeted sub-queries and routes each to a specialized agent for parallel investigation. The system orchestrates multiple agents through a large language model, coordinating their tasks and interpreting search results to produce coherent answers from multiple sources.

The project provides a configurable search backend interface that allows switching between Google, DuckDuckGo, Brave, and Bing search APIs by updating a configuration attribute. It includes a terminal-based debug interface for testing and troubleshooting the multi-agent search pipeline during development, enabling headless backend execution without a graphical frontend.

The system synthesizes findings from parallel sub-query agents into a single coherent answer, addressing the original multi-faceted question. The documentation covers running the search backend without a frontend and debugging the search pipeline locally through the command-line interface.

## Tags

### Artificial Intelligence & ML

- [Multi-Agent Search Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-search-engines/multi-agent-search-engines.md) — Runs a search engine powered by large language models that decomposes queries and synthesizes results from multiple sources.
- [LLM-Driven Agent Loops](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-runtimes/llm-driven-agent-loops.md) — Uses a large language model to coordinate agent tasks, route sub-queries, and interpret search results.
- [Multi-Agent Search Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-search-engines/multi-agent-search-engines.md) — An AI search engine that decomposes complex queries into sub-questions and routes them to specialized agents for parallel investigation and answer synthesis.
- [Multi-Agent Synthesis Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-synthesis-systems.md) — Collects findings from parallel sub-query agents and merges them into a single coherent answer.

### Part of an Awesome List

- [Multi-Agent Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/multi-agent-frameworks.md) — Orchestrates multiple LLM agents to perform web searches, synthesize results, and produce coherent answers to multi-faceted questions.
- [Question Answering](https://awesome-repositories.com/f/awesome-lists/ai/question-answering.md) — Collects and merges findings from multiple sub-queries into a single coherent answer addressing the original complex question.
- [AI Search Engines](https://awesome-repositories.com/f/awesome-lists/ai/ai-search-engines.md) — Multi-agent framework for web search and reasoning.
- [Search Engines](https://awesome-repositories.com/f/awesome-lists/ai/search-engines.md) — Multi-agent framework for web search and reasoning.

### Data & Databases

- [Recursive Query Decomposition](https://awesome-repositories.com/f/data-databases/query-processing/complex-query-processors/recursive-query-decomposition.md) — Splits complex user questions into parallel sub-queries handled by specialized agents.
- [Sub-Query Decomposers](https://awesome-repositories.com/f/data-databases/query-processing/complex-query-processors/sub-query-decomposers.md) — Splits multi-faceted questions into smaller, targeted sub-queries and routes each to a specialized agent for parallel investigation. ([source](https://cdn.jsdelivr.net/gh/internlm/mindsearch@main/README.md))
- [Search Backend Swapping](https://awesome-repositories.com/f/data-databases/table-indexing-systems/search-backends/search-backend-swapping.md) — Changes the web search API used for retrieving results by updating a configuration attribute, supporting Google, DuckDuckGo, Brave, and Bing. ([source](https://cdn.jsdelivr.net/gh/internlm/mindsearch@main/README.md))
- [Web Search API Swappers](https://awesome-repositories.com/f/data-databases/table-indexing-systems/search-backends/search-backend-swapping/web-search-api-swappers.md) — Switches between Google, DuckDuckGo, Brave, and Bing search APIs by updating a configuration attribute.

### Web Development

- [Multi-Query Answer Synthesizers](https://awesome-repositories.com/f/web-development/search-result-management/search-result-injection/search-result-synthesizers/multi-query-answer-synthesizers.md) — Synthesizes findings from parallel sub-query agents into a single coherent answer for multi-faceted questions. ([source](https://cdn.jsdelivr.net/gh/internlm/mindsearch@main/README.md))