Home › RAG and Search › Auto-Deep-Research

Auto-Deep-Research - AI RAG and Search Tool

Overview

Auto-Deep-Research is an open-source, fully automated personal AI assistant designed to streamline research workflows. According to the project's GitHub repository, it is built on the AutoAgent framework and positions itself as a cost-effective alternative to OpenAI's Deep Research. The tool focuses on automating end-to-end research tasks such as ingesting documents, performing retrieval-augmented search (RAG), orchestrating multi-step queries to language models, and providing function-calling interactions for structured outputs. Targeted at researchers, knowledge workers, and developers, Auto-Deep-Research supports integration with various LLMs, enables file uploads for document-centric retrieval, and offers a one-click launch to simplify deployment and experimentation. Typical uses include automated literature reviews, extracting structured insights from uploaded files, running multi-turn research queries that call external functions, and iterating on search-driven prompt chains. According to the repository, the architecture is extensible via the underlying AutoAgent framework, letting users swap LLM backends, add custom function handlers, and adapt retrieval connectors for their own document stores.

Installation

Install via docker:

git clone https://github.com/HKUDS/Auto-Deep-Research
cd Auto-Deep-Research && docker compose up --build

Key Features

  • Built on the AutoAgent framework for automated multi-step research orchestration.
  • Integration hooks for various LLM backends (swapable LLM providers supported).
  • Function-calling interactions to produce structured, executable outputs from LLMs.
  • File upload and document ingestion for retrieval-augmented search (RAG) workflows.
  • One-click launch to quickly start the system locally or in containerized environments.

Community

The project is hosted on GitHub (see repository URL) and follows an open-source contribution model. The issue tracker, pull requests, and README are the primary places for community discussions, bug reports, and feature requests. For latest activity, contributors and users should consult the repository's commits, issues, and discussion threads directly.

Last Refreshed: 2026-01-09

Key Information

  • Category: RAG and Search
  • Type: AI RAG and Search Tool
Visit Official Website

Related Tools

Crawl4AI

An open-source, LLM-friendly tool designed to crawl and extract data, facilitating content aggregation for AI applications.
Perplexica

Open-source AI-powered search engine that performs deep web research to generate and cite answers.
GPT Researcher

An LLM-based autonomous agent that conducts deep local and web research on any topic and generates long reports with citations, with support for connecting to specialized data sources.
Maxun

An open-source no-code web data extraction platform that lets users train a robot in minutes to automatically scrape websites and convert them into APIs and spreadsheets.
Open Deep Research Agent

An open–source deep research AI agent that utilizes reasoning models to conduct in–depth factual research. It separates planning and research execution for detailed report generation.
GPT-RAG

GPT-RAG is an enterprise-grade Retrieval-Augmented Generation (RAG) solution accelerator designed for integrating Azure Cognitive Search and Azure OpenAI services to power ChatGPT-style and Q&A experiences. It provides a modular architecture featuring data ingestion, an orchestrator (with options for Semantic Kernel functions or AutoGen-driven agentic workflows), and customizable front-end interfaces for efficient deployment in secure, enterprise environments.