A fully automated personal AI research assistant that supports multiple large language models to help users conduct in-depth research and information gathering.
One-Minute Overview#
Auto-Deep-Research is a fully automated personal AI research assistant built on the AutoAgent framework. It supports multiple mainstream LLM models (like Claude, GPT-4, Gemini, etc.) and enables AI agents to automatically execute deep research tasks without requiring code writing. It's ideal for researchers, analysts, or content creators who need extensive information collection and analysis.
Core Value: By simplifying the creation of AI agents, it enables everyone to have powerful automated research capabilities.
Quick Start#
Installation Difficulty: Medium - Requires Docker environment and API key configuration
conda create -n auto_deep_research python=3.10
conda activate auto_deep_research
git clone https://github.com/HKUDS/Auto-Deep-Research.git
cd Auto-Deep-Research
pip install -e .
Is this suitable for me?
- ✅ Academic Research: Automatically collect and organize academic literature
- ✅ Market Research: Quickly gather industry trends and competitor information
- ✅ Content Creation: Provide rich reference materials for articles and reports
- ❌ Simple Information Queries: For basic factual questions, traditional search engines are more efficient
Core Capabilities#
1. Multi-LLM Support - Adapt to different model preferences#
- Supports multiple mainstream LLM models including Anthropic, OpenAI, Mistral, Gemini, Huggingface
- Users can select the most suitable model based on their needs Actual Value: Users aren't limited to a single model and can flexibly choose the most appropriate AI assistant based on task requirements and budget
2. Automated Deep Research - Free up researchers' time#
- AI agents can independently plan research steps, execute searches, analyze, and summarize
- Supports multi-round interactions and deep information mining Actual Value: Compresses research work that would normally take hours into minutes, significantly improving work efficiency
3. No Coding Required - Lower the barrier to entry#
- Provides command-line interface, no code writing required
- One-click launch functionality simplifies configuration Actual Value: Enables researchers without programming backgrounds to leverage AI agents for efficient research
4. Environment Isolation - Ensure secure research environment#
- Uses Docker containerization for secure research environment
- Supports importing browser cookies for enhanced access to specific websites Actual Value: Research in isolated environments prevents contamination of local systems while providing more authentic web access capabilities
Tech Stack & Integration#
Development Language: Python Main Dependencies:
- Docker (containerization environment)
- Litellm (unified multi-LLM interface)
- AutoAgent framework (AI agent foundation)
Integration Method: Command-line tool / API
Maintenance Status#
- Development Activity: Actively developed with a clear feature roadmap
- Recent Updates: Recently released with rapid iteration ongoing
- Community Response: Active community support with Slack and Discord discussion groups
Documentation & Learning Resources#
- Documentation Quality: Basic but complete, with configuration examples for various LLMs
- Official Documentation: README in the GitHub repository
- Example Code: Configuration examples for multiple LLM providers