Deep Research
StaleDescription
AI-powered research assistant that performs iterative deep research on any topic by combining search engines, web scraping, and LLMs
Key Features
- Iterative deep research with configurable breadth and depth parameters
- Intelligent query generation using LLMs based on research goals and prior findings
- Concurrent processing for multiple parallel searches and result analysis
- Comprehensive markdown report generation with sources and references
- Supports multiple LLM backends: OpenAI o3-mini, DeepSeek R1, and custom endpoints
- Minimal implementation (~500 LoC) designed for easy understanding and extension
Use Cases
💡 Deep research on any topic with iterative refinement
💡 Competitive analysis and market research automation
💡 Academic literature review and fact-checking
💡 Technology scouting and trend analysis
💡 Investigative journalism and background research
Strengths & Limitations
✅ Strengths
- • High community interest (19.6k stars)
- • Permissive open-source license (MIT)
- • Responsive to issues, low backlog
Categories
Quick Start
1. Clone: git clone https://github.com/dzhng/deep-research && cd deep-research
2. Install: npm install
3. Configure: create .env.local with FIRECRAWL_KEY and OPENAI_KEY
4. Run: npm start
5. Enter query, set breadth (3-10) and depth (1-5), answer follow-up questions