deep-research and deep-research-web-ui
The second project, AnotiaWang/deep-research-web-ui, is a web-based user interface designed to support and interact with the iterative research capabilities provided by the dzhng/deep-research project, making them complements.
About deep-research
dzhng/deep-research
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.
Implements a recursive research loop with configurable depth and breadth parameters, using LLM-generated search queries fed through Firecrawl for web scraping and content extraction. The agent maintains context across iterations to refine research directions based on accumulated learnings, then synthesizes findings into structured markdown reports. Supports multiple LLM backends including OpenAI, DeepSeek R1 via Fireworks, and local OpenAI-compatible endpoints, with tunable concurrency limits for API rate management.
About deep-research-web-ui
AnotiaWang/deep-research-web-ui
(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.
Executes iterative research through a tree-structured visualization of the search process, with real-time streaming responses directly in the browser. Supports multiple LLM providers (OpenAI, DeepSeek, Ollama, OpenRouter) and search backends (Tavily, Firecrawl, Google PSE) via plain prompts for broader compatibility, plus server mode for centralized API key management via environment variables.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work