open_deep_research is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named open_deep_research among their alternatives. The relationship is not symmetric — how open_deep_research rates them is a separate judgement, made when open_deep_research is analysed in its own right.
calls open_deep_research “same deep research agent with LangChain integration; archived, choose if you want official LangChain implementation.”
An autonomous agent that conducts deep research on any data using any LLM providers
calls open_deep_research “Cloud-oriented sibling from the same org; choose if you want the non-local version of this agent.”
Fully local web research and report writing assistant
calls open_deep_research “When you want an archived LangChain reference implementation for deep research.”
Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
calls open_deep_research “archived LangChain deep-research implementation; choose it only if you need a minimal baseline and don't require maintenance.”
Tongyi Deep Research, the Leading Open-source Deep Research Agent
calls open_deep_research “archived predecessor, only if you need the exact historical LangChain implementation”
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.
calls open_deep_research “Use if you want a LangChain-based deep research agent; it is archived, so for legacy use only.”
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.