calls deep-research “same deep research agent in JavaScript with SSE/MCP server support.”
An autonomous agent that conducts deep research on any data using any LLM providers
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 deep-research among their alternatives. The relationship is not symmetric — how deep-research rates them is a separate judgement, made when deep-research is analysed in its own right.
calls deep-research “same deep research agent in JavaScript with SSE/MCP server support.”
An autonomous agent that conducts deep research on any data using any LLM providers
calls deep-research “LLM-agnostic deep research with SSE/MCP support; choose it for flexible model choice and streaming.”
Tongyi Deep Research, the Leading Open-source Deep Research Agent
calls deep-research “supports any LLM via SSE/MCP for model flexibility”
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 deep-research “Same iterative deep-research loop; choose if you prefer a Node/TypeScript implementation with SSE/MCP endpoints.”
Fully local web research and report writing assistant
calls deep-research “Use when you need a JavaScript/TypeScript deep-research library or want to expose research via SSE/MCP server.”
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
calls deep-research “Use if you want a JavaScript/Node deep research service with SSE/MCP integration.”
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.
calls deep-research “Choose for a JavaScript/TypeScript implementation with SSE and MCP support, if you are building in the Node.js ecosystem.”
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
calls deep-research “When you need a model-agnostic deep research service exposed via SSE or MCP.”
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 deep-research “narrower: LLM-agnostic deep research report generation, no experiment loop.”
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞