deep research / report generation
STORM is an LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Use when you want a widely adopted, actively maintained Python deep-research agent with pluggable LLM providers and citation-backed reports.
An autonomous agent that conducts deep research on any data using any LLM providers
Use when you want an Apache-licensed deep research agent with strong support for Tongyi models and Chinese/English content.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Use when you need a research agent optimized for complex, prediction-oriented queries with strong BrowseComp performance.
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.
Use when you want a deep research tool focused on reasoning over private data with integrated vector search.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Use when you want an autonomous research agent that generates complete academic papers from idea to final draft.
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Use when you need fully local research without sending data to cloud APIs, accepting the need for local LLM hardware.
Fully local web research and report writing assistant
Use when you need a JavaScript/TypeScript deep-research library or want to expose research via SSE/MCP server.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Use when you are already using the OpenAI Agents SDK and need a lightweight, iterative deep-research implementation.
An implementation of iterative deep research using the OpenAI Agents SDK
Use when you prefer a LangGraph-based multi-agent architecture with credibility scoring for research reports.
Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search
Use when you want a local-first research platform that can switch between cloud and self-hosted models with multi-step workflows.
Cerno is a local-first research platform that leverages agentic AI to break down complex queries into verifiable, multi-step workflows. Switch seamlessly between cloud LLMs and self-hosted models, track every reasoning step, and optimize cost and tokens—all while keeping your data on your machine.
Use when you need a research framework using progressive search and cross-evaluation, especially for Chinese-language content.
A deep research framework based on progressive search and cross-evaluation.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Use when you need a minimal, understandable deep-research agent prototype for learning or simple tasks, not a production system.
Deeper Seeker is an simpler OSS version of OpenAI's latest Deep Research feature in ChatGPT.It is an agentic research tool to reason , create multi step tasks , synthesize data from multiple online resources and create neat reports
These projects were analysed and named storm among their alternatives. The relationship is not symmetric — how storm rates them is a separate judgement, made when storm is analysed in its own right.
calls storm “knowledge curation system that researches and writes full reports with citations”
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 storm “Knowledge-curation approach to report generation from multiple perspectives; choose for academic-style synthesis.”
Fully local web research and report writing assistant
calls storm “Use if you want a structured knowledge-curation pipeline that generates a cited report from a topic.”
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 storm “Choose for a report-generation pipeline that produces structured, citable articles, rather than interactive Q&A on private data.”
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.