Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

awesome-deep-research

A list of things related to Deep Research at one place
https://github.com/demfier/awesome-deep-research

Last synced: 12 days ago
JSON representation

  • 🤖 Deep Research Systems

    • 🔬 Specialized Research Assistants

      • Elicit - AI-powered literature review and research automation.
      • PaperQA - AI-driven paper-based Q&A system for research.
      • ResearchRabbit - AI tool for discovering and tracking academic papers.
      • MetaGPT - Multi-agent framework for collaborative AI research.
      • PaperQA - AI-driven paper-based Q&A system for research.
      • ResearchRabbit - AI tool for discovering and tracking academic papers.
      • MetaGPT - Multi-agent framework for collaborative AI research.
      • LitLLM - A toolkit for leveraging large language models to assist in scientific literature reviews, helping researchers identify, synthesize, and contextualize relevant prior work more efficiently.
      • EmergentMind - A tool to find the most relevant computer science papers based on a query on arXiv and synthesize an answer with citations.
      • LitLLM - A toolkit for leveraging large language models to assist in scientific literature reviews, helping researchers identify, synthesize, and contextualize relevant prior work more efficiently.
      • EmergentMind - A tool to find the most relevant computer science papers based on a query on arXiv and synthesize an answer with citations.

    • 🔓 Commercial Deep Research Platforms

      • OpenAI's Deep Research - An AI agent that uses reasoning to synthesize large amounts of online information and complete multi-step research tasks.
      • Gemini's Deep Research - An agentic feature in Gemini that automatically browses websites, thinks through findings, and creates insightful multi-page reports.
      • Perplexity's Deep Research - Allows users to conduct in-depth research and analysis, delivering comprehensive reports.
      • Manus AI - An autonomous AI agent capable of independently carrying out complex real-world tasks.
      • Agents Inc - Provides specialized AI agents for tasks such as Global News Radar, Scientific Knowledge, and Patent Analysis, particularly useful for research in science and policy domains.
      • Pandi - An answer engine that compiles search results into concise webpages, providing multi-modal answers with citations, ideal for quick research synthesis.
      • OpenAI's Deep Research - An AI agent that uses reasoning to synthesize large amounts of online information and complete multi-step research tasks.
      • Gemini's Deep Research - An agentic feature in Gemini that automatically browses websites, thinks through findings, and creates insightful multi-page reports.
      • Perplexity's Deep Research - Allows users to conduct in-depth research and analysis, delivering comprehensive reports.
      • Manus AI - An autonomous AI agent capable of independently carrying out complex real-world tasks.
      • Agents Inc - Provides specialized AI agents for tasks such as Global News Radar, Scientific Knowledge, and Patent Analysis, particularly useful for research in science and policy domains.
      • Pandi - An answer engine that compiles search results into concise webpages, providing multi-modal answers with citations, ideal for quick research synthesis.

    • 🌐 Open-Source Deep Research Implementations

      • OpenManus - An open-source alternative to Manus AI, allowing users to create AI agents without invite codes.
      • Autogen - A framework for developing multi-agent conversation systems.
      • Crew AI - A framework for building collaborative AI agents.
      • OpenHands (fka OpenDevin) - An agentic AI software engineer that can understand high-level instructions and write code.
      • LocalGPT - Allows conversing with documents locally without compromising privacy.
      • DeepResearcher - A framework for scaling deep research via reinforcement learning in real-world environments.
      • Search-R1 - An efficient RL training framework for reasoning & search engine calling for LLMs.
      • OpenManus-RL - Explores reinforcement learning-based tuning methods for LLM agents.
      • XAgent - An open-source experimental LLM-driven autonomous agent for solving various tasks, featuring autonomy, safety, and a dual-loop mechanism.
      • WrenAI - An open-source AI-powered data assistant for retrieving results and insights without SQL, useful for non-programmers in research.
      • Local Deep Researcher - A fully local web research assistant that uses LLMs hosted by Ollama or LMStudio to generate search queries, gather results, summarize findings, and iterate through multiple research cycles.
      • OpenManus - An open-source alternative to Manus AI, allowing users to create AI agents without invite codes.
      • Autogen - A framework for developing multi-agent conversation systems.
      • Crew AI - A framework for building collaborative AI agents.
      • OpenHands (fka OpenDevin) - An agentic AI software engineer that can understand high-level instructions and write code.
      • LocalGPT - Allows conversing with documents locally without compromising privacy.
      • DeepResearcher - A framework for scaling deep research via reinforcement learning in real-world environments.
      • Search-R1 - An efficient RL training framework for reasoning & search engine calling for LLMs.
      • OpenManus-RL - Explores reinforcement learning-based tuning methods for LLM agents.
      • XAgent - An open-source experimental LLM-driven autonomous agent for solving various tasks, featuring autonomy, safety, and a dual-loop mechanism.
      • WrenAI - An open-source AI-powered data assistant for retrieving results and insights without SQL, useful for non-programmers in research.
      • Local Deep Researcher - A fully local web research assistant that uses LLMs hosted by Ollama or LMStudio to generate search queries, gather results, summarize findings, and iterate through multiple research cycles.
      • DeepSearcher - Combines cutting-edge LLMs and Vector Databases to perform search, evaluation, and reasoning based on private data, providing highly accurate answers for enterprise knowledge management.
      • Deep Research - A minimal implementation (<500 LOC) of a deep research agent that combines search engines, web scraping, and LLMs to perform iterative research on any topic.
      • OpenDeepResearcher - An AI researcher that continuously searches for information based on a user query, using SERPAPI for Google searches, Jina for webpage content extraction, and OpenRouter (default: claude-3.5-haiku) for generating search queries and evaluating relevance.
      • Deep Research Agent with Motia Framework - A powerful research assistant that leverages the Motia Framework to perform comprehensive web research on any topic and question.
      • DeepSearcher - Combines cutting-edge LLMs and Vector Databases to perform search, evaluation, and reasoning based on private data, providing highly accurate answers for enterprise knowledge management.
      • Deep Research - A minimal implementation (<500 LOC) of a deep research agent that combines search engines, web scraping, and LLMs to perform iterative research on any topic.
      • OpenDeepResearcher - An AI researcher that continuously searches for information based on a user query, using SERPAPI for Google searches, Jina for webpage content extraction, and OpenRouter (default: claude-3.5-haiku) for generating search queries and evaluating relevance.
      • Deep Research Agent with Motia Framework - A powerful research assistant that leverages the Motia Framework to perform comprehensive web research on any topic and question.

  • 📚 Tutorials & Guides

  • 📊 Datasets for Deep Research

    • 🛠️ Agent Frameworks

      • HotpotQA - A dataset for multi-hop question answering across documents, requiring reasoning over multiple sources.
      • Qasper - A dataset for question answering over scientific papers, ideal for evaluating research agents in academic contexts.
      • Natural Questions - A benchmark for open-domain question answering, testing agents' ability to find information from the web.
      • MS MARCO - Machine reading comprehension dataset, useful for evaluating information retrieval capabilities.
      • FEVER - Fact Extraction and VERification dataset, for evaluating fact-checking in research.
      • HotpotQA - A dataset for multi-hop question answering across documents, requiring reasoning over multiple sources.
      • Qasper - A dataset for question answering over scientific papers, ideal for evaluating research agents in academic contexts.
      • Natural Questions - A benchmark for open-domain question answering, testing agents' ability to find information from the web.
      • MS MARCO - Machine reading comprehension dataset, useful for evaluating information retrieval capabilities.
      • FEVER - Fact Extraction and VERification dataset, for evaluating fact-checking in research.

  • 🤖 Agent Technologies for Research

    • 🤖 General-Purpose AI Agents

      • AutoGPT - An open-source autonomous AI agent employing GPT-4 to tackle complex tasks by breaking them into subtasks.
      • BabyAGI - A task management system that creates and executes tasks based on user-defined objectives.
      • AgentGPT - An open-source platform for creating and deploying autonomous AI agents with pre-built templates.
      • Superagent - A tool for building personalized AI assistants specialized in web research.
      • OpenAgents - A platform for creating, hosting, and managing AI agents with user-friendly interfaces.
      • CAMEL AI - An open-source research community exploring agent scaling laws for collaboration.
      • AutoGPT - An open-source autonomous AI agent employing GPT-4 to tackle complex tasks by breaking them into subtasks.
      • BabyAGI - A task management system that creates and executes tasks based on user-defined objectives.
      • AgentGPT - An open-source platform for creating and deploying autonomous AI agents with pre-built templates.
      • Superagent - A tool for building personalized AI assistants specialized in web research.
      • OpenAgents - A platform for creating, hosting, and managing AI agents with user-friendly interfaces.
      • CAMEL AI - An open-source research community exploring agent scaling laws for collaboration.

    • 🛠️ Agent Frameworks

      • LangChain - A framework for building applications powered by large language models, with components for research workflows.
      • LangGraph - Framework for building stateful, multi-actor LLM applications extending LangChain.
      • veRL - A flexible and efficient reinforcement learning library for large language models, used by several deep research projects.
      • LangChain - A framework for building applications powered by large language models, with components for research workflows.
      • LangGraph - Framework for building stateful, multi-actor LLM applications extending LangChain.
      • veRL - A flexible and efficient reinforcement learning library for large language models, used by several deep research projects.
Programming Languages
Python 34 TypeScript 8 Jupyter Notebook 4 JavaScript 2
Categories
🤖 Deep Research Systems 53 📝 Related Papers and Resources 24 🤖 Agent Technologies for Research 18 📚 Tutorials & Guides 12 📊 Datasets for Deep Research 10
Sub Categories
🌐 Open-Source Deep Research Implementations 30 🛠️ Agent Frameworks 28 🤖 General-Purpose AI Agents 12 🔓 Commercial Deep Research Platforms 12 🔬 Specialized Research Assistants 11 📄 Deep Research Foundations 8 📄 Literature Review Systems 6 📄 Agent Systems & Collaboration 6 📄 Evaluation & Benchmarking 4
Keywords
agent 14 llm 10 gpt 10 ai 10 openai 8 python 6 artificial-intelligence 6 agents 4 rag 4 chatgpt 4 bigquery 2 duckdb 2 fastapi 2 nextjs 2 nlp 2 postgresql 2 sql 2 sqlai 2 text-to-sql 2 developer-tools 2 cli 2 claude-ai 2 llms 2 aiagentframework 2 ai-agents 2 llm-framework 2 llm-agent 2 framework 2 autogen-ecosystem 2 autogen 2 agentic-agi 2 generative-ai 2 open-source 2 assistant-chat-bots 2 code-generation 2 executable-langauge-grounding 2 language-model 2 language-model-agent 2 semantic-parsing 2 tool-learning 2 ui 2 ai-societies 2 communicative-ai 2 cooperative-ai 2 deep-learning 2 large-language-models 2 multi-agent-systems 2 agentic 2 text2sql 2 typescript 2