MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 80.8% Avg@8 score on the challenging GAIA benchmark.

MiroFlow is an agent framework that enables tool-use agent tasks, featuring a reproducible GAIA score of 82.4%.

[ICML 2025] ResearchTown: Simulator of Human Research Community

DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.

FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth

Gemini Deep Research Agent CLI

The CrewAI Research Assistant is a powerful tool designed to help users explore any topic using AI Agents. Built with CrewAI, Exa, and Streamlit, this assistant supports multiple large language models (LLMs) and offers advanced answering capabilities through Exa. It visualizes the research process in real-time, generates structured research reports

Deep researcher using langchain-ollama with deepseek-1.5b model.

An autonomous research agent that synthesizes detailed reports by combining dynamic planning, unsupervised topic discovery (PCA/KMeans) HyDe (hypothetical doc embeddings), and a self-correcting reflexion loop.

A multi-phase pipeline for automated academic research. The system discovers papers, constructs a vector-indexed library, generates structured documents with inline citations, and iterates through peer review until acceptance criteria are met.

research agent, which helps fetch and summarize the articles from internet

A multi-agent AI research assistant built with OpenAI Agents SDK and Firecrawl for deep, automated web research.

🧠Research Agent - 🔍 An AI-powered Research Agent to find, summarize, and analyze research papers using Replicate's LLMs. Supports web search, PDF summarization, and hypothesis generation – all in one Streamlit app.

full-stack research assistant (FastAPI + OpenAI + SerpAPI) with live web search, citation generation, and content filtering to reduce hallucinations.

Hands-on customization of DeepAgents (LangGraph/LangChain): a Research Agent demo (Python + notebook) with planning, subagents, tool loops, and report writing.

A Streamlit-based Web Research Agent that summarizes online content using Python.

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

Open source code for AlphaFold 2.

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report