Research AI Agents Agentic AI directory: Find intelligent solutions with open-source code from premier AI agencies and automation specialists globally.

Open-Source Agentic AI in "Research AI Agents" Category

Cell2Sentence (C2S) is an open-source framework from the van Dijk Lab that represents single-cell RNA-seq profiles as textual “cell sentences” (genes ordered by expression), enabling large language models to natively model biology. The project includes code, docs, and open models (C2S-Scale) released with Google Research/DeepMind for state-of-the-art single-cell tasks like cell typing, perturbation prediction, and virtual cell generation.

Cell2Sentence

cell2sentence

Open-source framework that turns single-cell gene expression into 'cell sentences' so LLMs can analyze and generate biology insights.

OneQuery is an AI-powered web agent that automates the process of browsing and extracting information from the internet to answer user queries. Utilizing technologies like Playwright for browser automation and OmniParser for webpage analysis, OneQuery can navigate websites, interpret content, and retrieve relevant data. It offers features such as a lightning-fast Zig-based browser, worldwide proxy support, and a job queuing system. Users can deploy OneQuery via a hosted solution or set it up locally, making it a versatile tool for tasks like data scraping, content aggregation, and real-time information retrieval.

OneQuery

onequery

An AI web agent designed to find answers to any question by browsing and extracting information from the internet.

Data-to-Paper is an innovative AI-powered framework designed to automate the entire scientific research process. By integrating Large Language Models (LLMs) with rule-based agents, it guides the transformation of raw data into complete, transparent, and verifiable scientific manuscripts. The platform autonomously handles tasks such as hypothesis generation, research planning, analysis code writing and debugging, result generation and interpretation, and manuscript drafting. This approach aims to accelerate scientific discovery while upholding essential values of transparency, traceability, and verifiability in research.

Data-to-Paper

data-to-paper

An AI-driven platform automating the transformation of raw data into comprehensive, traceable scientific papers.

FutureHouse is a nonprofit organization on a 10-year mission to create semi-autonomous AI systems, known as AI Scientists, aimed at expediting scientific discovery and providing global access to cutting-edge expertise in science, medicine, and engineering. By integrating advanced AI technologies, FutureHouse seeks to enhance the efficiency and effectiveness of scientific research, enabling rapid advancements in understanding complex biological systems and other scientific domains. Their initiatives include the development of tools like PaperQA2, an open-source AI system designed to search academic databases and summarize relevant scientific literature, thereby facilitating informed decision-making and innovation.

FutureHouse

futurehouse

A philanthropically-funded initiative dedicated to developing semi-autonomous AI systems to accelerate scientific research and democratize access to advanced scientific expertise.

GPT Researcher is an open-source platform designed to automate the research process by deploying AI agents capable of performing extensive online investigations. Utilizing large language models (LLMs) such as GPT-4, it generates research questions, employs crawler agents to gather information from over 20 web sources per task, and synthesizes the data into coherent reports. This approach addresses challenges related to misinformation, speed, determinism, and reliability by enabling parallelized agent work, resulting in stable performance and increased efficiency. GPT Researcher aims to empower individuals and organizations by providing accurate, unbiased, and factual information through AI-driven research.

GPT Researcher

gpt-researcher

An open-source autonomous agent that conducts comprehensive online research by scraping, filtering, and aggregating information from multiple web sources to generate detailed reports.

ChemCrow is an AI-powered platform developed by researchers at EPFL, designed to enhance chemical research by integrating 18 expert-designed tools. Utilizing large language models (LLMs) like GPT-4, ChemCrow autonomously plans and executes tasks such as chemical synthesis, literature extraction, and molecular analysis. This integration enables efficient synthesis planning and execution, assisting in the discovery of new compounds and materials. By democratizing access to complex chemical knowledge, ChemCrow lowers barriers for non-experts while augmenting the toolkit available to veteran chemists, thereby accelerating research and development in pharmaceuticals, materials science, and beyond.

ChemCrow

chemcrow

An AI-driven chemistry agent that integrates multiple specialized tools to autonomously perform complex chemical research tasks across organic synthesis, drug discovery, and materials design.