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

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

THEUS is Aigora’s enterprise AI research infrastructure for transforming proprietary sensory and consumer research into audit-ready insights. It uses a multimodal pipeline to extract and validate atomic facts from documents and provides page-level citations and Fact IDs for traceability. THEUS supports cross-study synthesis, research design assistance, and stakeholder-ready visualizations, and it emphasizes isolation between projects, no training on customer data, and time-limited data retention. The product also presents domain-expert AI “avatars” (e.g., an AI analyst or AI moderator) to guide exploration and insight generation from institutional research memory.

THEUS (Aigora)

theus-aigora

Enterprise AI research system that turns proprietary studies into traceable insights with fact IDs, citations, and expert avatars for synthesis.

Atelier Ruixen is a web-based AI knowledge companion focused on generative knowledge management (GKM). It is positioned as a “librarian” style agent that helps users move from vague questions to clearer, higher-signal queries, then curates and organizes an actionable reading list to support deeper understanding. The experience emphasizes turning exploration into structured insights by guiding query refinement, helping users discover relevant resources, and keeping an evolving knowledge flow for ongoing learning and research.

Atelier Ruixen

atelier-ruixen

AI knowledge companion that refines questions and curates reading lists to turn scattered info into actionable insights.

Kosmos is an autonomous AI scientist that automates data-driven discovery across domains like neuroscience, metabolomics, materials science, and genetics. Given an open-ended research objective and one or more datasets, Kosmos runs long research campaigns of up to ~12 hours, iterating between data analysis, literature search, and hypothesis generation. It uses a structured world model to coordinate agents and maintain coherence over hundreds of rollouts, typically executing tens of thousands of lines of code and reading around 1,500 papers per run before synthesizing a fully cited scientific report whose statements are traceable to code cells or primary literature. Independent scientists have estimated that a 20-cycle Kosmos run can compress roughly six months of PhD-level work into a single day, with most statements judged accurate and reproducible. Researchers can access Kosmos via the Edison Scientific platform with a credit-based pricing model, while an open-source implementation on GitHub allows teams to self-host and extend the system using multiple model providers.

Kosmos

kosmos

Autonomous AI scientist for long research campaigns that analyzes data and literature to produce fully cited scientific reports.

Lila Sciences is building what it calls “Scientific Superintelligence”: AI-driven platforms plus autonomous labs (AI Science Factories) that design, run, observe, and refine experiments across life sciences, chemistry, and materials. Founded in 2023 by Flagship Pioneering, it uses generative AI, robotics, and automation to accelerate R&D (e.g. novel therapeutics, catalysts, new materials) at a scale beyond traditional lab workflows.

Lila Sciences

lila-sciences

Platform combining autonomous labs & AI to accelerate discovery in life, chemical, and materials sciences.

AlphaSense is a market intelligence and search platform that leverages AI agents—including Generative Search, Deep Research, and Agent Interviewer—to autonomously source, analyze, and synthesize insights from over 500 million business documents and investor interview transcripts, accelerating decision-ready research workflows.

AlphaSense

alphasense

An AI-powered market intelligence platform that autonomously sources expert insights and delivers analyst-level research at scale.

Isomorphic Labs is an AI-driven drug discovery company founded by Demis Hassabis in 2021 as a spin-off from DeepMind. The company utilizes advanced AI models, including AlphaFold, to predict protein structures and interactions, aiming to revolutionize the drug discovery process. By modeling complex biological systems, Isomorphic Labs seeks to design novel therapeutics more efficiently. The company has established partnerships with pharmaceutical giants like Eli Lilly and Novartis and secured $600 million in funding to advance its mission of accelerating therapeutic development.

Isomorphic Labs

isomorphic-labs

An AI-driven drug discovery company leveraging AlphaFold to accelerate therapeutic development.

AMIE (Articulate Medical Intelligence Explorer) is a research AI system developed by Google Research and DeepMind, designed to engage in diagnostic medical conversations. Built upon the Gemini 2.0 Flash model, AMIE integrates a state-aware reasoning framework that allows it to adapt its responses based on the evolving context of a clinical dialogue. This enables AMIE to intelligently request, interpret, and reason about visual medical information, such as skin photos, ECGs, and lab results, enhancing its diagnostic capabilities. In evaluations using Objective Structured Clinical Examinations (OSCEs), AMIE demonstrated performance comparable to or exceeding that of primary care physicians in areas like diagnostic accuracy, multimodal data interpretation, and communication skills. While AMIE shows promise in augmenting clinical decision-making, further research and validation are required before real-world deployment.

AMIE

amie

A multimodal AI diagnostic agent that conducts clinical conversations and interprets medical images for accurate diagnoses.

Google's AI Co-Scientist is a multi-agent system built on Gemini 2.0, designed to function as a virtual scientific collaborator. It assists researchers by generating novel hypotheses, designing experiments, and analyzing complex datasets. The system employs specialized agents that mimic the scientific method through processes like generation, reflection, and ranking. In collaboration with institutions like Stanford University and Imperial College London, the AI Co-Scientist has demonstrated its ability to identify novel biological mechanisms and potential therapeutic targets, showcasing its potential to accelerate scientific and biomedical discoveries.

Google AI Co-Scientist

google-ai-co-scientist

A multi-agent AI system that collaborates with scientists to generate hypotheses and accelerate biomedical research.

Legora is a collaborative AI workspace designed for legal professionals to streamline document review, drafting, and research. Formerly known as Leya, Legora integrates features like Tabular Review for large-scale document analysis, a Microsoft Word add-in for seamless drafting, and agentic web search for advanced legal research. Trusted by over 250 law firms across 20 countries, including Cleary Gottlieb, Goodwin, and Bird & Bird, Legora empowers lawyers to enhance efficiency and precision in their workflows.

Legora

legora

A collaborative AI platform helping legal teams review, draft, and research faster with precision and scale.

QualiaInterviews is an AI-powered platform designed to facilitate conversational interviews for research and evaluation purposes. It enables users to design, test, and deploy interviews rapidly, allowing respondents to engage via text or speech in multiple languages. The platform features an Interview Advisor to assist in crafting effective interview guidelines, supports automatic respondent testing, and provides instant summaries and transcripts. With flexible pricing models and annual free credits, QualiaInterviews is tailored for researchers seeking scalable and nuanced data collection methods.

QualiaInterviews

qualiainterviews

AI-led platform for conducting multilingual, conversational interviews for research and evaluation.

Cresh is a multi-agent AI platform designed to analyze and enhance business ideas rapidly. By simulating expert-level research, it evaluates concepts across 33 metrics, including market viability, product strength, financial feasibility, and technical viability. Users input their ideas through an intuitive wizard, and within minutes, receive a comprehensive report detailing strengths, weaknesses, and actionable insights. Cresh aims to streamline the validation process, reducing weeks of manual research to mere minutes, thereby accelerating the journey from concept to execution.

Cresh

cresh

Multi-agent AI tool that analyzes and refines business ideas, delivering insights on viability, market fit, and risks in minutes.

AutoGLM Rumination is an AI agent developed by Zhipu AI, capable of performing deep research and tasks such as web searches, travel planning, and research report writing. Powered by Zhipu's proprietary models, including GLM-Z1-Air and GLM-4-Air-0414, it offers enhanced performance and efficiency. The agent is available for free through Zhipu's official channels, including their website and mobile app.

AutoGLM Rumination

autoglm-rumination

A free AI agent by Zhipu AI for deep research and autonomous task execution.

Closed-Source Agentic AI Category "Research AI Agents"