[Up-to-date] Awesome Agentic Deep Research Resources

Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)

Open‑source alternative to Perplexity Comet and director.ai and firecrawl combined

A multimodal agent that can interact with its own PC in a multimodal manner.

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.

A full-stack local deep research application built with LangGraph, supporting multiple LLM providers and search APIs. Powered by FastAPI + LangGraph backend and Next.js 15 + React 19 frontend, delivering a modern UI and comprehensive local research solution.

A minimalist deep research framework for any OpenAI API compatible LLMs. 简单、高度可扩展的深度研究工具，支持集成任意大型语言模型（LLM）和 MCP 工具。

The Deep Research Assistant is meticulously crafted on Mastra's modular, scalable architecture, designed for intelligent orchestration and seamless human-AI interaction. It's built to tackle complex research challenges autonomously.

OpenAI Deep Research MCP Server

Zo Computer, the world's first AI computer

A Benchmark for Evaluating Agentic Search and Deep Research Discovery, Completeness, and Traversal Depth

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.

Intelligent research automation system with three specialized AI agents for document discovery, web scraping, and automated report generation

An agent that can use browser to do deep search/research on people while bypassing captchas.

🔍 Deep Research Agent is an AI-powered research assistant that enhances online research with depth and accuracy, leveraging Google's Gemini API, web scraping, and natural language processing for comprehensive results, and it finally generates a detailed report at the end.

The Deep Research Agent is a sophisticated multi-agent system designed to conduct comprehensive research on user-specified topics within a chosen domain. It leverages AI-driven tools, including the Meta LLaMA model, to generate targeted research questions, perform in-depth analysis, and compile findings into a professional report.

A multi-agent research system built with LangGraph and TypeScript that orchestrates AI agents to perform comprehensive research.

Multi-agent modular workflow system to perform in-depth research on any prompt.

Deep research agent for Pokedex