Research-Assistant-Agent

Name: Research-Assistant-Agent
Author: emansarahafi

emansarahafi December 1, 2025

15 copies 0 downloads

An extensible multi-agent Research Assistant that uses Gemini-powered subagents (Researcher, Analyst, Formatter) with ArXiv and custom tools to search, analyze, format, and persist academic findings, and can run locally (Flask) or be deployed to Vertex AI.

🎓 Multi-Agent Research Assistant

An advanced AI agent system designed to automate the academic research process. Powered by Google Gemini 2.5, this project uses a multi-agent architecture to search for papers, analyze publication trends, format citations, and persist findings.

🚀 Features

Multi-Agent Architecture: Specialized agents working in concert: 🕵️ Researcher: Searches ArXiv for relevant papers (supports parallel queries). 📊 Analyst: Analyzes data (e.g., publication year distribution) and generates ASCII charts. 📝 Formatter: Formats raw paper data into proper APA citations. 🧠 Root Agent: Orchestrates the workflow and manages memory.
Tools & Integrations: ArXiv API: Real-time access to millions of academic papers. Long-Term Memory: Persists findings to a JSON knowledge base. Parallel Execution: Simulates concurrent research tasks for efficiency.
Deployment Ready: Run locally via Flask API. Deploy to production on Google Cloud Vertex AI Agent Engine. Interactive testing via ADK Web UI.

🏗️ Architecture

The system follows a hierarchical multi-agent pattern:

graph TD
    User[User Query] --> Root["Root Agent (Orchestrator)"]
    Root -->|Delegates Search| Researcher[Researcher Agent]
    Researcher -->|Calls| ArXiv[ArXiv API]
    Root -->|Delegates Analysis| Analyst[Analyst Agent]
    Root -->|Delegates Formatting| Formatter[Formatter Agent]
    Root -->|Saves Data| Memory[(Long-Term Memory)]
    Root -->|Final Report| User

🛠️ Tech Stack

LLM: Google Gemini 2.5 Flash Lite
Framework: Google Agent Development Kit (ADK)
Language: Python 3.10+
APIs: ArXiv API
Deployment: Flask, Vertex AI, Docker

📦 Installation

Clone the repository:

git clone https://github.com/emansarahafi/research-assistant-agent.git
cd research-assistant-agent

**Install dependenc

Comments

More Agents

View all

agentic-ai

Agentsmith

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.

PromptPartner

308

agent-skills

Awesome Gamedev Agent Skills

Game-development Agent Skills for AI coding agents: install once and a master router loads the right skill for your engine and task. 66 original, version-pinned skills (plus a master router) in the portable SKILL.md format that runs across Claude Code, Cursor, Codex, Copilot, Gemini CLI and more, for Godot, Unity, Unreal, web and beyond.

gamedev-skills

303

ai-agents

Agentpet

A desktop pet for macOS & Windows that monitors your AI coding agents (Claude Code, Codex, Cursor, Gemini...) in real time, and grows as you code, feed it tokens, level it up, climb the leaderboard.

ntd4996

279

ai-agent

UltraGameStudio

UltraGameStudio - AI coding agent for game development: engine workflows, gameplay code, and asset generation.

wellingfeng

260

Zero

The coding agent that answers to you, your model, your machine, your rules.

Gitlawb

1,099

agent-bridge

Lucarne

Stop babysitting local AI agents. Just notifications, approve, and resume your Codex,Pi,Grok, or Claude code sessions anywhere. 0-Intrusion mobile control bridge via Telegram/微信/飞书. No hooks, no skills, no MCP.

tuchg

314