decipher-research-agent

Overview

DecipherIt is a research assistant that transforms topics, links, and files into AI-generated research notebooks. It leverages Bright Data's MCP Server to bypass geo-restrictions and bot detection for comprehensive web scraping. The platform provides AI-powered summaries, interactive Q&A capabilities, audio overviews, visual mindmaps, and automatically generated FAQs. Built with Next.js frontend and FastAPI backend, it integrates CrewAI agents for complex research tasks.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• search_engine

  Find relevant sources based on research topics

  Try:Search for recent articles about artificial intelligenceTry:Find academic papers on climate change
• scrape_as_markdown

  Extract clean, structured content from URLs

  Try:Scrape content from this research articleTry:Convert this webpage to markdown format
• analyze_research

  Synthesize information from multiple research sources

  Try:Analyze the collected research on quantum computingTry:Summarize key findings from the scraped articles
• create_podcast_script

  Generate conversational scripts for audio summaries

  Try:Create a podcast script summarizing this researchTry:Turn this analysis into an engaging dialogue
• generate_audio

  Convert podcast scripts to audio using TTS

  Try:Generate audio from the research podcast scriptTry:Create a voiceover for this summary
• generate_faq

  Create relevant questions and answers from research

  Try:Generate FAQs based on this researchTry:Create common questions and answers for this topic
• create_mindmap

  Generate interactive, hierarchical visual mindmaps

  Try:Create a mindmap of the research findingsTry:Visualize the connections between these concepts

Note: Tools were extracted from CrewAI agent descriptions and workflow sections that explicitly document tool names and purposes.

Comparable tools

Installation

git clone https://github.com/mtwn105/decipher-research-agent.git
cd decipher-research-agent

cd client
pnpm install
cp .env.example .env.local
# Configure your environment variables
pnpm prisma generate
pnpm prisma migrate dev

cd ../backend
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv sync
cp .env.example .env
# Configure your environment variables

# Terminal 1 - Frontend
cd client && pnpm dev

# Terminal 2 - Backend
cd backend && uv run uvicorn server:app --host 0.0.0.0 --port 8001

FAQ

What does MCP server integration provide in this project?

Bright Data's MCP Server provides unrestricted web access, bypassing geo-restrictions and bot detection to enable comprehensive research from any global source.

Can I use this research assistant without web scraping capabilities?

Yes, you can still upload documents and input text directly, but web scraping functionality requires the Bright Data MCP server setup with proper API credentials.

Compare decipher-research-agent with