claude-skill

local-deep-research: AI Research

Name: local-deep-research: AI Research
Author: LearningCircuit

Get fast, local, and encrypted research tools for founders and academics, with 8.6k+ GitHub stars.

advanced⏱ 30 minutes💵 Free (self-hosted)

8,774 stars769 forksPythonQuality 8/10Updated 7/25/2026100% free · open source

What it is

Asks an AI to find answers or data for you from the internet or your own computer files.

What you can make with it

Automated reports like academic papers or company insights by searching across many sources and extracting relevant info.

How it helps

This skill helps you quickly and privately find relevant data and insights without manually searching multiple websites or files.

Real use case example

"A founder named Emma wants to understand a new market trend. She asks the AI to search across academic papers and news articles. After answering a few prompts, the AI gives Emma a concise summary of the trend and the most relevant supporting data. Emma can now use this information to inform her business strategy."

If you're new

Pick this up when you want to learn the basics of working with AI for data research, and you're not sure where to start.

If you're senior

Use this when you need to quickly and accurately aggregate data from multiple sources, especially when working with sensitive or private information.

Common confusion cleared up

Some users might confuse this skill with generic search engines, but it's designed to work with AI models to provide more accurate and context-specific results.

Best inside these AI tools

Claude Desktop

Pairs with

Claude APIStripe webhookNotion database

Why we list it on WorkflowStacks: This skill is here because it offers high-quality, private AI search capabilities at a lower cost than commercial alternatives.

What it does

Local-deep-research provides a fast, local, and encrypted research platform for founders and academics to search and analyze documents and data from various sources, including arXiv, PubMed, and private documents.

Install / run

git clone https://github.com/LearningCircuit/local-deep-research.git && cd local-deep-research

When to use it

•You need to conduct research on sensitive or private documents without relying on cloud services
•You want to utilize multiple search engines and databases, including local and cloud-based LLMs, in one platform
•You require a high level of encryption and security for your research data and results

Quick start

1Update the config.json file to include your private document paths and search engine APIs
2Run the setup script with `python setup.py` to initialize the environment
3Use the `python app.py` command to start the local-deep-research server
4Access the research platform through a web browser at the address indicated in the terminal output
5Use the web interface to create a new research project, select search engines, and input your research query

Ready-to-paste prompt

python app.py --query 'climate change mitigation' --search-engines arXiv,PubMed --private-docs /path/to/private/documents

Heads up: Make sure you have the necessary dependencies, including Python 3.8 or later and a compatible GPU, as the tool relies on GPU acceleration for optimal performance

Saves to your device