langchain-ai/local-deep-researcher

★ 9,151PythonAudience · developerComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((local-deep-researcher))
    What it does
      Automated web research
      Private no cloud AI
      Cited Markdown output
    Research loop
      Generate search query
      Fetch and summarize
      Identify gaps
      Repeat cycles
    AI backends
      Ollama local models
      LMStudio
    Search providers
      DuckDuckGo free
      Tavily
      SearXNG

mindmap root((local-deep-researcher)) What it does Automated web research Private no cloud AI Cited Markdown output Research loop Generate search query Fetch and summarize Identify gaps Repeat cycles AI backends Ollama local models LMStudio Search providers DuckDuckGo free Tavily SearXNG

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Run a private automated research session on any topic and receive a cited Markdown summary with source links.

USE CASE 2

Use a local AI model via Ollama for multi-step web research without paying per-query API costs.

USE CASE 3

Set up a self-hosted research workflow using DuckDuckGo, Tavily, or SearXNG as the search provider.

Tech stack

PythonLangGraphOllamaLMStudioDuckDuckGo

Getting it running

Difficulty · moderate Time to first run · 30min

Requires Ollama or LMStudio installed locally with a model downloaded, internet access needed for web searches.

In plain English

Local Deep Researcher is a tool that lets you do thorough web research using an AI model running entirely on your own computer, without sending your queries to a cloud service. You give it a topic, and it handles the research process automatically: it writes a search query, fetches results from the web, summarizes what it found, identifies what is still missing, writes a new search query to fill those gaps, and repeats this cycle as many times as you configure. At the end, it produces a written summary in Markdown format with links to all the sources it used. The AI that drives the research runs locally through Ollama or LMStudio, which are apps that let you download and run open AI models on your own machine. This means your research stays private, works without an internet connection for the AI part, and has no per-query costs from an AI provider. You still need internet access for the actual web searches. For web search, the tool defaults to DuckDuckGo, which needs no API key. You can also connect it to other search providers like Tavily, Perplexity, or SearXNG if you have accounts with those services. Setup involves cloning the repository, copying an example configuration file, choosing your local AI model, and optionally picking a search provider. The application then runs through LangGraph Studio, which is a visual interface for running and monitoring this kind of multi-step AI workflow. This project is aimed at developers and technically comfortable users who want private, automated research without relying on a paid AI service. You need to be comfortable installing software, running terminal commands, and editing configuration files to get it working.

Copy-paste prompts

Prompt 1

I cloned local-deep-researcher and installed Ollama. Walk me through running my first research session on climate policy.

Prompt 2

Show me how to configure local-deep-researcher to use Tavily instead of DuckDuckGo as the search backend.

Prompt 3

How do I increase the number of research cycles in local-deep-researcher to get a more thorough final report?

Prompt 4

Which Ollama models work best with local-deep-researcher for factual research? Walk me through the tradeoffs between speed and accuracy.

Open on GitHub → Explain another repo

← langchain-ai on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.