langchain-ai/local-deep-researcher

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

9319 stars · 975 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A fully local web research assistant that runs any LLM via Ollama or LMStudio to iteratively search the web, summarize findings, identify knowledge gaps, and produce a sourced markdown report. It is built with LangGraph and runs entirely on the user's machine.

Use cases

• research a topic with a local LLM and get a cited markdown report
• run deep research without sending data to cloud APIs
• automate iterative web search and summarization
• compare local models like DeepSeek R1 on research tasks
• build a custom deep research agent with LangGraph

When to choose

• you want private, fully local research using Ollama or LMStudio models
• you need an open-source, hackable deep research pipeline
• you want iterative search-reflection loops with source citations

When to avoid

• you need the highest-quality research from frontier cloud models
• you lack hardware to run local LLMs
• you want a polished hosted product rather than a developer tool

Facets

application · maturity active

agent-framework rag search-engine llm-inference web-scraping nlp artificial-intelligence large-language-models python self-hosted cross-platform deep-research ollama lmstudio local-llm langgraph report-generation iterative-search privacy ai-agents retrieval-augmented-generation search natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="langchain-ai/local-deep-researcher")