# langchain-ai/local-deep-researcher

Fully local web research and report writing assistant

Repository: https://github.com/langchain-ai/local-deep-researcher
Canonical: https://ross.abutalabs.com/products/local-deep-researcher
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-23T02:42:55+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 45
- inputs: {"age_days": 637, "days_push": 10, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9319, forks 975 (observed 2026-08-28T04:10:30.492198+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: agent-framework, rag, search-engine, llm-inference, web-scraping, nlp
- domain: artificial-intelligence, large-language-models
- platform: python, self-hosted, cross-platform
- tags: deep-research, ollama, lmstudio, local-llm, langgraph, report-generation, iterative-search, privacy, ai-agents, retrieval-augmented-generation, search, natural-language-processing

## Member repositories
- langchain-ai/local-deep-researcher (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:30.492198+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:22:30.107556+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/local-deep-researcher (fetched 2026-08-28T04:10:30.492198+00:00, sha 51ee7168443f)
- Data as of 2026-08-30T08:39:29.467469+00:00.