Local Deep Research

A research assistant that runs deep, multi-step research with local or cloud models across 10+ search engines and your own documents, with citations.

9.5k stars, 893 forks Python On GitHub since February 2025

View on GitHub How to run it

What is Local Deep Research?

Local Deep Research breaks a question into searches, reads sources and writes an answer or report with proper citations. It works with any local or hosted model, including llama.cpp, Ollama and Google, and searches more than ten engines, such as arXiv and PubMed, plus your private documents, which it can turn into a searchable knowledge base. Its database is encrypted with SQLCipher. The authors report about 95% on the SimpleQA benchmark with a 27-billion-parameter Qwen model on a single RTX 3090.

Good fit if

  • You want deep research that runs fully on your own hardware.
  • You research scientific literature and need arXiv and PubMed sources.

Look elsewhere if

  • You prefer a notebook for collecting sources and notes: Open Notebook.
  • You want a customizable research agent framework: GPT Researcher.

Before you adopt it

Local Deep Research is MIT-licensed and fully free. It is young, started in February 2025, and two thirds of recent commits come from its creator.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

Local Deep Research health: is it still maintained?

82 of 100, actively developed

  • Activity
    1,187 commits in the last 90 days, the latest on 1 November 2026.
    30 / 30
  • Contributors
    13 people wrote the latest 100 commits; the most active wrote 73% of them.
    15 / 20
  • Releases
    15 releases in the last 12 months; the latest, v1.10.7, on 28 August 2026.
    19 / 20
  • Replies to issues
    Too few recent issues from outside the team to measure, so this part gets a neutral score.
    10 / 20
  • Security practices
    OpenSSF Scorecard 8.4 of 10.
    8 / 10

Read from GitHub on 1 November 2026. How the score works

Local Deep Research license: is it open source?

Local Deep Research uses MIT, an open-source license approved by the OSI.

  1. February 2025First published on GitHub.
  2. TodayMIT.

How to run Local Deep Research yourself

Docker
Dockerfile or compose file in the repository
Compose file
docker-compose.yml: 3 services
Setup effort
2 of 5, judged from the compose file
Kubernetes
No Helm chart in the repository
Desktop and mobile
No app builds in GitHub releases
Interface languages
English only

Install instructions: the README on GitHub.

Alternatives to Local Deep Research

  • Open WebUIUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) 76 health · Open WebUI License · 157k stars
  • LibreChatEnhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API,… 74 health · MIT · 46.6k stars
  • OllamaGet up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. 89 health · MIT · 186k stars
  • LiteLLMThe fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format… 83 health · MIT · 62.5k stars
  • HarborStop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with… 80 health · Apache-2.0 · 3.3k stars

All 36 projects in AI chat & local LLMs

Questions about Local Deep Research

Is Local Deep Research open source?

Yes. Local Deep Research is published under MIT, an OSI-approved open-source license.

Is Local Deep Research still maintained?

Its health score is 82 of 100 (actively developed). It had 1,187 commits in the last 90 days, the latest on 1 November 2026, and its latest release came out on 28 August 2026.

How do I run Local Deep Research?

You can run it with Docker. The README on GitHub has the exact steps.

What are the alternatives to Local Deep Research?

Close alternatives in the AI chat & local LLMs category include Open WebUI, LibreChat, Ollama.