Local Deep Research

AI-powered deep research tool with multi-source search (arXiv, PubMed, web), PDF text extraction, and encrypted local storage.

Thriving · 87
87/100
Thriving

High commit volume, frequent releases and growing activity.

Maintenance 38/40
Releases 25/25
Community 15/20
Momentum 8/15

Commit activity more than 96% of tracked projects; popularity more than 77%. How this is calculated.

Commits, last 11 months

2025-10: 0 commits 2025-11: 0 commits 2025-12: 783 commits 2026-01: 864 commits 2026-02: 497 commits 2026-03: 630 commits 2026-04: 342 commits 2026-05: 433 commits 2026-06: 437 commits 2026-07: 268 commits 2026-08: 246 commits
2025-10 4500 total 2026-08
Stars9.1k
Latest releasev1.10.7 · 28 Aug 2026
Repo updated27 Sept 2026
LicenceMIT
Built withDocker, Python

Is Local Deep Research actively maintained?

Local Deep Research is under active development: 4500 commits landed over the last 11 months, averaging roughly 317 commits a month in the most recent quarter.

The most recent tagged release, v1.10.7, shipped within the last month — a current, installable version exists today.

Local Deep Research ranks #9 of 14 tracked generative artificial intelligence (genai) projects. Several better-maintained options exist in the same category — they are listed below.

What Local Deep Research actually does

Local Deep Research is a self-hosted artificial intelligence tool designed to perform investigations using multiple sources such as academic databases and the web. It extracts text from PDF documents and keeps your data secure using encrypted local storage. The application is packaged for containerised environments and is released under the MIT licence.

Best fit: Researchers and privacy-conscious professionals who need an automated tool to query literature and web sources while keeping their data strictly on local hardware.

Worth knowing: Running local AI models and multi-source search pipelines requires significant local compute resources and hardware acceleration.

Deployment notes

As a containerised Python application, you will typically need to configure persistent volumes for the encrypted storage and set up a reverse proxy to handle TLS termination.


Local Deep Research as a replacement for


Alternatives to Local Deep Research

Projects in the same categories, ordered by health score.